sumik5
218 verified skills218 total stars
converting-content
コンテンツ変換ガイド（画像ベースEPUB→テキストOCR変換・LM Studio英日翻訳）。 Use when converting image-based EPUBs to text or translating content with LM Studio. pandoc、recognize-image.py OCR、ローカルLLM翻訳ワークフローを含む。
documentation1
developing-go
Comprehensive Go development guide covering clean code practices, design patterns (GoF/concurrency/DDD), and internals (type system/memory/reflection). MUST load when go.mod is detected or Go code is being written. Covers naming, error handling, concurrency, testing, project structure, function design, data structures, refactoring strategies, GoF patterns, architectural patterns, type system internals, and performance optimization. For application logging design and structured logging patterns, use implementing-observability. For language-agnostic clean code/SOLID and refactoring, use writing-clean-code. For Clean Architecture/DDD strategic design, use applying-clean-architecture. For algorithm/data-structure complexity analysis, use solving-algorithms.
development1
developing-with-ai
AI-assisted development methodology covering prompt engineering, context engineering, code generation workflows, quality assurance, collaborative debugging, agent collaboration patterns, LLM dialogue design patterns (8 conversational patterns, Grammar of Intention), team LLM adoption workshops, and role-specific augmentation (Dev/PO/Coach/Manager). MUST load when working with AI coding tools or discussing AI-assisted development practices. Use when crafting prompts for code generation, managing AI context, reviewing AI-generated code, coordinating multi-agent workflows, or designing structured LLM dialogues.
tools1
creating-flashcards
Creates Anki flashcards from EPUB/PDF files via Anki MCP Server, covering MCP setup, deck/note-type management, and bulk import with HTML formatting. Use when converting textbooks, question banks, or study materials into spaced repetition flashcards, or when managing Anki cards via MCP tools. Covers full workflow: MCP setup → file conversion → content analysis → batch card creation. For MCP server/client development, use developing-mcp instead. For EPUB image compression/size reduction use compressing-epub-images; for image-EPUB→text OCR conversion use converting-content.
tools1
developing-databases
Comprehensive database development guide covering relational design (ER modeling, normalization, PostgreSQL implementation), SQL antipatterns (25 patterns with detection signals and solutions), database internals (storage engines B-tree/LSM, distributed systems, consensus algorithms), and PostgreSQL operations (server config, extensions, query tuning, MVCC/VACUUM, backup/PITR, replication/HA, monitoring). Use when designing database schemas, writing SQL queries, reviewing data models, choosing storage engines, tuning PostgreSQL performance, managing backup/replication, or debugging distributed system behavior. Replaces: designing-relational-databases, avoiding-sql-antipatterns, understanding-database-internals.
tools1
pursuing-simplicity
Discipline for recognizing and cutting self-induced complexity to keep software sustainable and effective. Covers the orient-step-learn loop and a rubric for judging which option is simpler (easier to understand, fewer parts, reflects the problem); technology minimalism (dependency decision chains, minimal-and-stable framework choice, feature-as-liability restraint, incremental delivery, conservative tech adoption); personal automation and environment mastery (automate-first, day-zero deploy, terminal/shell/editor fluency, reproducible machine provisioning); collaboration for simplicity (asynchronous decoupled work, lean meetings, skill spreading, dialectical reasoning, empathy, listening to code, analogies); and data-driven simplification with error-revealing code layout. Use when code or workflows feel more complicated than warranted, when weighing a new dependency/framework/feature, when setting up developer tooling, or when untangling logic.
tools1
developing-fullstack-javascript
Full-stack JavaScript development covering backend (NestJS/Express), frontend (React), deployment (CI/CD), and quality; also covers JavaScript language fundamentals (types, closures, prototypes, async/await, modules, and metaprogramming). MUST load when package.json contains Express, NestJS, or similar backend frameworks. Covers API design, state management, caching, and testing. Also use when working with JavaScript language-level concerns — type coercion, scoping, this binding, Promise patterns, Proxy/Reflect, or iterator protocols. Also covers V8 engine internals (hidden classes, inline caches, string/number repr), event loop model, JS/Node error model, and Express 5 + Drizzle ORM CRUD APIs.
development1
converting-content
コンテンツ変換ガイド（画像ベースEPUB→テキストOCR変換・LM Studio英日翻訳）。 Use when converting image-based EPUBs to text or translating content with LM Studio. pandoc、recognize-image.py OCR、ローカルLLM翻訳ワークフローを含む。For image compression/size reduction use studio:compressing-epub-images; for Anki flashcards use creating-flashcards.
documentation1
building-nodejs-services
Build backend services, web servers, and CLI tools on the Node.js runtime using the Fastify framework. Use when package.json contains fastify, when defining Fastify routes, plugins, hooks, or JSON-schema validation, or when working with Node runtime internals (event loop phases, libuv, streams, buffers, clustering, worker threads, blocking-the-event-loop avoidance) beyond browser-level JavaScript. Covers Fastify routing and request/reply, schema-based validation and serialization (AJV/JSON Schema), the plugin and encapsulation model, Pino logging, server-side rendering with EJS/Handlebars, RESTful CRUD APIs, persistence with Mongoose/Sequelize/SQLite/Redis, session/cookie and JWT authentication flows, message queues (RabbitMQ/amqplib), CLI tooling (process stdio, promisify, CSV), external data integration (fetch, feed aggregation, scraping via cheerio/Puppeteer), email and generative-AI service integration, and project scaffolding (npm init, ESM, node --watch).
tools1
applying-apple-hig
What: Apple公式のHuman Interface Guidelines（HIG）を基準に、iPhone・iPad向けiOS／iPadOSアプリのUI/UXを設計・実装・レビューし、SwiftUI／UIKitのレイアウト、ナビゲーション、コンポーネント、入力、アクセシビリティを判断する。REQUIRED when iPhone、iPad、iOS、iPadOS、SwiftUI、UIKit、HIG、App StoreのUI品質、画面設計、デザインレビュー、Dynamic Type、VoiceOver、キーボード、ポインタ、Apple Pencilを扱うとき。Differentiation: 技術アーキテクチャ、状態・データフロー、性能、テスト、Privacy Manifest、署名、TestFlight、配布はdeveloping-ios-appsを使い、UI実装では両方を併用する。Flutter独自のMaterial/CupertinoウィジェットによるクロスプラットフォームUI構築はdeveloping-flutter-appsを使う。
development1
auditing-app-store-compliance
What: iOS/iPadOS/macOSアプリのコードベース（Info.plist、entitlements、Xcodeプロジェクト設定、ソースコード）をApp Review Guidelines（Safety/Performance/Business/Design/Legal）、In-App Purchase実装（StoreKit 2）、macOS/Mac App Store固有要件に照らして実地検査し、「必須(Blocking)/推奨/手動確認要」の3段階で判定した審査提出可否レポートを作成する。REQUIRED when 審査提出前の最終チェック、リリース可否判断、既存コードベースの審査対応状況監査を行うとき。Differentiation: App Review Guidelines本文の解説、Privacy Manifest詳細、署名・TestFlight・技術実装手順はdeveloping-ios-appsを使い、HIGに基づくUI/UX判断はapplying-apple-higを使う。本スキルは実際のプロジェクトファイルを検査するアクション型の監査に特化し、ガイドライン本文の再解説はしない。FlutterアプリがビルドするiOS/macOSのXcodeプロジェクトにも同様に適用できる。
development1
developing-dart
Guides modern Dart language development, including the type system, null safety, variables, collections (List/Set/Map, Iterable, where/map/reduce), functions and functional programming (closures, higher-order functions, composition, Future/Stream), object-oriented programming (classes, constructors, inheritance, abstract classes, mixins, encapsulation, generics, enums, extension methods, operator overloading), asynchronous programming (async/await, isolates), error handling and debugging, the Dart test package, pub package management, CLI and web runtimes, and tooling (Dart SDK, DartPad, analyzer, formatter). REQUIRED when writing, reviewing, or modifying Dart code, or when pubspec.yaml or .dart files are present. For building Flutter UIs, widgets, state management, navigation, or shipping cross-platform apps, use developing-flutter-apps. For native iOS/iPadOS apps in Swift/SwiftUI, use developing-ios-apps instead.
tools1
developing-ios-apps
Guides production iPhone and iPad app development for iOS and iPadOS, including Xcode setup, SwiftUI/UIKit selection and interoperability, architecture, state and data flow, app and scene lifecycle, persistence, networking, background work, notifications, testing, performance, Privacy Manifest, Required Reason API, signing, TestFlight, App Store review, and release. REQUIRED when creating, implementing, modifying, testing, reviewing, or shipping an iOS/iPadOS app. For Apple HIG, UI/UX, navigation, layout, components, input, visual design, or accessibility decisions, use applying-apple-hig; UI implementation MUST use both skills. For codebase-level submission-readiness auditing (Info.plist/entitlements/source-code inspection with a pass/fail report), StoreKit 2 implementation-level IAP compliance, or macOS/Mac App Store-specific technical requirements (sandboxing, notarization, Hardened Runtime), use auditing-app-store-compliance instead. For cross-platform Flutter/Dart apps, use developing-flutter-apps.
development1
compressing-epub-images
EPUB ファイル内の画像（主にスキャン本の JPEG）を ImageMagick（magick）で再エンコード（quality 調整）・リサイズし、PNG は pngquant で圧縮してファイルサイズを削減するスキル。AskUserQuestion で圧縮レベル選択フローを提供し、実測サンプリングから予測サイズを提示してからユーザーに選ばせる。mimetype 先頭・無圧縮での再 zip など EPUB 規格を守った再パッケージ手順を含む。 Use when: EPUB ファイルが大きく画像圧縮で削減したい時、スキャン本（画像ベース EPUB）の容量を減らしたい時、Kindle などの電子書籍リーダーに転送する前にサイズ最適化したい時。 画像ベース EPUB（スキャン本）と通常 EPUB の両方に対応。書誌情報・xhtml・css は触らず画像のみ再エンコード。For OCR text conversion use certificate:converting-content; for Anki flashcards use certificate:creating-flashcards.
development1
developing-aws
AWS development guide covering serverless (Lambda, API Gateway, DynamoDB), CDK, EKS, ECS/Fargate, SRE, FinOps, security (IAM, VPC, KMS, GuardDuty), AI/ML (Bedrock, RAG, SageMaker), databases (Aurora, ElastiCache), data engineering (Glue, Athena, Redshift), 57 Cloud Design Patterns, VPC architecture, enterprise architecture (multi-account, Landing Zone, Cognito), cloud migration (7R, DMS), and HA/fault tolerance. Use when working with AWS services, CDK infrastructure, or serverless applications. MUST load when working with AWS services, detected by aws-cdk or @aws-sdk in package.json, cdk.json, samconfig.toml, serverless.yml, template.yaml (SAM), or eksctl configs. For vendor-neutral security architecture methodology use architecting-security instead.
development1
practicing-software-engineering
Comprehensive SW engineering practices covering project foundations (fast feedback, small steps, DORA metrics), team organization (Team Topologies, 4 types), pair programming (4 patterns), developer habits (GREAT framework), IC effectiveness mindset (outcomes vs outputs, strategic prioritization), career-stage skills (junior to staff, IC vs management), cross-functional influence (PM/design, authority-free leadership), 20 anti-patterns (15 individual + 5 team-level), sustainable performance (burnout, remote work), and AI-enhanced workflows (daily AI, 90-day rollout). Use when starting projects, organizing teams, for IC effectiveness, career growth, or team AI culture.
development1
software-security
Project CodeGuard-based secure-by-default coding rules (23 rule files spanning injection, authentication/MFA, cryptography, secrets, authorization, sessions, cloud/Kubernetes, IaC, supply chain, MCP, mobile, logging, privacy) for writing and reviewing secure code across 25+ languages. Use when writing, reviewing, or modifying code, handling user input/credentials/cryptographic operations, or configuring cloud infrastructure/CI-CD/containers. Japanese-localized adaptation of cosai-oasis/project-codeguard (CC-BY-4.0). For organizational AI-development security strategy use ai:securing-ai-development; for dynamic authorization model design (ABAC/ReBAC/Cedar) use cloud:implementing-dynamic-authorization; for OWASP-oriented code security and penetration testing use securing-code. For architecture-level security design methodology use cloud:architecting-security instead.
tools1
developing-flutter-apps
Guides production Flutter app development with Dart targeting iOS, Android, web, and desktop from a single codebase, including project setup, the widget system (Stateless/Stateful, Material and Cupertino), layout, theming and animation, state management (setState, Provider, Riverpod, BLoC/Cubit, Redux, GetX), navigation and routing (Navigator, go_router, auto_route), networking and backends (http, dio, REST, Firebase, GraphQL), local persistence, responsive multi-platform design, architecture patterns (Clean Architecture, BLoC, MVVM), the pub.dev package ecosystem, widget and integration testing, performance optimization, and build and store release. REQUIRED when creating, implementing, modifying, testing, or shipping a Flutter app, or when pubspec.yaml lists the flutter SDK. For the Dart language itself (types, null safety, OOP, async, collections), use developing-dart. For native iOS/iPadOS apps in Swift/SwiftUI, use developing-ios-apps. For Apple HIG UI/UX decisions, use applying-apple-hig.
development1
optimizing-search-visibility
生成AI時代の検索可視性最適化リファレンス。古典SEO（Googleランキング要因・E-E-A-T・検索意図・トピッククラスター・Core Web Vitals(LCP/INP/CLS)・クロール/インデックス/レンダリング・構造化データ・hreflang・キーワードリサーチ・オンページ最適化・被リンク・ローカル/EC）、生成AI活用（制作支援プロンプト・プロンプトエンジニアリング・カスタムGPT・RAG・エージェント自動化・周辺業務）、AI検索最適化（AI Overviews/AI Mode・GEO・AEO・LLMO・llms.txt・AI引用構造・AI引用源最適化）、計測（GA4/GSC・KPI/ROI・ゼロクリック計測限界・AI可視性計測(Mentions/Citations分離・プロンプトトラッカー・自己診断)）、リスクとガバナンス（Scaled content abuse・著作権・ハルシネーション・Googleポリシー・開示規制・社内AIガバナンス）を統合。SEOライティング・運用診断ロードマップも収録。Use when planning SEO strategy, auditing technical SEO, doing keyword/content research, optimizing for AI Overviews/GEO/AEO/LLMO, designing SEO KPIs, or governing AI-generated content risk. For eliminating AI smell from prose use devkit:writing-effective-prose. For marketing copy/headlines use creating-content. For RAG/LLMOps/prompt architecture use ai:designing-genai-patterns. For web AI/RAG implementation use ai:integrating-ai-web-apps. For querying live GA4 data via the analytics MCP use google:analyzing-with-google-analytics.
tools1
developing-firebase
Firebase platform development guide covering Authentication (email/social/session), Firestore & Realtime Database (modeling/queries/security rules), Cloud Storage, Cloud Functions (triggers/scheduling), Hosting, Analytics (events/BigQuery), FCM push notifications, Remote Config, Test Lab, Performance Monitoring, Dynamic Links, App Distribution, AdMob, and Extensions. MUST load when firebase, @firebase, or firebase-admin packages detected, or firebaseConfig/firebase.json/firestore.rules files present. For GCP infra→developing-google-cloud. For Next.js integration→developing-nextjs. For REST API design→developing-web-apis.
tools1
choosing-api-styles
Decision guide for choosing among API styles — REST, GraphQL (query-based), gRPC (RPC), webhooks (callback), WebSocket (bidirectional), messaging (broker-based), and web feeds — based on trade-offs in communication type, transmission mode, responsiveness, binary-data support, and development effort. Covers API concepts (message, transmission modes, lifecycle, API-as-a-product), protocol foundations (HTTP/1.1 vs HTTP/2 vs HTTP/3 QUIC, TCP head-of-line blocking), cross-style patterns (pagination, rate limiting, caching, retries, versioning, OWASP), and per-style trade-offs with a when-to-use decision matrix. Use when selecting or comparing API styles — REST vs GraphQL vs gRPC vs realtime/event-driven — or justifying an architecture decision. For REST API design, testing, or gRPC .proto specs, use developing-web-apis. For Express/NestJS implementation, use developing-fullstack-javascript. For MCP protocol, use lang:developing-mcp. For microservice/infrastructure trade-offs, use cloud:architecting-infrastructure.
tools1
developing-fullstack-javascript
Full-stack JavaScript development covering backend (NestJS/Express), frontend (React), deployment (CI/CD), and quality; also covers JavaScript language fundamentals (types, closures, prototypes, async/await, modules, and metaprogramming). MUST load when package.json contains Express, NestJS, or similar backend frameworks. Covers API design, state management, caching, and testing. Also use when working with JavaScript language-level concerns — type coercion, scoping, this binding, Promise patterns, Proxy/Reflect, or iterator protocols. Also covers V8 engine internals (hidden classes, inline caches, string/number repr), event loop model, JS/Node error model, and Express 5 + Drizzle ORM CRUD APIs. For Fastify-based services, Node.js runtime internals (libuv, streams, clustering, worker threads), CLI tools, message queues, or standalone Node project scaffolding, use building-nodejs-services instead.
tools1
developing-terraform
Terraform IaC development with HCL syntax, module design, state management (S3/GCS remote backends, workspaces, drift handling), Terragrunt wrapper patterns, testing (Terratest, Terraform Testing Framework), CI/CD (GitHub Actions, GitOps, security scanning), custom provider development (Plugin Framework), and CDKTF. MUST load when .tf files or terragrunt.hcl are detected, or go.mod contains 'terraform'. Covers AWS/GCP infrastructure patterns and mise task automation. For Docker infrastructure, broader DevOps methodology, and IaC tool comparison, use practicing-devops instead. For AWS CDK (TypeScript/Python IaC), use developing-aws instead.
tools1
implementing-as-tachikoma
Operates as Tachikoma Agent (Implementation Worker) performing actual code implementation. Use when receiving task assignments from Claude Code for implementation work, test creation, or documentation. Adapts to frontend, backend, or testing roles based on task assignment.
development1
gws-slides
Google Slides: Read and write presentations.
development1
creating-flashcards
Creates Anki flashcards in bulk from EPUB/PDF/scanned-book files via Anki MCP Server or AnkiConnect API, covering MCP setup, OCR for image-based sources (Apple Vision first choice, local VLM fallback), deck/note-type management, and batch import with HTML formatting. Use when converting textbooks, question banks, or study materials into spaced repetition flashcards, or when managing Anki cards via MCP tools. Covers full workflow: MCP setup → file conversion (pandoc / OCR) → content analysis → batch card creation. For MCP server/client development, use lang:developing-mcp instead. Also supports fast-paths for pre-structured exam JSON collected by collecting-kentei-lab-exams (kentei-lab schema: exam_title/slug/questions, via scripts/kentei_lab_import.py), collecting-whizlabs-exams (whizlabs schema: course_title/quiz_title/quiz_id/questions, via scripts/whizlabs_import.py), and collecting-studying-exams (studying schema: course_title/category/subject_title/practice_id/questions, via scripts/studying_import.py), skipping AI structure inference in all three cases. For EPUB image compression/size reduction use studio:compressing-epub-images; for standalone image-EPUB→text OCR conversion (no flashcard creation) use converting-content.
tools1
managing-keycloak
Comprehensive Keycloak identity and access management guide covering OIDC/SAML protocols, SSO, Realms, Clients, Users, Roles, authentication flows, MFA, authorization policies, JWT token management, application integration (Java/Node.js/Spring Boot), Docker/Kubernetes deployment, clustering, and SPI extensions. MUST load when keycloak.json, keycloak.conf, or Keycloak-related dependencies are detected. For general security practices, use securing-code instead. For Cedar/ABAC/ReBAC authorization models, use implementing-dynamic-authorization instead.
tools1
designing-genai-patterns
32 production-grade GenAI design patterns covering content control (Logits Masking, Grammar, Style Transfer), RAG architecture, model capabilities (Chain of Thought, Adapter Tuning), reliability (LLM-as-Judge, Reflection, Prompt Optimization), agentic systems (Tool Calling, Multiagent Collaboration), deployment optimization (SLM, Prompt Caching, Inference Optimization), safety guardrails (Self-Check, Guardrails), RAG implementation (11 source types, chunking, vector stores), and LLMOps/AgentOps (maturity L0–2, Tool/Agent Registry, Memory Governance, LLM metrics, LLMSecOps). Also covers AI performance (GPU/CUDA, LLM inference) via PERF- references. Use when designing GenAI applications, choosing RAG strategies, implementing agent architectures, optimizing LLM reliability, or operating AI systems in production. For web AI (Vercel AI SDK, LangChain.js), use integrating-ai-web-apps. For GCP-specific ML (BigQuery ML, Vertex AI), use developing-google-cloud.
tools1
collecting-studying-exams
studying（スタディング, member.studying.jp）のコースレッスン一覧URLから、配下の「スマート問題集」 「セレクト過去問集（学科試験対策・実技試験対策）」の全問題（問題文・選択肢・正解・解説）を科目単位で 取得し、1科目1JSONファイルに保存する。出力は creating-flashcards スキルへ渡して科目ごとに Anki フラッシュカード化できる。 Use when studying のコースレッスン一覧URL（https://member.studying.jp/course/id/<course_id>/ 形式） を渡され「問題を全部保存したい」「Anki カードにしたい」等と言われたとき。 補足トリガー: studying, スタディング, 資格試験, スマート問題集, セレクト過去問集, 問題集, JSON 保存, Anki 連携。 ブラウザ操作自体の汎用ガイドは web:automating-browser、E2E テストは web:testing-e2e-with-playwright を使う。本スキルは studying 専用の収集ワークフロー + bundled script（scripts/collect-studying.sh） ＋ログイン認証を提供する。
development1
operating-gitlab
GitLab operations via the glab CLI (GitLab official command-line tool). Comprehensive reference for all command groups: auth (login, tokens, self-managed --hostname, CI job tokens, GITLAB_TOKEN), mr (create, list, diff, approve, merge, rebase, notes), issue and incident, ci/cd pipelines and jobs (run, trace, lint, retry, artifacts, schedules, variables), repo and project management (clone, fork, mirror, members), release (create, upload assets), api (REST and GraphQL), label, milestone, snippet, runner, securefile, ssh/gpg/deploy keys, and end-to-end workflows. Use when operating on GitLab from the terminal, automating GitLab tasks, or composing glab commands for merge requests, pipelines, issues, releases, or API calls. For GitHub operations use the gh CLI and the pull-request command instead; for commit message wording use writing-conventional-commits; for code review methodology use reviewing-code.
tools1
writing-user-stories
Guides effective user story creation for software projects covering story templates (As a.../I want.../So that...), common mistakes, technical requirements to story conversion, acceptance criteria writing, and story splitting techniques. Use when writing user stories, converting technical requirements to stories, or improving backlog quality. For product management practices (PRD, roadmap, prioritization), use practicing-product-management instead.
testing1
building-design-systems
Design system construction, governance, Figma implementation, and practical launch/adoption methodology covering system foundations, pattern taxonomy (CEV naming), organizational adoption (consensus building, proposal templates), pattern library operations, UI pattern catalog (20+ patterns), Figma variable/token architecture, incremental launch, buy-in strategies, content creation, CI/CD automation, update notification framework (6 steps), operational ownership patterns, case studies, and self-assessment. Use when architecting, evaluating, or restructuring a design system, planning organizational adoption, building a pattern library, constructing a design system within Figma, starting a DS from scratch, or creating design system content. For component styling, use web:styling-with-tailwind instead. For design-to-code, use web:implementing-design instead. For frontend codegen, use web:designing-frontend instead.
tools1
developing-nextjs
Next.js 16.x development guide covering App Router, Server Components, Turbopack, React Compiler, proxy.ts, Cache Components, opt-in caching APIs (updateTag/revalidateTag/refresh), strict TypeScript, Tailwind CSS 4.x, Prisma 7.x, Zod 4.x, Vitest 4.x, Playwright, Docker. MUST load when package.json contains 'next' or next.config.* is detected. For React-specific concerns (internals, performance rules, animation, RTL testing) and React Router based routing/client-side auth/i18n architecture, use developing-react. SaaS構築パターン（認証・決済・AI統合）を含む。 For enterprise multi-tenant SaaS, use cloud:building-multi-tenant-saas. For AI integration with Vercel AI SDK and LangChain.js, use ai:integrating-ai-web-apps. For application logging design and structured logging patterns, use cloud:implementing-observability. For Tailwind CSS methodology, component design patterns, and customization, use styling-with-tailwind. For Firebase platform details (Auth/Firestore/Rules)→cloud:developing-firebase.
tools1
testing-code
REQUIRED for all feature implementations. Automatically load when writing or reviewing tests. Enforces TDD with AAA pattern, actual/expected variables, and 100% coverage goal for business logic. Covers Vitest, Jest, Playwright, AI-augmented testing. Includes the Four Pillars of good tests (regression protection, refactoring resistance, fast feedback, maintainability), three testing styles (output/state/communication-based), code classification, test anti-patterns, test pyramid, mock patterns (stub/spy/MSW), integration testing, and testable design (DI). Covers ATDD/BDD/flaky-test elimination. For RTL patterns, use web:developing-react. For Web API testing, use web:developing-web-apis. For A/B testing, use product:practicing-product-management. For full-stack test strategy (exploratory/visual/perf/a11y/mobile), use testing-strategies. For team organization, use practicing-software-engineering. For Vitest 4.x specifics (migration, projects, Browser Mode, coverage config), use web:testing-with-vitest.
development1
designing-data-visualizations
Comprehensive data visualization principles covering chart type selection (amounts, distributions, proportions, relationships, time series, geospatial, uncertainty), color scales (qualitative/sequential/diverging, colorblind-safe palettes), design best practices (proportional ink, overplotting remedies, redundant coding, multi-panel figures, avoiding 3D), data storytelling, and image format (bitmap/vector, DPI) and visualization software selection. Use when creating charts, graphs, dashboards, or any visual data representation, or when choosing chart types, color palettes, or reviewing visualization quality. For UI/UX design principles, use designing-ux instead. For technical diagrams (flowcharts, architecture), use studio:creating-diagrams instead.
development1
mastering-typescript
Comprehensive TypeScript guide covering type system, advanced patterns, design patterns (GoF Creational/Structural/Behavioral), functional/reactive programming, framework integration (React/Angular/Vue/Express), and 83 best practice decision criteria. MUST load when working in TypeScript projects detected by tsconfig.json. Covers Generics, Conditional Types, type inference, type design, SOLID/DDD, anti-patterns, and migration tips. Includes type safety rules (any prohibition, type guards, strict mode), compiler behavior/modern tsconfig (satisfies), TS 5.0 decorators, type-safe error handling, performance/project scaling, contract evolution (Zod validation), IDE-driven workflow and common pitfalls, and TSDoc/TypeDoc docs generation. For Next.js-specific TS config/patterns, use web:developing-nextjs. For React component typing, use web:developing-react. For JavaScript language fundamentals, use web:developing-fullstack-javascript. For language-agnostic clean code, use writing-clean-code.
development1
building-design-systems
Design system construction, governance, Figma implementation, and practical launch/adoption methodology covering system foundations, pattern taxonomy (CEV naming), organizational adoption (consensus building, proposal templates), pattern library operations, UI pattern catalog (20+ patterns), Figma variable/token architecture, incremental launch, buy-in strategies, content creation, CI/CD automation, update notification framework (6 steps), operational ownership patterns, case studies, and self-assessment. Use when architecting, evaluating, or restructuring a design system, planning organizational adoption, building a pattern library, constructing a design system within Figma, starting a DS from scratch, or creating design system content. NOT for component styling (applying-design-guidelines), design-to-code (implementing-design), frontend codegen (designing-frontend), or Tailwind config (styling-with-tailwind).
tools1
applying-behavior-design
Behavioral design methodology for products that change user behavior using CREATE Action Funnel (Cue, Reaction, Evaluation, Ability, Timing) and three strategies (cheat, habit, conscious action). Use when designing product features that aim to change user habits, increase engagement, or guide users toward beneficial actions. For visual UI/UX design principles, use designing-ux instead. For training program design and facilitation methodology, use designing-training instead. For human-centered design thinking process (user research, ideation, prototyping), use designing-ux instead.
development1
converting-agents-to-codex
Claude Code Agent定義（.md）をCodex subagent定義（agents/*.toml）に変換するガイド。 フィールドマッピング・developer_instructions変換・skillsのdescription自動ロード方式・モデルtier-map（model_reasoning_effort）・config.toml/mcp_servers設定・AGENTS.mdルーティング統合・検証手順・よくある失敗パターンを網羅。 Use when converting Claude Code agents to Codex format, migrating agent definitions, or setting up Codex subagents. Triggers: "agentをcodexに変換", "codex agent変換", "agent migration"。 For Codex-side agent orchestration (Wave並列実行・max_threads運用), use orchestrating-codex instead. For authoring new Claude Code plugins/agents/skills, use authoring-plugins instead.
tools1
authoring-plugins
Claude Code and Codex plugin authoring guide for Agent, Skill, Command, and Hook components. Covers the Agent Skills standard (agentskills.io), Codex skill packaging (.agents/skills, .codex-plugin manifests, agents/openai.yaml), Claude Code extensions (context: fork, when_to_use, disable-model-invocation), name/description validation, spec-freshness checks, source-to-skill conversion, multi-plugin management, version sync, agent impact analysis, cross-reference integrity, and skill-improvement loops. Use when creating, modifying, or reviewing plugin components, auditing Codex skill compatibility, splitting or adding plugins in a multi-plugin repo, or processing skill-improvement proposals. For discovering and installing existing skills, use find-skills instead. For MCP protocol/server development, use lang:developing-mcp. For converting Claude Code agents to Codex, use converting-agents-to-codex. For codebase-wide automation recommendations, use recommending-automations.
tools1
implementing-design
Comprehensive design-to-code implementation skill covering general design principles, Figma MCP integration, and Figma UI design workflows. General: design system integration, visual parity validation, responsive implementation, accessibility. Figma MCP (13 tools): basic/advanced workflows (Figma Make, Code Connect, Design System Rules, design token sync), visual validation. Figma UI design: wireframe→prototype→detailed design→handoff workflow, 8pt grid, component-driven design, UIStack (5 states), style naming conventions, engineer collaboration. Use when implementing designs from any source (screenshots, mockups, Figma URLs, specs) or when designing mobile UI in Figma and preparing design handoff. Requires Figma MCP server for Figma-specific code generation workflows. For design system architecture and organizational adoption strategy, use building-design-systems instead.
tools1
creating-content
コンテンツ制作統合スキル。AIコピーライティング（15テクニック＋心理的トリガーでマーケティングコピー・ブログタイトル・広告見出し・SNS投稿を生成）とAIデザインクリエイティブ（バナー・SNS・ポスター等の広告ビジュアル制作プロンプト設計・75プロンプトテンプレート・i2iワークフロー）を統合。 Use when creating marketing copy, blog titles, ad headlines, social media posts, or generating visual creatives (banners, social images, posters) with AI tools. For eliminating AI smell from text use devkit:writing-effective-prose. For UI/UX design principles use design:designing-ux. For presentations use creating-slides. For LaTeX → writing-latex.
tools1
developing-web-apis
Web API development guide covering design (endpoints, responses, HTTP spec, versioning, security), spec-first methodology (spec writing, E2E test framework architecture, technical debt repayment), and testing strategy (design testing, contract testing, automation, performance, security testing). Use when designing REST APIs, writing API specs, adopting spec-first development, or building API test strategies. For framework-specific implementation (Express, NestJS), use respective framework skill. For microservices patterns and trade-off analysis of API usability vs maintenance, use architecting-infrastructure instead.
tools1
styling-with-tailwind
Tailwind CSS styling methodology covering utility-first philosophy, v4 CSS-first config, utility/modifier reference, component design patterns, customization (plugins, presets, JS API), migration strategies, and design system construction with design tokens. Use when styling web applications with Tailwind CSS or making CSS architecture decisions. For frontend code generation with shadcn/ui and Storybook, use designing-frontend instead. For general UI/UX design principles, use designing-ux instead. For design system strategy beyond CSS (pattern language, organizational adoption, UI pattern catalog, measurement), use building-design-systems instead.
tools1
developing-react
React 19.x development guide covering internals (rendering, reconciliation, Fiber), design patterns (Container/Presenter, HOC, Render Props, Compound Components), state management (useState to Zustand/TanStack Query, nuqs/Jotai), error handling (ErrorBoundary, React 19 error APIs), accessibility (ARIA, focus management, keyboard navigation, WCAG 2.1 AA), performance optimization (react-doctor, React Compiler, memoization), UI animation patterns (CSS transitions, easing), React Testing Library (RTL queries, interactions, TDD patterns), and Storybook (CSF3, interaction testing, a11y). Also covers React Router, auth/RBAC, i18n, OpenAPI, and production architecture. Use when package.json contains 'react' (without 'next'), or when working on React-specific concerns in any framework.
development1
evaluating-with-promptfoo
LLM evaluation and red-teaming toolkit using promptfoo. Covers promptfooconfig.yaml configuration, 40+ assertion types (deterministic, model-graded, RAG), provider setup (OpenAI, Anthropic, Google, Ollama, HTTP, custom JS/Python), red teaming (134+ plugins, jailbreak strategies, compliance frameworks), CLI commands, caching, and CI/CD integration. Use when writing promptfooconfig.yaml, designing LLM test suites, running adversarial red team evaluations, or integrating LLM quality gates in CI/CD. Detects: promptfooconfig.yaml or promptfoo in package.json. For general LLMOps operations, use designing-genai-patterns. For general test methodology (TDD/AAA), use devkit:testing-code.
tools1
developing-nextjs
Next.js 16.x development guide covering App Router, Server Components, Turbopack, React Compiler, proxy.ts, Cache Components, opt-in caching APIs (updateTag/revalidateTag/refresh), strict TypeScript, Tailwind CSS 4.x, Prisma 7.x, Zod 4.x, Vitest 4.x, Playwright, Docker. MUST load when package.json contains 'next' or next.config.* is detected. For React-specific concerns (internals, performance rules, animation, RTL testing), use developing-react. SaaS構築パターン（認証・決済・AI統合）を含む。 For AI integration with Vercel AI SDK and LangChain.js, use integrating-ai-web-apps. For application logging design and structured logging patterns, use implementing-observability. For Tailwind CSS methodology, component design patterns, and customization, use styling-with-tailwind. For Firebase platform details (Auth/Firestore/Rules)→developing-firebase. For React Router based routing/rendering and client-side auth/i18n architecture, use developing-react.
tools1
implementing-design
Comprehensive design-to-code implementation skill covering general design principles, Figma MCP integration, and Figma UI design workflows. General: design system integration, visual parity validation, responsive implementation, accessibility. Figma MCP (13 tools): basic/advanced workflows (Figma Make, Code Connect, Design System Rules, design token sync), visual validation. Figma UI design: wireframe→prototype→detailed design→handoff workflow, 8pt grid, component-driven design, UIStack (5 states), style naming conventions, engineer collaboration. Use when implementing designs from any source (screenshots, mockups, Figma URLs, specs) or when designing mobile UI in Figma and preparing design handoff. Requires Figma MCP server for Figma-specific code generation workflows. For design system architecture and organizational adoption strategy, use building-design-systems instead.
tools1
developing-fastapi
FastAPI (Python) web API development guide covering fundamentals (routing, path/query params, Pydantic models, request/response, error handling), data persistence (SQLAlchemy, SQLModel, async DB, MongoDB, CRUD, Alembic migrations), dependency injection (Depends, dependency_overrides, scopes/lifespan), auth & security (OAuth2, JWT, CORS), async & concurrency (async/await, Starlette, BackgroundTasks, WebSocket, SSE/streaming), testing (TestClient, pytest, httpx, mocking), production deployment & scaling (uvicorn/gunicorn, Docker, optimization), generative-AI services (model serving, streaming, concurrency), and microservice/GraphQL/OpenAPI patterns. MUST load when fastapi is in pyproject.toml/requirements.txt or .py files import fastapi. For Python language/tooling fundamentals (uv/ruff/mypy, packaging, non-FastAPI patterns), use lang:developing-python. For REST/HTTP-spec design, versioning, and API test strategy, use developing-web-apis. For Node.js/Fastify backend services, use building-nodejs-services.
tools1
recommending-automations
コードベースを解析し、Claude Code と Codex CLI 双方の自動化（hooks / subagents / skills / MCP servers / plugins）を推奨する読み取り専用スキル。検出したプラットフォーム （.claude/・CLAUDE.md / .codex/・AGENTS.md）を優先しつつ、各レコメンドに両クライアントの セットアップ手順を併記する。Use when the user asks for automation recommendations, wants to set up or optimize Claude Code or Codex for a project, asks what hooks / subagents / skills / MCP servers they should use, or mentions improving their AI coding assistant workflow. For authoring a specific plugin / skill / agent, use authoring-plugins instead. For converting an existing Claude agent to Codex, use converting-agents-to-codex.
tools1
integrating-ai-web-apps
Comprehensive guide to integrating generative AI into web applications using Vercel AI SDK, LangChain.js, and MCP with React/Next.js. Covers streaming chat, RAG and summarization, tool calling, structured data generation, prompt engineering, AI app testing (mocking, E2E, evaluation), and deployment security (API key management, CORS, rate limiting). Use when building AI-powered web features in JavaScript/TypeScript projects. For framework-agnostic GenAI design patterns and RAG system internals (vector stores, chunking, LLMOps), use designing-genai-patterns. For MCP protocol/server development, use lang:developing-mcp. For Next.js framework specifics, use web:developing-nextjs. For Python LangChain/LangGraph agent development, use building-ai-agents. For Python/FastAPI generative-AI service backends (model serving, streaming), use web:developing-fastapi.
tools1
using-next-devtools
Next.js development integration tools via next-devtools MCP. Use when interacting with the next-devtools MCP on a running dev server. Provides diagnostics, version upgrades, Cache Components optimization, and automatic error fixes. Primary tool for next-devtools MCP interactions. For Next.js framework patterns (App Router, Server Components, caching APIs, Prisma/Zod), use developing-nextjs instead.
tools1
practicing-software-engineering
Comprehensive SW engineering practices covering project foundations (fast feedback, small steps, DORA metrics), team organization (Team Topologies, 4 types), pair programming (4 patterns), developer habits (GREAT framework), IC effectiveness mindset (outcomes vs outputs, strategic prioritization), career-stage skills (junior to staff, IC vs management), cross-functional influence (PM/design, authority-free leadership), 20 anti-patterns (15 individual + 5 team-level), sustainable performance (burnout, remote work), and AI-enhanced workflows (daily AI, 90-day rollout). Use when starting projects, organizing teams, for IC effectiveness, career growth, or team AI culture.
development1
building-multi-tenant-saas
Multi-tenant SaaS architecture covering deployment models, tenant isolation, and data partitioning. Use when designing SaaS platforms or evaluating silo vs pool strategies. Covers identity, onboarding, tiering, and operations. For Next.js single-tenant SaaS (auth, payments), use developing-nextjs instead. For vendor-neutral infrastructure and microservices patterns, use architecting-infrastructure instead. For data-flow architecture and CQRS/polyglot persistence, use architecting-data instead.
development1
creating-content
コンテンツ制作統合スキル。AIコピーライティング（15テクニック＋心理的トリガーでマーケティングコピー・ブログタイトル・広告見出し・SNS投稿を生成）とAIデザインクリエイティブ（バナー・SNS・ポスター等の広告ビジュアル制作プロンプト設計）を統合。 Use when creating marketing copy, blog titles, ad headlines, social media posts, or generating visual creatives (banners, social images, posters) with AI tools. For eliminating AI smell from text use writing-effective-prose. For UI/UX design principles use designing-ux. For presentations use creating-slides. For LaTeX → writing-latex.
tools1
practicing-product-management
プロダクトマネジメント総合ガイド（基礎・AIプロダクト・A/Bテスト・成長戦略・GPM・PLG・カスタマーサクセス・Claude Code PM活用）。 Use when practicing product management, managing AI products, designing experiments, growth product management, PLG strategy, customer success, or using Claude Code as PM tool. AARRR海賊指標、AIプロダクトライフサイクル、MLプロダクト化、AI統合戦略、オンライン実験設計、PM調査パターン、GPM実践、リテンション戦略、拡張収益を含む。 For engineer-focused user story writing techniques (templates, common mistakes, splitting), use writing-user-stories instead.
tools1
securing-ai-development
Organizational security strategy for AI-powered software development covering trust frameworks, adaptive guardrails, AI-BOM, AI-SPM, governance models, and cross-functional ownership. Use when establishing security controls for AI coding assistants, agentic systems, or AI-accelerated SDLC workflows. For code-level security (OWASP, CodeGuard), use securing-code instead. For AI development methodology (prompts, context engineering), use developing-with-ai instead. For LLM-specific security (prompt injection, LLMSecOps), use ai:designing-genai-patterns.
development1
creating-diagrams
ダイアグラム作成ガイド（Mermaid構文・draw.io MCP・24種類のダイアグラム対応）。 Use when creating diagrams, charts, or visual documentation with Mermaid or draw.io. C4モデル、ER図、シーケンス図、フローチャート、ガントチャート等を含む。
tools1
testing-e2e-with-playwright
Playwright E2Eテストの設計・実装・運用ガイド。 Use when writing, reviewing, or maintaining E2E tests with @playwright/test. playwright.config.* 検出時に自動ロード。testing-code（テスト全般）とは異なりPlaywright E2E固有のパターンに特化。
development1
solving-algorithms
Comprehensive algorithm and data structure reference for competitive programming covering sorting, searching, trees, graphs, dynamic programming, computational geometry, and number theory with complexity analysis and language-agnostic implementations. Use when solving algorithmic problems, optimizing code for time/space complexity, or implementing classic data structures (stack, queue, heap, BST, union-find). For database-specific data structures (B-tree, LSM), use lang:developing-databases instead.
development1
applying-behavior-design
Behavioral design methodology for products that change user behavior using CREATE Action Funnel (Cue, Reaction, Evaluation, Ability, Timing) and three strategies (cheat, habit, conscious action). Use when designing product features that aim to change user habits, increase engagement, or guide users toward beneficial actions. For visual UI/UX design principles, use designing-ux instead. For training program design and facilitation methodology, use designing-training instead. For human-centered design thinking process (user research, ideation, prototyping), use designing-ux instead.
development1
creating-diagrams
ダイアグラム作成ガイド（Mermaid構文・draw.io MCP・24種類のダイアグラム対応）。 Use when creating diagrams, charts, or visual documentation with Mermaid or draw.io. C4モデル、ER図、シーケンス図、フローチャート、ガントチャート等を含む。 For data-visualization design theory (chart selection, color scales), use designing-data-visualizations. For LaTeX/TikZ figures inside .tex documents, use writing-latex.
tools1
compressing-epub-images
EPUB ファイル内の画像（主にスキャン本の JPEG）を再エンコード・リサイズしてファイルサイズを削減するスキル。AskUserQuestion で圧縮レベル選択フローを提供し、実測サンプリングから予測サイズを提示してからユーザーに選ばせる。 Use when: EPUB ファイルが大きく画像圧縮で削減したい時、スキャン本（画像ベース EPUB）の容量を減らしたい時、Kindle などの電子書籍リーダーに転送する前にサイズ最適化したい時。 画像ベース EPUB（スキャン本）と通常 EPUB の両方に対応。書誌情報・xhtml・css は触らず画像のみ再エンコード。For OCR text conversion use converting-content; for Anki flashcards use creating-flashcards.
development1
building-ai-agents
AIエージェント構築ガイド（LangChain/LangGraph・Google ADK・リアルタイムマルチモーダル）。 Use when building AI agents with LangChain, LangGraph, Google ADK, or Gemini Live API. フレームワーク選択、ツール定義、マルチエージェント、A2A、リアルタイム音声/動画を含む。 For framework-agnostic GenAI design patterns, use designing-genai-patterns. For JS/Vercel AI SDK web integration, use integrating-ai-web-apps. For MCP protocol/server design, use developing-mcp.
tools1
building-design-systems
Design system construction, governance, Figma implementation, and practical launch/adoption methodology covering system foundations, pattern taxonomy (CEV naming), organizational adoption (consensus building, proposal templates), pattern library operations, UI pattern catalog (20+ patterns), Figma variable/token architecture, incremental launch, buy-in strategies, content creation, CI/CD automation, update notification framework (6 steps), operational ownership patterns, case studies, and self-assessment. Use when architecting, evaluating, or restructuring a design system, planning organizational adoption, building a pattern library, constructing a design system within Figma, starting a DS from scratch, or creating design system content. For component styling, use styling-with-tailwind instead. For design-to-code, use implementing-design instead. For frontend codegen, use designing-frontend instead.
tools1
converting-content
コンテンツ変換ガイド（画像ベースEPUB→テキストOCR変換・LM Studio英日翻訳）。 Use when converting image-based EPUBs to text or translating content with LM Studio. pandoc、recognize-image.py OCR、ローカルLLM翻訳ワークフローを含む。For image compression/size reduction use compressing-epub-images; for Anki flashcards use creating-flashcards.
documentation1
architecting-infrastructure
Vendor-neutral infrastructure and system architecture patterns. Infrastructure: 127 patterns for availability (HA, DR, backup), security, performance/scalability, operations, network/storage configuration, and cloud. Modernization: socio-technical strategy, domain redesign, trade-off analysis (code/API/system/meta levels). Microservices: CQRS, Event Sourcing, Saga, distributed transactions, service granularity, data ownership, resilience, messaging. Use when designing infrastructure, evaluating non-functional requirements, modernizing legacy systems, making architectural trade-offs, or designing microservices.
development1
architecting-data
Data architecture patterns covering read-side optimization (replicas, materialized views, CQRS, CDC, event sourcing), domain-based decomposition, polyglot persistence, and caching strategies (cache-aside, read-through, write-through, write-around). Use when designing data flow architecture, choosing read scalability strategies, or implementing caching for enterprise systems. For microservices patterns (Saga, granularity), use architecting-infrastructure instead. For DDD domain modeling, use applying-clean-architecture instead. For database engine internals, use developing-databases instead. For relational DB schema design, use developing-databases instead. For GCP-specific data services (BigQuery, Dataflow, Dataproc), lakehouse (BigLake, Dataplex), and BigQuery advanced operations (editions, HA/DR), use developing-google-cloud instead.
development1
building-multi-tenant-saas
Multi-tenant SaaS architecture covering deployment models, tenant isolation, and data partitioning. Use when designing SaaS platforms or evaluating silo vs pool strategies. Covers identity, onboarding, tiering, and operations. For Next.js single-tenant SaaS (auth, payments), use developing-nextjs instead.
development1
designing-genai-patterns
32 production-grade GenAI design patterns covering content control (Logits Masking, Grammar, Style Transfer), RAG architecture, model capabilities (Chain of Thought, Adapter Tuning), reliability (LLM-as-Judge, Reflection, Prompt Optimization), agentic systems (Tool Calling, Multiagent Collaboration), deployment optimization (SLM, Prompt Caching, Inference Optimization), safety guardrails (Self-Check, Guardrails), RAG implementation (11 source types, chunking, vector stores), and LLMOps/AgentOps (maturity L0–2, Tool/Agent Registry, Memory Governance, LLM metrics, LLMSecOps). Also covers AI performance (GPU/CUDA, LLM inference). Use when designing GenAI applications, choosing RAG strategies, implementing agent architectures, optimizing LLM reliability, or operating AI systems in production. For LangChain/LangGraph/ADK agents, use building-ai-agents. For web AI (Vercel AI SDK, LangChain.js), use integrating-ai-web-apps. For GCP-specific ML (BigQuery ML, Vertex AI), use cloud:developing-google-cloud.
tools1
developing-databases
Comprehensive database development guide covering relational design (ER modeling, normalization, PostgreSQL implementation), SQL antipatterns (25 patterns with detection signals and solutions), database internals (storage engines B-tree/LSM, distributed systems, consensus algorithms), and PostgreSQL operations (server config, extensions, query tuning, MVCC/VACUUM, backup/PITR, replication/HA, monitoring). Use when designing database schemas, writing SQL queries, reviewing data models, choosing storage engines, tuning PostgreSQL performance, managing backup/replication, or debugging distributed system behavior. Replaces: designing-relational-databases, avoiding-sql-antipatterns, understanding-database-internals.
tools1
architecting-infrastructure
Vendor-neutral infrastructure and system architecture patterns. Infrastructure: 127 patterns for availability (HA, DR, backup), security, performance/scalability, operations, network/storage configuration, and cloud. Modernization: socio-technical strategy, domain redesign, trade-off analysis (code/API/system/meta levels). Microservices: CQRS, Event Sourcing, Saga, distributed transactions, service granularity, data ownership, resilience, messaging. Use when designing infrastructure, evaluating non-functional requirements, modernizing legacy systems, making architectural trade-offs, or designing microservices.
development1
designing-training
Training program design and facilitation methodology covering needs analysis (participant analysis, stakeholder mapping), KSA framework, instructional design theory (ADDIE, TOTE, Gagné, mastery learning), objective setting, activity catalog, training operations (instructor, space, logistics), brain science principles (7±2 rule, long-term memory, habit formation), learner-centered facilitation (90/20/8 rule, EAT), online/hybrid delivery, skill map creation, and training material development. Use when designing training programs, facilitating workshops, creating training materials, building skill maps, or managing training operations. For behavior design→applying-behavior-design. For presentation content→creating-slides. For design thinking process methodology (empathize/define/ideate/prototype/test)→designing-ux.
development1
creating-countdown-icons
カウントダウンアプリ用アプリアイコン（512×512 PNG）を絵文字・背景パレット選択の対話フローで生成するスキル。テキスト・絵文字・斜めストライプ背景を組み合わせたデザインアイコンを出力し、clean版とプレビュー版（白数字重ね）の2枚を提供する。 Use when creating app icons for countdown apps, generating text-based app icons with emoji, selecting icon designs interactively, or producing 512x512 PNG icons with diagonal striped backgrounds. 絵文字候補4択 → 背景パレット4択の対話フローで、ユーザーの意図に合ったアイコンを段階的に確定する。詳細な手順は INSTRUCTIONS.md を参照。
development1
designing-data-visualizations
Comprehensive data visualization principles covering chart type selection, color scales, design best practices, and data storytelling. Use when creating charts, dashboards, or any visual data representation. For UI/UX design principles, use designing-ux instead. For technical diagrams (flowcharts, architecture), use creating-diagrams instead.
testing1
collecting-kentei-lab-exams
kentei-lab.com の資格・検定問題を、指定 URL からその資格の全問題（問題文・選択肢・正解・解説）を巡回取得し 1 資格 1 JSON ファイル（Anki 登録に適した構造化データ）に保存する。出力はそのまま creating-flashcards スキルへ渡して試験名ごとに Anki フラッシュカード化できる。 Use when kentei-lab の資格 URL（/exams/<slug> ・ /exams/<slug>/start ・ /quiz/<slug>/<n> のいずれか）を渡され 「問題を全部保存したい」「問題集を収集したい」「Anki カードにしたい」等と言われたとき。 補足トリガー: kentei-lab, ケンテイラボ, 検定, 資格試験, 問題集, quiz 収集, JSON 保存, Anki 連携。 ブラウザ操作自体の汎用ガイドは web:automating-browser、E2E テストは web:testing-e2e-with-playwright を使う。 本スキルは kentei-lab 専用の収集ワークフローと bundled script（scripts/collect-kentei-lab.sh）を提供する。
development1
developing-with-ai
AI-assisted development methodology covering prompt engineering, context engineering, code generation workflows, quality assurance, collaborative debugging, agent collaboration patterns, LLM dialogue design patterns (8 conversational patterns, Grammar of Intention), team LLM adoption workshops, and role-specific augmentation (Dev/PO/Coach/Manager). MUST load when working with AI coding tools or discussing AI-assisted development practices. Use when crafting prompts for code generation, managing AI context, reviewing AI-generated code, coordinating multi-agent workflows, or designing structured LLM dialogues.
tools1
mastering-typescript
Comprehensive TypeScript guide covering type system, advanced patterns, design patterns (GoF Creational/Structural/Behavioral), functional/reactive programming, framework integration, and 83 best practice decision criteria. MUST load when working in TypeScript projects detected by tsconfig.json. Covers Generics, Conditional Types, type inference, type design, SOLID/DDD in TypeScript, anti-patterns, and practical migration tips. Includes type safety rules (any prohibition, type guards, strict mode) formerly in enforcing-type-safety. Includes IDE-driven workflow and common TypeScript pitfalls (TT-PRACTICAL-WORKFLOW). Includes TSDoc/TypeDoc documentation generation workflow (CC-DOCUMENTATION).
development1
writing-clean-code
REQUIRED for all code implementations. Automatically load when writing or reviewing any code. Covers SOLID principles, MAPPER principles with 25 code smell categories, practical refactoring, software design laws, the 4 rules of simple design, 66 code smell heuristics, formatting principles, and boundary management patterns. Language-agnostic clean code guide. For language-specific practices, use developing-go, mastering-typescript, or developing-python. For architecture-level clean design, use applying-clean-architecture. For legacy code refactoring, see CHANGEABLE-CODE.md subfile. For refactoring mindset (spikes, feature toggles, structural discovery), see REFACTORING-MINDSET.md reference.
development1
creating-content
コンテンツ制作統合スキル。AIコピーライティング（15テクニック＋心理的トリガーでマーケティングコピー・ブログタイトル・広告見出し・SNS投稿を生成）とAIデザインクリエイティブ（バナー・SNS・ポスター等の広告ビジュアル制作プロンプト設計）を統合。 Use when creating marketing copy, blog titles, ad headlines, social media posts, or generating visual creatives (banners, social images, posters) with AI tools. For eliminating AI smell from text use writing-effective-prose. For UI/UX design principles use designing-ux. For presentations use creating-slides. For LaTeX → writing-latex.
tools1
developing-terraform
Terraform IaC development with HCL syntax, module design, state management, and Terragrunt wrapper patterns. MUST load when .tf files or terragrunt.hcl are detected, or go.mod contains 'terraform'. Covers AWS/GCP infrastructure patterns and mise task automation. For Docker infrastructure, use practicing-devops instead. For broader DevOps methodology and IaC tool comparison, use practicing-devops instead. For AWS CDK (TypeScript/Python IaC), use developing-aws instead.
tools1
securing-code
REQUIRED after all code implementations. Automatically load when implementation is complete to apply secure-code review with the software-security skill. Covers input validation, secrets management, OWASP top 10 countermeasures, authentication/authorization patterns, web penetration testing (reconnaissance, attack techniques, bypass methods), and serverless security (IAM/storage/functions across AWS/GCP/Azure, 17 threat categories, supply chain attacks). Use when implementing any code, handling external input, or developing serverless applications (Lambda, Cloud Run, Azure Functions). For dynamic authorization model design (ABAC/ReBAC/Cedar), use cloud:implementing-dynamic-authorization instead. For organizational AI development security strategy (trust frameworks, governance, AI-BOM), use ai:securing-ai-development instead. For security logging patterns and compliance logging, use cloud:implementing-observability.
development1
evaluating-with-promptfoo
LLM evaluation and red-teaming toolkit using promptfoo. Covers promptfooconfig.yaml configuration, 40+ assertion types (deterministic, model-graded, RAG), provider setup (OpenAI, Anthropic, Google, Ollama, HTTP, custom JS/Python), red teaming (134+ plugins, jailbreak strategies, compliance frameworks), CLI commands, caching, and CI/CD integration. Use when writing promptfooconfig.yaml, designing LLM test suites, running adversarial red team evaluations, or integrating LLM quality gates in CI/CD. Detects: promptfooconfig.yaml or promptfoo in package.json. For general LLMOps operations, use designing-genai-patterns. For general test methodology (TDD/AAA), use testing-code.
tools1
creating-slides
HTMLスライド作成スキル。slides repoの3層分離モデル（Engine/Theme/Content）に基づく16:9 HTMLプレゼンデッキの作成・テーマカスタマイズ・ソース素材変換をガイド。認知科学・ロジック構築（接続関係診断・基本ロジック図）・ストーリーテリング・聴衆分析・スライドデザイン・ビジュアルデザイン実践・提案書構成術・デリバリー（実践Tips集含む）・準備プロセスの9リファレンスで品質を担保。国際学会・学術研究発表（Q&A・ネットワーキング・ポスター発表・英語表現・発音）向け専門リファレンス6本も収録。 Use when creating HTML slide decks, converting source materials to slides, customizing slide themes, initializing new slide projects, or preparing international conference presentations and academic research talks. Delegates actual slide creation to tachikoma-slide agent. For presentation quality improvement (storytelling, delivery, engagement) use designing-training. For text polishing use writing-effective-prose. For marketing copy use creating-content. For proposal structure (ロジック3つの力, MECE, メッセージマップ) see QUALITY-PROPOSAL-CONSTRUCTION.md. For academic presentations, see ACADEMIC-* refs (Q&A mastery, research structure, networking, poster) and ENGLISH-* refs (expressions, pronunciation).
development1
developing-databases
Comprehensive database development guide covering relational design (ER modeling, normalization, PostgreSQL implementation), SQL antipatterns (25 patterns with detection signals and solutions), database internals (storage engines B-tree/LSM, distributed systems, consensus algorithms), and PostgreSQL operations (server config, extensions, query tuning, MVCC/VACUUM, backup/PITR, replication/HA, monitoring). Use when designing database schemas, writing SQL queries, reviewing data models, choosing storage engines, tuning PostgreSQL performance, managing backup/replication, or debugging distributed system behavior. Replaces: designing-relational-databases, avoiding-sql-antipatterns, understanding-database-internals.
tools1
developing-python
Modern Python development guide covering project setup, tooling, Pythonic best practices, OOP design principles, GoF design patterns, SE process, and type safety. MUST load when pyproject.toml or requirements.txt is detected. Covers Python 3.13 + uv + ruff + mypy, FastAPI/FastMCP, pytest, Docker, Effective Python idioms, software design patterns (encapsulation, LSP, Design by Contract), SE practices (SDLC, Scrum/Kanban, CI/CD, deployment), type safety rules (Any prohibition, TypedDict, Protocol, dataclass), Architecture Patterns (Repository, Unit of Work, Aggregates, Domain Events, CQRS, Event-Driven Architecture), and DDD Tactical Patterns (Value Object, Entity, Aggregate Root). For language-agnostic clean code principles, use writing-clean-code. For application logging design, use implementing-observability. For Clean Architecture in Python, see references/CA-PYTHON.md. For general Clean Architecture principles, use applying-clean-architecture.
tools1
implementing-observability
Unified observability guide covering monitoring system design (anti-patterns, 6-layer strategy, alerting, SLOs, telemetry pipelines, observability maturity model), OpenTelemetry implementation (tracing/metrics/logs API/SDK, Collector deployment, semantic conventions), logging design (structured logging, collection pipelines, analysis, anomaly detection, security compliance), and observability engineering practices (core analysis loop, debugging, ODD, build-vs-buy ROI, CI/CD observability, high-cardinality data). Use when designing monitoring strategy, implementing OpenTelemetry instrumentation, building log pipelines, setting up alerts, establishing SLO-based reliability, or adopting observability practices. Replaces: designing-monitoring, implementing-opentelemetry, implementing-logging.
development1
orchestrating-teams
Agent Teamオーケストレーション（チーム編成・タチコマ並列起動・進捗管理）。 Use when multiple files need parallel changes with independent concerns (2+ files, frontend+backend, UI+API+test). Triggers: 複数ファイル並列変更、マルチ関心事開発、フロントエンド+バックエンド同時変更。
development1
developing-bash
Comprehensive Bash shell scripting and automation guide covering fundamentals, control flow, I/O pipelines, process control, system administration automation, testing/debugging, security, design patterns, and penetration testing automation (Nmap, web scanning, exploitation, Wi-Fi assessment, reporting). MUST load when .sh files are detected or shell scripts are being written. For Docker-specific patterns, use practicing-devops instead. For broader DevOps methodology, use practicing-devops instead.
tools1
writing-effective-prose
Unified writing craft guide: prose fundamentals, AI smell detection (always active), technical docs (7Cs), engineering design docs, academic writing (Harvard, dissertation), tech blog writing, Japanese prose craft, clarity/explanation techniques, web/digital writing, UX copywriting, FAQ writing, revision (no-revision/first-aid), writing mindset and career, persuasive business documents, sensory writing with five senses, README creation, and Zenn publishing. REQUIRED for all text output — AI smell check is always active regardless of document type. Use when writing, reviewing, proofreading, or creating any document (technical docs, articles, engineering design documents (requirements specs, system design docs), reports, slides, emails, academic papers, dissertations, university reports, graduation theses, business documents, web content, FAQ/help docs, design specs, README.md files, Zenn tech articles). For LaTeX → writing-latex. For presentations → creating-slides.
development1
reviewing-with-hunk
Drives live Hunk diff-review sessions via the `hunk session *` CLI (Hunk is an interactive terminal diff viewer controlled through a local daemon). Inspect review focus and file/hunk structure, navigate to files/hunks/lines, reload session contents (diff/show), and add inline review comments (single `comment add` or batched `comment apply`). Use when the user has a Hunk session running — or wants to review a diff/changeset interactively — and asks you to walk them through changes, steer their view, or leave review notes. The Hunk TUI itself belongs to the user: never run interactive `hunk diff`/`hunk show` directly; only `hunk session` subcommands through the daemon. For code-review methodology (PR structure, comment tone, CodeRabbit), use reviewing-code instead. For GitLab MR operations via the glab CLI, use operating-gitlab instead. For GitHub PR descriptions, use the pull-request command instead.
tools1
applying-clean-architecture
Clean Architecture and Domain-Driven Design (DDD) unified guide covering the Dependency Rule, concentric layer model (Entities, Use Cases, Interface Adapters, Frameworks & Drivers), component principles (REP/CCP/CRP, ADP/SDP/SAP), Screaming Architecture, Humble Objects, and DDD strategic/tactical patterns (Bounded Context, Ubiquitous Language, Context Mapping, Value Object, Entity, Aggregate, Event Sourcing, CQRS, Saga, data decomposition). Use when designing application layer structure, enforcing dependency rules, separating business logic from frameworks/UI/databases, modeling complex domains with DDD patterns, or mapping Bounded Contexts to Clean Architecture layers. For code-level clean practices, use writing-clean-code. For distributed/infrastructure patterns, use cloud:architecting-infrastructure. For evolutionary architecture and microservices intro, see ARCHITECTURE-EVOLUTION.md. For project foundations and team practices, use practicing-software-engineering.
development1
testing-code
REQUIRED for all feature implementations. Automatically load when writing or reviewing tests. Enforces TDD approach with AAA pattern, actual/expected variables, and 100% coverage goal for business logic. Covers Vitest, Jest, Playwright, and AI-augmented testing strategies. Includes the Four Pillars of good tests (regression protection, refactoring resistance, fast feedback, maintainability), three testing styles (output/state/communication-based), code classification, and test anti-patterns. For RTL patterns, use developing-react. For Web API testing, use developing-web-apis. For A/B testing, use practicing-product-management. For TDD mindset/ATDD/BDD, see TESTING-PRACTICES.md. For project foundations and team organization, use practicing-software-engineering.
development1
developing-web-apis
Web API development guide covering design (endpoints, responses, HTTP spec, versioning, security incl. OAuth 2.0 and rate limiting), spec-first methodology (spec writing incl. gRPC .proto, Go E2E test framework architecture, technical debt repayment), and testing strategy (design testing with OpenAPI schemas, contract testing with Pact, automation, ATDD, performance, security testing). Use when designing REST APIs, writing API specs, adopting spec-first development, or building API test strategies. For framework-specific implementation (Express, NestJS), use developing-fullstack-javascript. For microservices patterns and trade-off analysis of API usability vs maintenance, use cloud:architecting-infrastructure instead. For choosing among API styles (REST vs GraphQL vs gRPC vs webhooks vs WebSocket vs messaging) and their trade-offs before implementation, use choosing-api-styles. For Fastify framework implementation (routing, plugins, schema validation), use building-nodejs-services.
tools1
implementing-dynamic-authorization
Dynamic authorization design covering authorization model selection (ACL, RBAC, ReBAC, ABAC, PBAC), Policy as Code vs Policy as Data, Cedar policy language (PARC model, type system, operators), policy language comparison (Cedar vs OPA/Rego vs OpenFGA/Zanzibar), XACML reference architecture (PEP/PDP/PAP/PIP), PEP deployment patterns (Embedded/API Gateway/Sidecar), centralized vs distributed PDP, policy governance lifecycle, and multi-tenant policy layering. Use when designing access control systems, choosing authorization models, writing Cedar policies, or selecting policy engines (Cedar, OPA, OpenFGA). For code-level security (input validation, OWASP), use devkit:securing-code instead. For Keycloak identity and access management (OIDC/SAML, SSO, authorization policies), use managing-keycloak instead. For end-to-end security architecture design use architecting-security instead. For applying authorization inside HTTP APIs (RBAC/scopes, JWT/OAuth enforcement), use web:securing-web-apis.
development1
transforming-legacy-systems
A hands-on, iterative method for transforming a legacy codebase into a domain-driven, modular target architecture. Assess maturity with the Modularity Maturity Index (MMI, 0-10: modularity, hierarchy, pattern consistency), then run four strategic steps (domain rediscovery, target architecture modeling, actual-vs-target comparison, prioritized refactoring). Covers transformation approaches (big-bang vs step-by-step vs reshaping), technical stabilization (seams, characterization tests, design by contract), fighting model anemia, sociotechnical team reshaping, and a catalog of strategic/tactical/sociotechnical refactorings with motivation and mechanics. Use when modernizing a legacy monolith, planning incremental migration, or decomposing a big ball of mud into bounded contexts. For DDD/clean-architecture layering, use applying-clean-architecture. For portfolio modernization and migration patterns, use cloud:architecting-infrastructure. For code-level refactoring, use writing-clean-code.
development1
applying-semantic-versioning
Semantic Versioning 2.0.0仕様に基づくバージョン判断ガイド。MAJOR/MINOR/PATCH判定、プレリリース・ビルドメタデータ、範囲指定を提供。 REQUIRED for all version-related decisions. Use when determining version bumps, creating releases, or managing dependencies.
testing1
writing-latex
LaTeX document creation for Japanese academic reports. MUST load when .tex files are detected. Covers upLaTeX + dvipdfmx setup, minted code highlighting with Japanese font support, equations, figures, tables, and cover pages.
development1
writing-conventional-commits
Conventional Commits 1.0.0仕様に基づくコミットメッセージフォーマットガイド。type/scope/BREAKING CHANGEの判定とSemVerとの対応を提供。 REQUIRED for all commit messages and version descriptions. Use when writing git commit messages. For version bump decisions and SemVer rules, use applying-semantic-versioning instead.
testing1
architecting-security
Artifact-based methodology for designing security architecture for hybrid and multi-cloud systems across the solution lifecycle (Plan, Design, Build, Run, Close): artifact dependency framework, threat modeling (STRIDE, attack trees, LINDDUN), zero trust integration, data-centric security (data classification, information asset register), compliance and governance mapping, security requirements engineering, shared responsibility models, and architecture decision records. Use when designing an information system's security, threat modeling, planning zero trust, producing security architecture artifacts, or defining a security architect's deliverables. For infrastructure and microservices patterns use architecting-infrastructure; for secure-by- default coding use devkit:software-security; for OWASP code security use devkit:securing-code; for authorization models (ABAC/ReBAC/Cedar) use implementing-dynamic-authorization; for cloud-vendor security use developing-aws or developing-google-cloud instead.
development1
testing-strategies
Full-stack test strategy guide spanning ten quality dimensions: manual exploratory testing (equivalence/boundary/state-transition/decision-table frameworks), functional automation strategy (micro/macro test types, contract testing), continuous testing (CI etiquette, DORA), data testing (DB/cache/batch/event streams, Testcontainers), visual testing, security testing (STRIDE, threat modeling, OWASP tools), performance testing (KPIs, load patterns, JMeter/Gatling, RAIL), accessibility testing (WCAG, axe), cross-functional requirements testing (chaos/architecture/compliance), mobile testing, and AI-assisted testing (agentic test authoring, MCP-based exploration). Use when designing test strategy across the stack, choosing test types beyond unit tests, or planning exploratory/visual/performance/accessibility/mobile testing. For TDD/unit methodology (AAA, four pillars, mocks), use testing-code. For Playwright E2E implementation, use web:testing-e2e-with-playwright. For code-level security, use securing-code.
tools1
securing-cloud
Vendor-neutral cloud security body of knowledge aligned with the six CCSP domains: cloud fundamentals (IaaS/PaaS/SaaS, shared responsibility), architecture and design principles (cryptography, IAM, network security, zero trust, BC/DR), data security (lifecycle, storage architectures, DLP, information rights management), platform and infrastructure security (data center, virtualization/hypervisor), application security (API security, WAF), secure development (SDLC, DevSecOps), security operations (SOC, SIEM/SOAR), governance/risk/compliance, legal and privacy (privacy regulations, SLA, forensics), and emerging trends (cloud-native, AI/ML security). Use when securing cloud workloads, designing cloud security controls, evaluating provider security, or studying cloud security certification topics. For security architecture methodology (threat modeling artifacts), use architecting-security. For code-level security, use devkit:securing-code. For AWS/GCP specifics, use developing-aws or developing-google-cloud.
development1
applying-clean-architecture
Clean Architecture and Domain-Driven Design (DDD) unified guide covering the Dependency Rule, concentric layer model (Entities, Use Cases, Interface Adapters, Frameworks & Drivers), component principles (REP/CCP/CRP, ADP/SDP/SAP), Screaming Architecture, Humble Objects, and DDD strategic/tactical patterns (Bounded Context, Ubiquitous Language, Context Mapping, Value Object, Entity, Aggregate, Event Sourcing, CQRS, Saga, data decomposition). Use when designing application layer structure, enforcing dependency rules, separating business logic from frameworks/UI/databases, modeling complex domains with DDD patterns, or mapping Bounded Contexts to Clean Architecture layers. For code-level clean practices, use writing-clean-code. For distributed/infrastructure patterns, use architecting-infrastructure. For evolutionary architecture and microservices intro, see ARCHITECTURE-EVOLUTION.md. For project foundations and team practices, use practicing-software-engineering.
development1
developing-fullstack-javascript
Full-stack JavaScript development covering backend (NestJS/Express), frontend (React), deployment (CI/CD), and quality; also covers JavaScript language fundamentals (types, closures, prototypes, async/await, modules, and metaprogramming). MUST load when package.json contains Express, NestJS, or similar backend frameworks. Covers API design, state management, caching, and testing. Also use when working with JavaScript language-level concerns — type coercion, scoping, this binding, Promise patterns, Proxy/Reflect, or iterator protocols. Also covers V8 engine internals (hidden classes, inline caches, string/number repr), event loop model, JS/Node error model, and Express 5 + Drizzle ORM CRUD APIs.
development1
developing-firebase
Firebase platform development guide covering Authentication (email/social/session), Firestore & Realtime Database (modeling/queries/security rules), Cloud Storage, Cloud Functions (triggers/scheduling), Hosting, Analytics (events/BigQuery), FCM push notifications, Remote Config, Test Lab, Performance Monitoring, Dynamic Links, App Distribution, AdMob, and Extensions. MUST load when firebase, @firebase, or firebase-admin packages detected, or firebaseConfig/firebase.json/firestore.rules files present. For GCP infra→developing-google-cloud. For Next.js integration→developing-nextjs. For REST API design→developing-web-apis.
tools1
designing-ux
UXデザイン総合ガイド（認知心理学・UIガイドライン・グラフィック基礎・インターフェイス哲学・UXエレメント5段階モデル・UIデザイン実践TIPS・Webビジュアルデザイン実践）。 Use when designing user experiences, UI, creating web page layouts and visual designs, defining web design concepts using functionality/emotionality frameworks, or referencing UI/graphic design principles and interaction philosophy. 認知心理学基盤（知覚・記憶・思考）、UIデザインガイドライン（コンポーネント・マルチデバイス・ユーザビリティ）、グラフィックデザイン基礎（造形・色彩・タイポグラフィ・レイアウト）、インターフェイス哲学（Fluid Interfaces・モーション理論・ウェルビーイング）、UXエレメント5段階モデル（Strategy/Scope/Structure/Skeleton/Surface）、UIデザイン実践TIPS（状態設計・フィードバック・コンポーネント選択）、Webビジュアルデザイン実践（機能性7軸・情緒性6軸・コンセプト策定）を含む。デザイン思考プロセス・ユーザーリサーチは practicing-design-thinking スキルへ。AIエクスペリエンス設計は designing-ai-experiences スキルへ。
development1
designing-ai-experiences
AI experience (AIX) design guide: agentic UX, Copilot patterns, mental models, AI-first interfaces, input/output design, framing, ethics. Use when designing AI-powered product UX or human-AI interaction patterns such as agentic systems, Copilot features, prompt UI, or AI output presentation. For general UI/UX & visual design use designing-ux. For design-thinking process & UX research use practicing-design-thinking. For behavior-change product design use applying-behavior-design.
testing1
designing-genai-patterns
32 production-grade GenAI design patterns covering content control (Logits Masking, Grammar, Style Transfer), RAG architecture, model capabilities (Chain of Thought, Adapter Tuning), reliability (LLM-as-Judge, Reflection, Prompt Optimization), agentic systems (Tool Calling, Multiagent Collaboration), deployment optimization (SLM, Prompt Caching, Inference Optimization), safety guardrails (Self-Check, Guardrails), RAG implementation (11 source types, chunking, vector stores), and LLMOps/AgentOps (maturity L0–2, Tool/Agent Registry, Memory Governance, LLM metrics, LLMSecOps). Also covers AI performance (GPU/CUDA, LLM inference) via PERF- references. Use when designing GenAI applications, choosing RAG strategies, implementing agent architectures, optimizing LLM reliability, or operating AI systems in production. For web AI (Vercel AI SDK, LangChain.js), use integrating-ai-web-apps. For GCP-specific ML (BigQuery ML, Vertex AI), use developing-google-cloud.
tools1
designing-frontend
Creates distinctive, production-grade frontend code with shadcn/ui integration, object-oriented UI (OOUI) methodology, and micro-frontend architecture patterns. Use when implementing web components, pages, or applications requiring creative, polished UI code; when designing UI structure using object-oriented approach (object extraction, view/navigation patterns, layout pattern selection); or when architecting micro-frontend systems (team splitting, Module Federation, BFF patterns, migration strategy, Conway's Law application). For Storybook story creation and component testing, use developing-react instead. For theoretical UI/UX design principles, use designing-ux instead. For Tailwind CSS methodology, component design patterns, and design system construction, use styling-with-tailwind instead. For design system methodology (pattern language, organizational strategy, UI pattern catalog, anti-patterns), use building-design-systems instead.
development1
designing-training
Training program design and facilitation methodology covering needs analysis (participant analysis, stakeholder mapping), KSA framework, instructional design theory (ADDIE, TOTE, Gagné, mastery learning), objective setting, activity catalog, training operations (instructor, space, logistics), brain science principles (7±2 rule, long-term memory, habit formation), learner-centered facilitation (90/20/8 rule, EAT), online/hybrid delivery, skill map creation, and training material development. Use when designing training programs, facilitating workshops, creating training materials, building skill maps, or managing training operations. For behavior design→applying-behavior-design. For presentation content→creating-slides. For design thinking process methodology (empathize/define/ideate/prototype/test)→designing-ux.
development1
designing-data-visualizations
Comprehensive data visualization principles covering chart type selection, color scales, design best practices, and data storytelling. Use when creating charts, dashboards, or any visual data representation. For UI/UX design principles, use designing-ux instead. For technical diagrams (flowcharts, architecture), use creating-diagrams instead.
testing1
creating-slides
HTMLスライド作成スキル。slides repoの3層分離モデル（Engine/Theme/Content）に基づく16:9 HTMLプレゼンデッキの作成・テーマカスタマイズ・ソース素材変換をガイド。認知科学・ロジック構築（接続関係診断・基本ロジック図）・ストーリーテリング・聴衆分析・スライドデザイン・ビジュアルデザイン実践・提案書構成術・デリバリー（実践Tips集含む）・準備プロセスの9リファレンスで品質を担保。国際学会・学術研究発表（Q&A・ネットワーキング・ポスター発表・英語表現・発音）向け専門リファレンス6本も収録。 Use when creating HTML slide decks, converting source materials to slides, customizing slide themes, initializing new slide projects, or preparing international conference presentations and academic research talks. Delegates actual slide creation to tachikoma-slide agent. For presentation quality improvement (storytelling, delivery, engagement) use designing-training. For text polishing use writing-effective-prose. For marketing copy use creating-content. For proposal structure (ロジック3つの力, MECE, メッセージマップ) see QUALITY-PROPOSAL-CONSTRUCTION.md. For academic presentations, see ACADEMIC-* refs (Q&A mastery, research structure, networking, poster) and ENGLISH-* refs (expressions, pronunciation).
development1
creating-pptx
箇条書き・メモ・素朴なスライドを「6つの構造」で組み直し、So What（だから何が言えるか）まで届くコンサル品質の1枚スライドを、編集可能な PowerPoint（.pptx）とプレビュー画像（.png）のハイブリッドで生成するスキル。情報を足すのではなく削り、情報の差と余白で意思決定を一目で促す。 Use when creating or remaking a consultant-quality single slide as an editable PowerPoint (pptx) from rough notes, bullet points, or an existing slide — restructuring into a So-What-driven 16:9 deliverable with strict flat design discipline (6-color palette, Noto Sans JP, grid alignment). 手動呼び出し専用（/creating-pptx）。For multi-slide HTML decks use creating-slides. For Google Slides editing use gws-slides. For standalone diagrams use creating-diagrams. For data-visualization theory use designing-data-visualizations.
development1
researching-libraries
Researches existing libraries before implementation to prevent reinventing the wheel. REQUIRED before writing any new functionality. Use when evaluating npm packages, pip packages, Go modules, or any third-party libraries to find and evaluate existing solutions.
development1
using-serena
Token-efficient structured development via /serena command. Use when implementing components, APIs, system designs, tests, bug fixes, or optimizations with structured problem-solving approach. Available for Claude Code本体 and all Agents including Tachikoma.
development1
writing-conventional-commits
Conventional Commits 1.0.0仕様に基づくコミットメッセージフォーマットガイド。type/scope/BREAKING CHANGEの判定とSemVerとの対応を提供。 REQUIRED for all commit messages and version descriptions. Use when writing git commit messages.
tools1
developing-react
React 19.x development guide covering internals (rendering, reconciliation, Fiber), design patterns (Container/Presenter, HOC, Render Props, Compound Components), state management (useState to Zustand/TanStack Query, nuqs/Jotai), error handling (ErrorBoundary, React 19 error APIs), accessibility (ARIA, focus management, keyboard navigation, WCAG 2.1 AA), performance optimization (react-doctor, React Compiler, memoization), UI animation patterns (CSS transitions, easing), React Testing Library (RTL queries, interactions, TDD patterns), and Storybook (CSF3, interaction testing, a11y). Also covers React Router, auth/RBAC, i18n, OpenAPI, and production architecture. Use when package.json contains 'react' (without 'next'), or when working on React-specific concerns in any framework.
development1
developing-nextjs
Next.js 16.x development guide covering App Router, Server Components, Turbopack, React Compiler, proxy.ts, Cache Components, opt-in caching APIs (updateTag/revalidateTag/refresh), strict TypeScript, Tailwind CSS 4.x, Prisma 7.x, Zod 4.x, Vitest 4.x, Playwright, Docker. MUST load when package.json contains 'next' or next.config.* is detected. For React-specific concerns (internals, performance rules, animation, RTL testing), use developing-react. SaaS構築パターン（認証・決済・AI統合）を含む。 For AI integration with Vercel AI SDK and LangChain.js, use integrating-ai-web-apps. For application logging design and structured logging patterns, use implementing-observability. For Tailwind CSS methodology, component design patterns, and customization, use styling-with-tailwind. For Firebase platform details (Auth/Firestore/Rules)→developing-firebase. For React Router based routing/rendering and client-side auth/i18n architecture, use developing-react.
tools1
developing-google-cloud
Google Cloud guide: Cloud Run, GCP security (IAM/VPC/KMS/Zero Trust), data engineering (BigQuery/Dataflow/pipelines/governance/lakehouse), networking (VPC/LB/CDN), Memorystore, enterprise architecture, compute selection (GCE/GKE/GAE/Run/Functions), GKE, GAE, monitoring (SLO/SLI), BigQuery analytics (SQL/window functions/GA4), BigQuery ops (editions/HA-DR/slots), workflow (Composer/Dataform/Data Fusion), BI (Looker/Looker Studio/BI Engine), ingestion (DTS/Datastream CDC/GA4), real-time (Pub/Sub/Dataflow streaming), ML (BigQuery ML/Vertex AI/GIS). MUST load when google-cloud packages, cloudbuild.yaml, BigQuery/Dataflow/Memorystore/Looker/Dataplex detected. For Docker→practicing-devops. For monitoring→implementing-observability. For OWASP→securing-code. For CQRS→architecting-data. For AWS→developing-aws. For GenAI→designing-genai-patterns. For Firebase (Auth/Firestore/Storage/Functions/Hosting)→developing-firebase.
development1
developing-web-apis
Web API development guide covering design (endpoints, responses, HTTP spec, versioning, security), spec-first methodology (spec writing, E2E test framework architecture, technical debt repayment), and testing strategy (design testing, contract testing, automation, performance, security testing). Use when designing REST APIs, writing API specs, adopting spec-first development, or building API test strategies. For framework-specific implementation (Express, NestJS), use respective framework skill. For microservices patterns and trade-off analysis of API usability vs maintenance, use architecting-infrastructure instead.
tools1
integrating-ai-web-apps
Comprehensive guide to integrating generative AI into web applications using Vercel AI SDK, LangChain.js, and MCP with React/Next.js. Use when building AI-powered web features (streaming chat, RAG, tool calling, structured data generation) in JavaScript/TypeScript projects. For RAG system internals, use designing-genai-patterns. For MCP protocol development, use developing-mcp. For Next.js framework specifics, use developing-nextjs. For Python LangChain/LangGraph agent development, use building-ai-agents. For framework-agnostic GenAI design patterns (32 patterns covering content control through safety guardrails), use designing-genai-patterns.
tools1
using-next-devtools
Next.js development integration tools via next-devtools MCP. MUST load when working on Next.js projects detected by package.json. Provides diagnostics, version upgrades, Cache Components optimization, and automatic error fixes. Primary tool for Next.js tasks.
tools1
styling-with-tailwind
Tailwind CSS styling methodology covering utility-first philosophy, v4 CSS-first config, utility/modifier reference, component design patterns, customization (plugins, presets, JS API), migration strategies, and design system construction with design tokens. Use when styling web applications with Tailwind CSS or making CSS architecture decisions. For frontend code generation with shadcn/ui and Storybook, use designing-frontend instead. For general UI/UX design principles, use designing-ux instead. For design system strategy beyond CSS (pattern language, organizational adoption, UI pattern catalog, measurement), use building-design-systems instead.
tools1
analyzing-with-google-analytics
Google Analytics 4 (GA4) のデータを公式 MCP サーバー analytics-mcp 経由で分析するスキル。アカウントサマリー取得・プロパティ詳細確認・標準/ファネル/リアルタイムレポート実行・カスタムディメンション/メトリクス取得・Google Ads リンク確認をカバーする。 Use when GA4 のトラフィック・コンバージョン・ユーザー行動を MCP ツール (run_report / run_realtime_report / run_funnel_report 等) で照会・分析するとき、または google プラグインの google-analytics MCP サーバーのセットアップ (ADC 認証・必要 API 有効化・環境変数) を行うとき。 For 検索可視性戦略・SEO/GEO・KPI 設計, use studio:optimizing-search-visibility instead. For BigQuery への GA4 エクスポートを使った大規模分析, use cloud:developing-google-cloud instead. For MCP サーバーそのものの開発・プロトコル, use lang:developing-mcp instead.
tools1
developing-react
React 19.x development guide covering React 19 features (Actions, useActionState, useOptimistic, View Transitions, Activity, useEffectEvent), internals (rendering principles, memoization, Context/data flow), design patterns (Container/Presenter, HOC, Render Props, Compound Components), state management (useState to Zustand/TanStack Query, nuqs/Jotai), error handling (ErrorBoundary, React 19 error APIs), accessibility (ARIA, focus management, keyboard navigation, WCAG 2.1 AA), performance optimization (react-doctor 47+ rules, React Compiler, hydration/PPR), UI animation patterns (CSS transitions, easing), React Testing Library (RTL queries, userEvent, MSW mocks, TDD patterns), and Storybook (CSF3, interaction testing, a11y). Also covers React Router, auth/RBAC, i18n (react-i18next), OpenAPI type generation, and production architecture. Use when package.json contains 'react' (without 'next'), or when working on React-specific concerns in any framework.
development1
using-next-devtools
Next.js development integration tools via the next-devtools MCP (nextjs_runtime, upgrade_nextjs_16, enable_cache_components, nextjs_docs). Covers dev-server discovery, route structure inspection (nextjs_get_routes), error diagnostics with automatic fixes (nextjs_get_errors / nextjs_auto_fix), automated version upgrades with codemods for Next.js/React, Cache Components setup (Suspense boundaries, "use cache" directive insertion), and official docs search. Use when interacting with the next-devtools MCP on a running dev server (requires Next.js 16.0.0+ and a started dev server via npm run dev). Primary tool for next-devtools MCP interactions. For Next.js framework patterns (App Router, Server Components, caching APIs, Prisma/Zod), use developing-nextjs instead.
tools1
implementing-dynamic-authorization
Dynamic authorization design covering ABAC, ReBAC, PBAC models and Cedar policy language. Use when designing access control systems, choosing authorization models, or writing Cedar policies. Distinct from securing-code (code-level) by focusing on authorization model selection and policy-based access control.
development1
developing-aws
AWS development guide covering serverless (Lambda, API Gateway, DynamoDB), CDK, EKS, ECS/Fargate, SRE, FinOps, security (IAM, VPC, KMS, GuardDuty), GenAI (Bedrock, RAG), databases (Aurora, ElastiCache), data engineering (Glue, Athena, Redshift), 57 Cloud Design Patterns, VPC architecture, enterprise architecture (multi-account, Landing Zone, Cognito), cloud migration (7R, DMS), and HA/fault tolerance. Use when working with AWS services, CDK infrastructure, or serverless applications. MUST load when working with AWS services, detected by aws-cdk or @aws-sdk in package.json, cdk.json, samconfig.toml, serverless.yml, template.yaml (SAM), or eksctl configs.
development1
architecting-data
Data architecture patterns covering read-side optimization (replicas, materialized views, CQRS, CDC, event sourcing), domain-based decomposition, polyglot persistence, and caching strategies (cache-aside, read-through, write-through, write-around). Use when designing data flow architecture, choosing read scalability strategies, or implementing caching for enterprise systems. For microservices patterns (Saga, granularity), use architecting-infrastructure instead. For DDD domain modeling, use applying-clean-architecture instead. For database engine internals, use developing-databases instead. For relational DB schema design, use developing-databases instead. For GCP-specific data services (BigQuery, Dataflow, Dataproc), lakehouse (BigLake, Dataplex), and BigQuery advanced operations (editions, HA/DR), use developing-google-cloud instead.
development1
reviewing-code
コードレビューガイドライン（PR構成・効果的コメント・トーン原則・CodeRabbit統合）。 Use when reviewing code, creating PRs, or using CodeRabbit for automated review. 3原則（客観性・具体性・明確なアウトカム）、自動修正ループを含む。
development1
building-ai-agents
AIエージェント構築ガイド（LangChain/LangGraph・Google ADK・リアルタイムマルチモーダル）。 Use when building AI agents with LangChain, LangGraph, Google ADK, or Gemini Live API. フレームワーク選択、ツール定義、マルチエージェント、A2A、リアルタイム音声/動画を含む。
development1
compressing-epub-images
EPUB ファイル内の画像（主にスキャン本の JPEG）を再エンコード・リサイズしてファイルサイズを削減するスキル。AskUserQuestion で圧縮レベル選択フローを提供し、実測サンプリングから予測サイズを提示してからユーザーに選ばせる。 Use when: EPUB ファイルが大きく画像圧縮で削減したい時、スキャン本（画像ベース EPUB）の容量を減らしたい時、Kindle などの電子書籍リーダーに転送する前にサイズ最適化したい時。 画像ベース EPUB（スキャン本）と通常 EPUB の両方に対応。書誌情報・xhtml・css は触らず画像のみ再エンコード。
development1
practicing-devops
DevOps実践ガイド（進化3ステージ・IaCツール選定・オーケストレーション・CI/CD・コンテナ管理）。 Use when practicing DevOps, selecting IaC tools, designing CI/CD pipelines, or managing Docker/Podman containers. Docker/Podman、マルチステージビルド、Compose、セキュリティ強化を含む。 For continuous delivery philosophy, CD maturity assessment, and deployment pipeline design principles, see CONTINUOUS-DELIVERY.md subfile. For project foundations, team organization, and developer habits, use practicing-software-engineering instead. For monitoring and observability design, use implementing-observability instead. For GCP CI/CD and GKE container orchestration, use developing-google-cloud instead. For GPU-optimized Docker/Kubernetes environment tuning (NVIDIA Container Toolkit, MPS, MIG), use designing-genai-patterns instead.
tools1
practicing-product-management
プロダクトマネジメント総合ガイド（基礎・AIプロダクト・A/Bテスト・成長戦略・GPM・PLG・カスタマーサクセス・Claude Code PM活用）。 Use when practicing product management, managing AI products, designing experiments, growth product management, PLG strategy, customer success, or using Claude Code as PM tool. AARRR海賊指標、AIプロダクトライフサイクル、MLプロダクト化、AI統合戦略、オンライン実験設計、PM調査パターン、GPM実践、リテンション戦略、拡張収益を含む。 For engineer-focused user story writing techniques (templates, common mistakes, splitting), use writing-user-stories instead.
tools1
writing-user-stories
Guides effective user story creation for software projects covering story templates (As a.../I want.../So that...), common mistakes, technical requirements to story conversion, acceptance criteria writing, and story splitting techniques. Use when writing user stories, converting technical requirements to stories, or improving backlog quality. For product management practices (PRD, roadmap, prioritization), use practicing-product-management instead.
testing1
orchestrating-codex
Codex CLI統合スキル（基本操作・プランレビュー・Agentオーケストレーション）。 Use when using Codex for code consultation, plan review, or orchestrating Codex agents in Wave parallel execution. Triggers: "codex", "codexと相談", "codexでレビュー", "codexでオーケストレーション"。Wave計画に基づき自然言語でagentを同時起動し、config.tomlのmax_threadsで並列度を宣言的に制御する。 For agent conversion to Codex format, use converting-agents-to-codex instead.
tools1
testing-e2e-with-playwright
Playwright E2Eテストの設計・実装・運用ガイド。 Use when writing, reviewing, or maintaining E2E tests with @playwright/test. playwright.config.* 検出時に自動ロード。testing-code（テスト全般）とは異なりPlaywright E2E固有のパターンに特化。
development1
developing-mcp
Comprehensive MCP (Model Context Protocol) development guide covering architecture (Host/Client/Server roles, Tools/Resources/Prompts, Control Segregation), server and client implementation with TypeScript SDK, protocol specification (JSON-RPC 2.0, stdio/Streamable HTTP), and security threats (Tool Poisoning, Shadowing, Rug Pull, Prompt Injection). MUST load when building MCP servers or clients. For Claude Code plugin MCP configuration, use authoring-plugins instead. For MCP integration with Vercel AI SDK in web apps, see integrating-ai-web-apps. For consuming MCP tools from LangGraph agents, see building-ai-agents.
tools1
writing-user-stories
Guides effective user story creation for software projects covering story templates (As a.../I want.../So that...), common mistakes, technical requirements to story conversion, acceptance criteria writing, and story splitting techniques. Use when writing user stories, converting technical requirements to stories, or improving backlog quality. For product management practices (PRD, roadmap, prioritization), use practicing-product-management instead.
testing1
designing-frontend
Creates distinctive, production-grade frontend code with shadcn/ui integration, object-oriented UI (OOUI) methodology, and micro-frontend architecture patterns. Use when implementing web components, pages, or applications requiring creative, polished UI code; when designing UI structure using object-oriented approach (object extraction, view/navigation patterns, layout pattern selection); or when architecting micro-frontend systems (team splitting, Module Federation, BFF patterns, migration strategy, Conway's Law application). For Storybook story creation and component testing, use developing-react instead. For theoretical UI/UX design principles, use designing-ux instead. For Tailwind CSS methodology, component design patterns, and design system construction, use styling-with-tailwind instead. For design system methodology (pattern language, organizational strategy, UI pattern catalog, anti-patterns), use building-design-systems instead.
development1
automating-browser
Browser Agent CLIによるブラウザ操作自動化（セマンティックロケーター、状態永続化、ネットワーク傍受）。 Use when automating browser interactions via agent-browser CLI (NOT for E2E testing). E2Eテストは testing-e2e-with-playwright スキルを参照。
tools1
managing-claude-md
Manages CLAUDE.md creation, improvement, and maintenance following 8 core principles (size limits, progressive disclosure, essential elements, living documentation). Use when starting new projects, reviewing existing CLAUDE.md, or when Claude repeatedly makes the same mistakes. For skill file authoring, use authoring-plugins instead.
tools1
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
data-ai1
securing-ai-development
Organizational security strategy for AI-powered software development covering trust frameworks, adaptive guardrails, AI-BOM, AI-SPM, governance models, and cross-functional ownership. Use when establishing security controls for AI coding assistants, agentic systems, or AI-accelerated SDLC workflows. For code-level security (OWASP, CodeGuard), use securing-code instead. For AI development methodology (prompts, context engineering), use developing-with-ai instead. For LLM-specific security (prompt injection, LLMSecOps), use designing-genai-patterns.
development1
authoring-plugins
Claude Code Plugin (Agent / Skill / Command) authoring guide. Use when creating, modifying, or reviewing plugin components. Includes Agent Skills standard (agentskills.io) + Claude Code extensions, context: fork applicability matrix, name/description constraint validation, and spec-freshness checks.
tools1
chronicle
Allows you to view the user's screen as well as several hours of history. Use when the user makes a reference to their recent work, for which it'd be helpful to see the screen. This skill MUST be used whenever you need to resolve ambiguity in a user request, where the user hasn't specified enough context to do the task. Examples include disambiguating the specific user/app/document/error the user is referring to. You must also use this skill if the user asks about any question regarding Chronicle or asks what you can see from the screen.
testing1
creating-slides
HTMLスライド作成スキル。slides repoの3層分離モデル（Engine/Theme/Content）に基づく16:9 HTMLプレゼンデッキの作成・テーマカスタマイズ・ソース素材変換をガイド。認知科学・ロジック構築（接続関係診断・基本ロジック図）・ストーリーテリング・聴衆分析・スライドデザイン・ビジュアルデザイン実践・提案書構成術（ロジック3つの力・MECE・メッセージマップ）・デリバリー（実践Tips集含む）・準備プロセスの9リファレンスで品質を担保。国際学会・学術研究発表（Q&A・ネットワーキング・ポスター発表・英語表現・発音）向け専門リファレンス6本も収録。 Use when creating HTML slide decks, converting source materials to slides, customizing slide themes, initializing new slide projects, or preparing international conference presentations and academic research talks. Delegates actual slide creation to the tachikoma-doc-slide agent (falls back to direct creation when subagents are unavailable, e.g. Codex CLI). For presentation quality improvement (storytelling, delivery, engagement) use designing-training. For text polishing use devkit:writing-effective-prose. For marketing copy use creating-content. For consultant-quality single-slide PowerPoint (.pptx) use creating-pptx. For Google Slides editing via the gws CLI use gws-slides.
tools1
designing-frontend
Creates distinctive, production-grade frontend code with shadcn/ui integration, object-oriented UI (OOUI) methodology, and micro-frontend architecture patterns. Use when implementing web components, pages, or applications requiring creative, polished UI code; when designing UI structure using object-oriented approach (object extraction, view/navigation patterns, layout pattern selection); or when architecting micro-frontend systems (team splitting, Module Federation, BFF patterns, migration strategy, Conway's Law application). For Storybook story creation and component testing, use developing-react instead. For theoretical UI/UX design principles, use designing-ux instead. For Tailwind CSS methodology, component design patterns, and design system construction, use styling-with-tailwind instead. For design system methodology (pattern language, organizational strategy, UI pattern catalog, anti-patterns), use building-design-systems instead.
development1
converting-agents-to-codex
Claude Code Agent定義（.md）をCodex subagent定義（agents/*.toml）に変換するガイド。 フィールドマッピング・developer_instructions変換・skills.config展開・検証手順・よくある失敗パターンを網羅。 Use when converting Claude Code agents to Codex format, migrating agent definitions, or setting up Codex subagents. Triggers: "agentをcodexに変換", "codex agent変換", "agent migration"。
development1
solving-algorithms
Comprehensive algorithm and data structure reference for competitive programming covering sorting, searching, trees, graphs, dynamic programming, computational geometry, and number theory with complexity analysis and language-agnostic implementations. Use when solving algorithmic problems, optimizing code for time/space complexity, or implementing classic data structures (stack, queue, heap, BST, union-find). For database-specific data structures (B-tree, LSM), use developing-databases instead.
development1
searching-web
Web検索統合スキル。Exa MCP（第一優先）による高度検索（7カテゴリ: Company, Code, People, Financial Report, Research Paper, Personal Site, Tweet/X）と、gemini CLI（フォールバック）による複雑なクエリ検索を統合。 Use when performing web searches, researching technologies, companies, people, academic papers, or social media. Load Exa MCP first; fall back to gemini CLI when Exa is unavailable. MUST load as first-choice search tool. context7 for library docs, deepwiki for GitHub wiki, WebSearch built-in as last resort.
tools1
designing-ux
UXデザイン総合ガイド（認知心理学・UIガイドライン・グラフィック基礎・デザイン思考・AIエクスペリエンス設計・Webビジュアルデザイン実践・UXメソッド実践）。 Use when designing user experiences, UI, conducting design thinking workshops, designing AI interfaces, creating web page layouts and visual designs, defining web design concepts using functionality/emotionality frameworks, or implementing UX methods such as usability evaluations, prototyping, user research, journey mapping, and organizational UX adoption. デザイン思考（d.school 5ステップ）、AIインターフェース設計（メンタルモデル、Copilotパターン）、Webレイアウト・配色・UIコンポーネント・モーションデザイン、Webデザイン機能性7軸・情緒性6軸フレームワーク、デザインコンセプト立案プロセス、レイアウト実践パターン（即応用可能な判断パターン集）、イメージワードシステム（デザイン方向性の言語化・共有手法）、クリエイティブプロセスパターン（プロの制作プロセス・発想法・試作サイクル）を含む。実践メソッド（PRACTICE-*）としてユーザビリティ評価・プロトタイピング・構造化シナリオ法・ユーザーリサーチ・カスタマージャーニーマップ・組織導入戦略を含む。
development1
creating-flashcards
Creates Anki flashcards from EPUB/PDF files via Anki MCP Server, covering MCP setup, deck/note-type management, and bulk import with HTML formatting. Use when converting textbooks, question banks, or study materials into spaced repetition flashcards, or when managing Anki cards via MCP tools. Covers full workflow: MCP setup → file conversion → content analysis → batch card creation. For MCP server/client development, use developing-mcp instead.
tools1
testing-with-vitest
Vitest 4.x specialized testing guide covering the test runner core: v3 to v4 migration and breaking changes (maxWorkers, test.projects, module runner, coverage overhaul), configuration (environments, coverage v8/istanbul, reporters), CLI and test filtering/tags, parallelism and performance (pools, sharding), Browser Mode (stable in v4, visual regression), fixtures and test context (test.extend), lifecycle hooks (aroundEach/aroundAll, globalSetup), mocking (vi API, modules, timers, MSW), matchers, type testing, and in-source testing. Use when package.json contains vitest or vitest.config.* is present, or when configuring, migrating, or optimizing Vitest. For framework-agnostic test methodology (TDD, AAA, test pyramid, four pillars, anti-patterns), use testing-code. For React Testing Library and React component testing, use lang:developing-react. For Playwright E2E, use testing-e2e-with-playwright.
tools1
developing-processing
Processing (Java Mode) のスケッチ開発と、Processing 4 CLI(processing cli)による自動コンパイル・実行・検証ループ。 Use when 大学等で .pde スケッチを書く / Processing でビジュアル・インタラクティブ作品やジェネラティブアート・データ可視化を作る / 作成したスケッチをコマンドラインで自動コンパイル(--build)・実行(--run)して検証したいとき。 補足トリガー: .pde ファイル, Processing.app, processing cli, sketch, setup()/draw(), creative coding。 詳細は CLI.md(CLI完全リファレンス) / REFERENCE.md(言語API) / LIBRARIES.md(ライブラリ) / EXAMPLES.md(スケッチ雛形と検証例) / scripts/verify-sketch.sh(検証ヘルパー) を参照。
tools1
writing-clean-code
REQUIRED for all code implementations. Automatically load when writing or reviewing any code. Covers SOLID principles, MAPPER principles with 25 code smell categories, practical refactoring, software design laws, the 4 rules of simple design, 66 code smell heuristics, formatting principles, dependency injection / composition roots, and boundary management patterns. Language-agnostic clean code guide. For language-specific practices, use lang:developing-go, mastering-typescript, or lang:developing-python. For architecture-level clean design, use applying-clean-architecture. For legacy code refactoring, see CHANGEABLE-CODE.md subfile. For refactoring mindset (spikes, feature toggles, structural discovery), see REFACTORING-MINDSET.md reference. For project-, environment-, and collaboration-level simplicity beyond code (technology minimalism, personal automation, cutting self-induced complexity), use pursuing-simplicity.
tools1
practicing-devops
DevOps実践ガイド（進化3ステージ・IaCツール選定・オーケストレーション・CI/CD・コンテナ管理・プラットフォームエンジニアリング/IDP）。 Use when practicing DevOps, selecting IaC tools, designing CI/CD pipelines, or managing Docker/Podman containers. Docker/Podman、マルチステージビルド、Compose、rootless/Quadlet、セキュリティ強化を含む。 For continuous delivery philosophy, CD maturity assessment, and deployment pipeline design principles, see CONTINUOUS-DELIVERY.md subfile. For Terraform/OpenTofu HCL development and module design, use developing-terraform instead. For project foundations, team organization, and developer habits, use devkit:practicing-software-engineering instead. For monitoring and observability design, use implementing-observability instead. For GCP CI/CD and GKE container orchestration, use developing-google-cloud instead. For GPU-optimized Docker/Kubernetes environment tuning (NVIDIA Container Toolkit, MPS, MIG), use ai:designing-genai-patterns instead.
tools1
implementing-design
Comprehensive design-to-code implementation skill covering general design principles, Figma MCP integration, and Figma UI design workflows. General: design system integration, visual parity validation, responsive implementation, accessibility. Figma MCP (13 tools): basic/advanced workflows (Figma Make, Code Connect, Design System Rules, design token sync), visual validation. Figma UI design: wireframe→prototype→detailed design→handoff workflow, 8pt grid, component-driven design, UIStack (5 states), style naming conventions, engineer collaboration. Use when implementing designs from any source (screenshots, mockups, Figma URLs, specs) or when designing mobile UI in Figma and preparing design handoff. Requires Figma MCP server for Figma-specific code generation workflows. For creative frontend code generation with shadcn/ui and Storybook, use designing-frontend instead. For design system architecture and organizational adoption strategy, use design:building-design-systems instead.
tools1
implementing-as-tachikoma
Operates as Tachikoma Agent (Implementation Worker) performing actual code implementation, test creation, and documentation based on task assignments from Claude Code. Covers the worker lifecycle: worktree-confined work (no worktree creation/deletion, no git add/commit/push — git writes are user-executed), serena MCP-first code editing, parallel execution criteria, tachikoma1-4 specializations (frontend/UI, backend/API, testing/QA, infrastructure/DevOps), mandatory software-security check before completion, and the completion report format. Use when receiving task assignments from Claude Code for implementation work, test creation, or documentation as a worker agent. For orchestrating multiple Tachikoma agents in parallel (team formation, planning), use orchestrating-teams instead. For Codex-side orchestration, use orchestrating-codex instead. For detailed serena MCP usage, use using-serena instead.
tools1
practicing-design-thinking
Design thinking process and UX research methodology: empathize/define/ideate/prototype/test, HCD process (ISO 9241-210), user research methods, journey maps, personas, prototyping, structured scenario method, usability evaluation, 100 phased UX principles (Consider/Empathize/Define/Research/Design/Validate checklists), and a 3-level organizational adoption framework. Use when running design-thinking workshops or UX research, or conducting user-centered design activities such as persona creation, journey mapping, scenario writing, usability evaluation, or organizational UX adoption and change management. For UI/visual design principles use designing-ux. For AI experience design (agentic UX, AI-first interfaces) use designing-ai-experiences. For behavior-change product design use applying-behavior-design. For design system construction and governance use building-design-systems.
development1
reviewing-code
コードレビューガイドライン（PR構成・効果的コメント・トーン原則・レビュアー/PR作成者の姿勢・チーム合意（TWA）・アンチパターン回避・CodeRabbit統合）。 Use when reviewing code, creating PRs, establishing team review agreements, or using CodeRabbit for automated review. 3原則（客観性・具体性・明確なアウトカム）、自動修正ループを含む。 For pair programming patterns and team organization, use practicing-software-engineering instead. For commit message format, use writing-conventional-commits instead. For generating PR descriptions, use the pull-request command. For GitLab MR operations via the glab CLI, use operating-gitlab instead.
tools1
building-ai-agents
AIエージェント構築ガイド（LangChain/LangGraph・Google ADK・リアルタイムマルチモーダル）。 Use when building AI agents with LangChain, LangGraph, Google ADK, or Gemini Live API. フレームワーク選択、ツール定義、マルチエージェント、A2A、RAGパイプライン、リアルタイム音声/動画を含む。 For framework-agnostic GenAI design patterns, use designing-genai-patterns. For JS/Vercel AI SDK web integration, use integrating-ai-web-apps. For MCP protocol/server design, use lang:developing-mcp.
tools1
developing-with-ai
AI-assisted development methodology covering prompt engineering, context engineering, code generation workflows, quality assurance, collaborative debugging, agent collaboration patterns, LLM dialogue design patterns (8 conversational patterns, Grammar of Intention, Test-Driven Prompting), team LLM adoption workshops, and role-specific augmentation (Dev/PO/Coach/Manager). MUST load when working with AI coding tools or discussing AI-assisted development practices. Use when crafting prompts for code generation, managing AI context, reviewing AI-generated code, coordinating multi-agent workflows, or designing structured LLM dialogues.
tools1
developing-aws
AWS development guide covering serverless (Lambda, API Gateway, DynamoDB), CDK, EKS, ECS/Fargate, SRE, FinOps, security (IAM, VPC, KMS, GuardDuty), GenAI (Bedrock, RAG), databases (Aurora, ElastiCache), data engineering (Glue, Athena, Redshift), 57 Cloud Design Patterns, VPC architecture, enterprise architecture (multi-account, Landing Zone, Cognito), cloud migration (7R, DMS), and HA/fault tolerance. Use when working with AWS services, CDK infrastructure, or serverless applications. MUST load when working with AWS services, detected by aws-cdk or @aws-sdk in package.json, cdk.json, samconfig.toml, serverless.yml, template.yaml (SAM), or eksctl configs.
development1
answering-genai-exam
生成AI活用試験の問題画像（左=問題文・右=回答欄の見開きスクリーンショット）を読み取り、各小問について「対話の要点」（自分: ○○ → AI: ○○ → … 形式・最大1000字）と提出物（拡張子で分岐: .md=markdown回答本文 / 画像系=画像生成AIへのテキスト指示 / コード系=ソースコード）を生成し、入力画像と同じディレクトリの answers/<問番号>/ 配下にファイルとして保存する。 Use when 生成AI活用試験・資格試験の問題スクリーンショット（ローカル画像パス・複数可）を渡され、各小問の対話の要点と回答提出物を一括作成して保存したいとき。「この試験問題を解いて」「対話の要点と提出物を作って」等の依頼が該当する。 複数画像は Workflow で問ごとに並列求解する（第一推奨）。Workflow 不可時は exam-solver agent を画像ごとに background 並列起動する代替経路、単一エージェント環境（agent も Workflow も不可）では逐次処理にフォールバックする。曖昧点（試験分野・提出物形式・解答方針・既存answers上書き）は並列起動前に AskUserQuestion で必ず一括解消する。画像系/PDF提出物は既定で指示文のみだが、opt-inで実PNG/実PDFをレンダリングできる（references/RENDERING.md）。詳細手順は INSTRUCTIONS.md、Workflow 雛形は references/WORKFLOW-SCRIPT.md、出力規約は references/OUTPUT-FORMAT.md、出力サンプルは assets/answer-template.md を参照。
development1
architecting-data
Data architecture patterns covering read-side optimization (replicas, materialized views, CQRS, CDC, event sourcing), domain-based decomposition, polyglot persistence, and caching strategies (cache-aside, read-through, write-through, write-around). Use when designing data flow architecture, choosing read scalability strategies, or implementing caching for enterprise systems. For microservices patterns (Saga, granularity), use architecting-infrastructure instead. For DDD domain modeling, use devkit:applying-clean-architecture instead. For database engine internals and relational DB schema design, use lang:developing-databases instead. For GCP-specific data services (BigQuery, Dataflow, Dataproc), lakehouse (BigLake, Dataplex), and BigQuery advanced operations (editions, HA/DR), use developing-google-cloud instead.
development1
developing-mcp
Comprehensive MCP (Model Context Protocol) development guide covering architecture (Host/Client/Server roles, Tools/Resources/Prompts, Control Segregation), server and client implementation with TypeScript SDK (including MCP Gateway pattern and MCP Inspector debugging), protocol specification (JSON-RPC 2.0, stdio/Streamable HTTP transports, session management), security threats and countermeasures (Prompt Injection, Tool Poisoning, Shadowing, Rug Pull, OAuth 2.1 authorization, container sandboxing), and the MCP ecosystem (registries, official SDKs, A2A protocol relationship). MUST load when building MCP servers or clients. For Claude Code plugin MCP configuration, use devkit:authoring-plugins instead. For MCP integration with Vercel AI SDK in web apps, see ai:integrating-ai-web-apps. For consuming MCP tools from LangGraph agents, see ai:building-ai-agents.
tools1
developing-python
Modern Python development guide covering project setup, tooling, Pythonic best practices, OOP design principles, GoF design patterns, SE process, and type safety. MUST load when pyproject.toml or requirements.txt is detected. Covers Python 3.13 + uv + ruff + mypy, FastAPI/FastMCP, pytest, Docker, Pythonic best-practice idioms, software design patterns (encapsulation, LSP, Design by Contract), SE practices (SDLC, Scrum/Kanban, CI/CD, deployment), type safety rules (Any prohibition, TypedDict, Protocol, dataclass), Architecture Patterns (Repository, Unit of Work, Aggregates, Domain Events, CQRS, Event-Driven Architecture), and DDD Tactical Patterns (Value Object, Entity, Aggregate Root). For language-agnostic clean code principles, use devkit:writing-clean-code. For application logging design, use cloud:implementing-observability. For Clean Architecture in Python, see references/CA-PYTHON.md. For general Clean Architecture principles, use devkit:applying-clean-architecture.
tools1
designing-ux
UXデザイン総合ガイド（認知心理学・UIガイドライン・グラフィック基礎・インターフェイス哲学・UXエレメント5段階モデル・UIデザイン実践TIPS・Webビジュアルデザイン実践）。 Use when designing user experiences, UI, creating web page layouts and visual designs, defining web design concepts using functionality/emotionality frameworks, or referencing UI/graphic design principles and interaction philosophy. 認知心理学基盤（知覚・記憶・思考）、UIデザインガイドライン（コンポーネント・マルチデバイス・ユーザビリティ）、グラフィックデザイン基礎（造形・色彩・タイポグラフィ・レイアウト）、インターフェイス哲学（Fluid Interfaces・モーション理論・ウェルビーイング）、UXエレメント5段階モデル（Strategy/Scope/Structure/Skeleton/Surface）、UIデザイン実践TIPS（状態設計・フィードバック・コンポーネント選択）、Webビジュアルデザイン実践（機能性7軸・情緒性6軸・コンセプト策定）を含む。デザイン思考プロセス・ユーザーリサーチは practicing-design-thinking スキルへ。AIエクスペリエンス設計は designing-ai-experiences スキルへ。
development1
find-skills
Discovers and installs agent skills from the open skills ecosystem using the Skills CLI (npx skills find / add / check / update) and the skills.sh registry and leaderboard, vetting candidates by install count and source reputation before recommending or installing them. Use when the user asks questions like "how do I do X", "find a skill for X", "is there a skill that can...", wants to search for tools, templates, or workflows, or expresses interest in extending agent capabilities with installable skills. For evaluating npm/pip/Go code libraries, use researching-libraries instead. For authoring local plugin/skill components, use authoring-plugins instead.
tools1
creating-pptx
箇条書き・メモ・素朴なスライドを「6つの構造」で組み直し、So What（だから何が言えるか）まで届くコンサル品質の1枚スライドを、編集可能な PowerPoint（.pptx）とプレビュー画像（.png）のハイブリッドで生成するスキル。情報を足すのではなく削り、情報の差と余白で意思決定を一目で促す。 Use when creating or remaking a consultant-quality single slide as an editable PowerPoint (pptx) from rough notes, bullet points, or an existing slide — restructuring into a So-What-driven 16:9 deliverable with strict flat design discipline (6-color palette, Noto Sans JP, grid alignment). 手動呼び出し専用（/creating-pptx）。For multi-slide HTML decks use creating-slides. For Google Slides editing use gws-slides. For standalone diagrams use creating-diagrams. For data-visualization theory use design:designing-data-visualizations.
development1
searching-web
Web検索統合スキル。Exa MCP（第一優先）によるカテゴリ別高度検索（7カテゴリ: Company, News, Tweet/X, People, Personal Site, Financial Report, Research Paper）・コード検索（get_code_context_exa）・URL crawling（crawling_exa）・deep research と、gemini CLI（フォールバック・scripts/web-search.sh）による複雑なクエリ検索を統合。 Use when performing web searches, researching technologies, companies, people, academic papers, news, or social media. Load Exa MCP first; fall back to gemini CLI when Exa is unavailable. MUST load as first-choice search tool. context7 for library docs, deepwiki for GitHub wiki, WebSearch built-in as last resort. For evaluating npm/pip/Go libraries before implementation, use researching-libraries instead.
tools1
converting-content
コンテンツ変換ガイド（画像ベースEPUB→テキストOCR変換・LM Studio英日翻訳）。 Use when converting image-based EPUBs to text or translating content with LM Studio. pandoc、recognize-image.py OCR、ローカルLLM翻訳ワークフローを含む。For image compression/size reduction use compressing-epub-images; for Anki flashcards use creating-flashcards.
documentation1
securing-code
REQUIRED after all code implementations. Automatically load when implementation is complete to run CodeGuard security check. Covers input validation, secrets management, OWASP top 10 countermeasures, authentication/authorization patterns, web penetration testing (reconnaissance, attack techniques, bypass methods), and serverless security (IAM/storage/functions across AWS/GCP/Azure, 17 threat categories, supply chain attacks). Use when implementing any code, handling external input, or developing serverless applications (Lambda, Cloud Run, Azure Functions). For dynamic authorization model design (ABAC/ReBAC/Cedar), use implementing-dynamic-authorization instead. For organizational AI development security strategy (trust frameworks, governance, AI-BOM), use securing-ai-development instead. For security logging patterns and compliance logging, use implementing-observability.
development1
developing-bash
Comprehensive Bash shell scripting and automation guide covering fundamentals, control flow, I/O pipelines, process control, system administration automation, testing/debugging, security, design patterns, and penetration testing automation (Nmap, web scanning, exploitation, Wi-Fi assessment, reporting). MUST load when .sh files are detected or shell scripts are being written. For Docker-specific patterns, use cloud:practicing-devops instead. For broader DevOps methodology, use cloud:practicing-devops instead.
tools1
automating-browser
Browser Agent CLIによるブラウザ操作自動化（セマンティックロケーター、状態永続化、ネットワーク傍受）。 Use when automating browser interactions via agent-browser CLI (NOT for E2E testing). E2Eテストは testing-e2e-with-playwright スキルを参照。
tools1
developing-google-cloud
Google Cloud guide: Cloud Run, GCP security (IAM/VPC/KMS/Zero Trust), data engineering (BigQuery/Dataflow/pipelines/governance/lakehouse), networking (VPC/LB/CDN), Memorystore, enterprise architecture, compute selection (GCE/GKE/GAE/Run/Functions), GKE, GAE, monitoring (SLO/SLI), BigQuery analytics (SQL/window functions/GA4), BigQuery ops (editions/HA-DR/slots), workflow (Composer/Dataform/Data Fusion), BI (Looker/Looker Studio/BI Engine), ingestion (DTS/Datastream CDC/GA4), real-time (Pub/Sub/Dataflow streaming), ML (BigQuery ML/Vertex AI/GIS). MUST load when google-cloud packages, cloudbuild.yaml, BigQuery/Dataflow/Memorystore/Looker/Dataplex detected. For Docker→practicing-devops. For monitoring→implementing-observability. For OWASP→securing-code. For CQRS→architecting-data. For AWS→developing-aws. For GenAI→designing-genai-patterns. For Firebase (Auth/Firestore/Storage/Functions/Hosting)→developing-firebase.
development1
designing-frontend
Creates distinctive, production-grade frontend code with bold aesthetic direction (typography, color, motion, anti-AI-slop), shadcn/ui integration, object-oriented UI (OOUI) methodology, and micro-frontend architecture patterns. Use when implementing web components, pages, or applications requiring creative, polished UI code; when designing UI structure using object-oriented approach (object extraction, view/navigation patterns, layout pattern selection); or when architecting micro-frontend systems (team splitting, Module Federation, BFF patterns, migration strategy, Conway's Law application). For Storybook story creation and component testing, use developing-react instead. For theoretical UI/UX design principles, use design:designing-ux instead. For Tailwind CSS methodology and component design patterns, use styling-with-tailwind instead. For design system methodology (pattern language, organizational strategy, UI pattern catalog), use design:building-design-systems instead.
development1
researching-libraries
Researches existing libraries before implementation to prevent reinventing the wheel. REQUIRED before writing any new functionality. Use when evaluating npm packages, pip packages, Go modules, or any third-party libraries to find and evaluate existing solutions. For generic web/company/people/paper search and search-tool routing, use searching-web instead.
tools1
writing-effective-prose
Unified writing and editorial-quality guide covering natural prose, evidence-grounded revision, AI-pattern diagnosis, citation integrity, output-artifact cleanup, prose fundamentals, technical and engineering docs, academic and university writing, Japanese prose, web and UX copy, FAQs, tech blogs, README files, Zenn publishing, persuasive documents, and sensory writing. REQUIRED for all text output: apply the integrity and natural-prose pass without claiming AI detector evasion. Use when writing, reviewing, proofreading, rewriting, translating, or creating documents such as articles, reports, slides, emails, papers, theses, requirements, design docs, business documents, help content, and developer documentation. For LaTeX → studio:writing-latex. For presentations → studio:creating-slides.
development1
building-multi-tenant-saas
Multi-tenant SaaS architecture covering control plane/application plane design, deployment models (silo, pool, hybrid, pod), tenant isolation, data partitioning, and container/serverless compute patterns. Use when designing SaaS platforms, evaluating silo vs pool strategies, or planning SaaS migration. Covers identity, onboarding, tenant context injection, tiering, and operations. For Next.js single-tenant SaaS (auth, payments), use web:developing-nextjs instead. For vendor-neutral infrastructure and microservices patterns, use architecting-infrastructure instead. For data-flow architecture and CQRS/polyglot persistence, use architecting-data instead.
development1
developing-google-cloud
Google Cloud guide: Cloud Run, GCP security (IAM/VPC/KMS/Zero Trust), data engineering (BigQuery/Dataflow/pipelines/governance/lakehouse), networking (VPC/LB/CDN), Memorystore, enterprise architecture, compute selection (GCE/GKE/GAE/Run/Functions), GKE, GAE, monitoring (SLO/SLI), BigQuery analytics (SQL/window functions/GA4), BigQuery ops (editions/HA-DR/slots), workflow (Composer/Dataform/Data Fusion), BI (Looker/Looker Studio/BI Engine), ingestion (DTS/Datastream CDC/GA4), real-time (Pub/Sub/Dataflow streaming), ML (BigQuery ML/Vertex AI/GIS). MUST load when google-cloud packages, cloudbuild.yaml, BigQuery/Dataflow/Memorystore/Looker/Dataplex detected. For Docker→practicing-devops. For monitoring→implementing-observability. For OWASP→devkit:securing-code. For CQRS→architecting-data. For AWS→developing-aws. For GenAI→ai:designing-genai-patterns. For Firebase (Auth/Firestore/Storage/Functions/Hosting)→developing-firebase.
development1
applying-behavior-design
Behavioral design methodology for products that change user behavior using CREATE Action Funnel (Cue, Reaction, Evaluation, Ability, Timing) and three strategies (cheat, habit, conscious action). Covers behavior discovery (target outcome/actor/action selection), behavior plans, interface tactics per funnel stage, dual-process psychology foundations, and impact measurement/improvement. Use when designing product features that aim to change user habits, increase engagement, or guide users toward beneficial actions. For visual UI/UX design principles, use designing-ux instead. For human-centered design thinking process (user research, ideation, prototyping), use practicing-design-thinking instead. For training program design and facilitation methodology, use studio:designing-training instead.
development1
designing-ai-experiences
AI experience (AIX) design guide: agentic UX (5 agentic patterns, human-in-the-loop checkpoints/permissions), Copilot placement patterns for SaaS, user mental models, AI-first interfaces (IA, forecasting/anomaly-detection UI), input design (3-channel model, CARE Framework, voice), computation UX (pipeline, routing, latency), output design (5 principles: Clear/Verifiable/Grounded/Actionable/Adjustable, overreliance countermeasures, watermarking), framing (storyboards, digital twin, Value Matrix), AI user research (MUSE, RITE), and AI ethics/bias. Use when designing AI-powered product UX or human-AI interaction patterns such as agentic systems, Copilot features, prompt UI, AI output presentation, or validating AI use cases. For general UI/UX & visual design use designing-ux. For design-thinking process & UX research use practicing-design-thinking. For behavior-change product design use applying-behavior-design. For technical GenAI architecture patterns (RAG, guardrails, LLMOps) use ai:designing-genai-patterns.
development1
chronicle
Views the user's screen and several hours of screen-recording history via the Chronicle (Codex screen recording) feature: reads the latest per-display frame, greps OCR sidecars (*.ocr.jsonl) for recent on-screen text, inspects historical 1-minute frames across multiple displays, and consults Chronicle memories. Use when the user makes a reference to their recent work, for which it'd be helpful to see the screen. This skill MUST be used whenever you need to resolve ambiguity in a user request, where the user hasn't specified enough context to do the task. Examples include disambiguating the specific user/app/document/error the user is referring to. You must also use this skill if the user asks about any question regarding Chronicle or asks what you can see from the screen. Chronicle is passive observation only; for actively driving or automating a browser, use web:automating-browser instead.
development1
orchestrating-codex
Codex CLI統合スキル（基本操作・プランレビュー・Agentオーケストレーション）。 Use when using Codex for code consultation, plan review, or orchestrating Codex agents in Wave parallel execution. Triggers: "codex", "codexと相談", "codexでレビュー", "codexでオーケストレーション"、`.codex/agents/*.toml` や config.toml の [agents] セクションの検出。 tachikoma-product-manager agent に計画策定を委譲する2フェーズ方式で、Wave計画に基づき自然言語でagentを同時起動し、config.tomlのmax_threadsで並列度を宣言的に制御する。 カスタムagent定義はTOML形式（name/description/developer_instructions/sandbox_mode）。 For agent conversion to Codex format, use converting-agents-to-codex instead. For Claude Code teammate orchestration (parallel sub-agents via Agent + run_in_background), use orchestrating-teams instead.
tools1
developing-r
Comprehensive R development guide covering project setup, R scripts, packages, data structures, vectorization, tidyverse data wrangling, ggplot2 visualization, statistics, simulation, tidymodels machine learning, AI API workflows, Shiny dashboards, Quarto/R Markdown reporting, renv reproducibility, testthat testing, debugging, performance, parallel R, and C/C++/Python interop. MUST load when .R, .Rmd, .qmd, renv.lock, DESCRIPTION, NAMESPACE, .Rproj, app.R, RStudio, tidyverse, dplyr, ggplot2, Shiny, Quarto, R package development, or R data analysis is involved.
development1
practicing-product-management
プロダクトマネジメント総合ガイド（基礎・AIプロダクト・A/Bテスト・成長戦略・GPM・PLG・カスタマーサクセス・Claude Code PM活用）。 Use when practicing product management, managing AI products, designing experiments, growth product management, PLG strategy, customer success, writing PRDs/requirements docs, prioritizing roadmaps, or using Claude Code as PM tool. AARRR海賊指標、AIプロダクトライフサイクル、MLプロダクト化、AI統合戦略、オンライン実験設計、PM調査パターン、GPM実践、リテンション戦略、拡張収益、優先順位付け手法、ロードマップ（Now-Next-Later）、要件定義（PRD）、責任あるAIを含む。 For engineer-focused user story writing techniques (templates, common mistakes, splitting), use writing-user-stories instead.
tools1
managing-keycloak
Comprehensive Keycloak identity and access management guide covering OIDC/SAML protocols, SSO, Realms, Clients, Users, Roles, User Federation (LDAP/AD), Identity Brokering and social login, authentication flows, MFA, authorization policies (fine-grained permissions, UMA 2.0), JWT token management, application integration (Java/Node.js/Spring Boot), Docker/Kubernetes deployment, clustering, multi-tenant realm design (realm-per-tenant vs shared realm), large-scale user provisioning, observability and monitoring, migration/upgrade strategies, and SPI extensions. MUST load when keycloak.json, keycloak.conf, or Keycloak-related dependencies are detected. For general security practices, use devkit:securing-code instead. For Cedar/ABAC/ReBAC authorization models, use implementing-dynamic-authorization instead.
tools1
creating-flashcards
Creates Anki flashcards in bulk from EPUB/PDF/scanned-book files via Anki MCP Server or AnkiConnect API, covering MCP setup, OCR for image-based sources (Apple Vision first choice, local VLM fallback), deck/note-type management, and batch import with HTML formatting. Use when converting textbooks, question banks, or study materials into spaced repetition flashcards, or when managing Anki cards via MCP tools. Covers full workflow: MCP setup → file conversion (pandoc / OCR) → content analysis → batch card creation. For MCP server/client development, use lang:developing-mcp instead. For EPUB image compression/size reduction use compressing-epub-images; for standalone image-EPUB→text OCR conversion (no flashcard creation) use converting-content.
tools1
automating-browser
agent-browser CLI（Vercel Labs 製・Rust ネイティブ・CDP で Chrome を直接制御・デーモンに Node.js/Playwright 不要）によるブラウザ操作自動化。snapshot→ref ワークフロー、read（Chrome 起動なしで URL を markdown 取得）/chat（自然言語操作）/batch（連続実行）/mcp（MCP サーバー化）、セマンティックロケーター・状態永続化（storageState 互換 JSON）・認証 Vault・ネットワーク傍受に対応。 Use when アプリの web 操作・ブラウザ自動化（スクレイピング、UI 操作フロー、認証永続化、フォーム送信、データ抽出）を行うとき。これらは本スキル（agent-browser CLI）を第一選択にする。 住み分け: E2E テストスイートの設計・実装は testing-e2e-with-playwright、パフォーマンス計測/Lighthouse/詳細トレース等の診断は chrome-devtools MCP、ユーザーの既存 Chrome タブ/ログイン済みセッション操作は claude-in-chrome を使う。
tools1
creating-diagrams
ダイアグラム作成ガイド（Mermaid構文・draw.io MCP・draw.io XML/CSVフォーマット・22種類以上のダイアグラム対応）。 Use when creating diagrams, charts, or visual documentation with Mermaid or draw.io. C4モデル、ER図、シーケンス図、フローチャート、状態遷移図、ガントチャート、マインドマップ等を含む。精密なスタイリング・座標指定はdraw.io XML、組織図・階層データはdraw.io CSVで対応。 For data-visualization design theory (chart selection, color scales), use design:designing-data-visualizations. For LaTeX/TikZ figures inside .tex documents, use writing-latex.
tools1
writing-latex
LaTeX document creation and typesetting centered on Japanese academic reports. MUST load when .tex files are detected. Covers upLaTeX + dvipdfmx setup, minted code highlighting with Japanese font support, equations, figures, tables, cover pages, and thebibliography. References extend to advanced packages (tabularray, tcolorbox, TikZ, pgfplots, biblatex/natbib, fontspec), Beamer presentations, math symbol tables, large-document management, TeX engine selection (pdfTeX/XeTeX/LuaTeX/upTeX), special documents (CV, letters, posters), diagrams/charts, PDF optimization, package development, and troubleshooting. Use when creating or editing .tex documents, compiling Japanese LaTeX with upLaTeX + dvipdfmx, writing Beamer slides, or typesetting academic papers and reports. For HTML presentation decks, use creating-slides. For Mermaid/draw.io diagrams (non-LaTeX), use creating-diagrams. For prose quality and academic writing craft, use devkit:writing-effective-prose.
development1
securing-ai-development
Organizational security strategy for AI-powered software development covering trust frameworks (Early/Explainable/Experience), trust platform maturity model, adaptive governance with dynamic policies, AI-BOM, AI-SPM, cross-functional ownership, risk landscape (CWE vulnerability patterns in AI-generated code, hallucinated package references, OWASP Agentic AI threat categories), security KPIs/metrics, secure prompt templates, incident response updates, and a phased implementation roadmap. Use when establishing security controls, governance programs, or usage policies for AI coding assistants, agentic systems, or AI-accelerated SDLC workflows. For code-level security (OWASP, CodeGuard), use devkit:securing-code instead. For AI development methodology (prompts, context engineering), use developing-with-ai instead. For LLM-specific security (prompt injection, LLMSecOps), use designing-genai-patterns.
development1
implementing-observability
Unified observability guide covering monitoring system design (anti-patterns, 6-layer strategy, alerting, SLOs, telemetry pipelines, observability maturity model), OpenTelemetry implementation (tracing/metrics/logs API/SDK, Collector deployment, semantic conventions), logging design (structured logging, collection pipelines, analysis, anomaly detection, security compliance), and observability engineering practices (core analysis loop, debugging, ODD, build-vs-buy ROI, CI/CD observability, high-cardinality data). Use when designing monitoring strategy, implementing OpenTelemetry instrumentation, building log pipelines, setting up alerts, establishing SLO-based reliability, or adopting observability practices. Replaces: designing-monitoring, implementing-opentelemetry, implementing-logging.
development1
applying-semantic-versioning
Semantic Versioning 2.0.0仕様に基づくバージョン判断ガイド。MAJOR/MINOR/PATCH判定フロー、プレリリース・ビルドメタデータ、優先度比較ルール、npm/pipのバージョン範囲指定（^・~・==）、検証用正規表現を提供。 REQUIRED for all version-related decisions. Use when determining version bumps, creating releases, or managing dependencies. For commit message format (type/scope/BREAKING CHANGE), use writing-conventional-commits instead. For API versioning strategy trade-offs, use cloud:architecting-infrastructure instead.
development1
developing-firebase
Firebase platform development guide covering Authentication (email/social/session), Firestore & Realtime Database (modeling/queries/security rules), Cloud Storage, Cloud Functions (triggers/scheduling), Hosting, Emulator Suite (local dev/testing), Analytics (events/BigQuery), Crashlytics, FCM push notifications, Remote Config, Test Lab, Performance Monitoring, Dynamic Links, App Distribution, AdMob, and Extensions. MUST load when firebase, @firebase, or firebase-admin packages detected, or firebaseConfig/firebase.json/firestore.rules files present. For GCP infra→developing-google-cloud. For Next.js integration→web:developing-nextjs. For REST API design→web:developing-web-apis.
tools1
using-serena
Token-efficient structured development via the /serena command. Covers command syntax and option flags (-q quick, -c code-focus, -d detailed analysis, -r research, -s step-by-step, -t TODO list, --summary, --focus) and keyword-based auto-selection of thinking patterns (debugging, design, implementation, optimization). Use when implementing components, APIs, system designs, tests, bug fixes, or optimizations with a structured problem-solving approach. Available for Claude Code本体 and all Agents including Tachikoma. For parallel multi-file orchestration, use orchestrating-teams instead. For Tachikoma runtime operation, use implementing-as-tachikoma instead. For choosing between serena MCP symbol search and fff file search, use searching-files-with-fff instead.
tools1
testing-e2e-with-playwright
Playwright E2Eテストの設計・実装・運用ガイド。セマンティックロケーター優先順位、Page Object Model、fixtures、Web-First Assertionsとフレークテスト対策、テストデータ分離、APIモッキング/ネットワークエミュレーション、認証セットアップ（storageState）、CI/CD・Docker統合と並列実行、デバッグ（trace/UI Mode）、ビジュアルリグレッション、アクセシビリティテストをカバー。 Use when writing, reviewing, or maintaining E2E tests with @playwright/test. playwright.config.* 検出時に自動ロード。 テスト全般の方法論（TDD/AAA/テストピラミッド）は devkit:testing-code、Vitestランナー固有（設定・移行・Browser Mode）は testing-with-vitest、テスト以外のブラウザ操作自動化（スクレイピング/UI操作/フォーム送信）は automating-browser を使う。
development1
operating-herdr
herdr operations via the herdr CLI — a terminal-native agent multiplexer controlled over a local unix socket. Manage workspaces (project contexts), tabs (subcontexts), and panes (terminal splits); split, move, resize, and navigate panes and run commands; read another pane's output (visible / recent / recent-unwrapped / detection); wait for output text (`pane wait-output` with literal `--match` or `--regex`) or an agent status (`agent wait --until` idle / working / blocked / done / unknown); spawn agents with `herdr pane split` + `herdr agent start --kind <kind> --pane <id>` and coordinate them (read / prompt / send-keys / wait / attach); install lifecycle integration for authoritative status where supported (Claude Code/Codex remain screen-manifest-based). Use when running inside herdr (HERDR_ENV=1) to orchestrate agents, dev servers, tests, or log streams across panes from the terminal. Guarded: if HERDR_ENV is not 1, do not control herdr panes — stop. For parallel Tachikoma team orchestration inside Claude Code, use orchestrating-teams instead. For generic tmux multiplexing outside herdr this skill does not apply.
tools1
managing-claude-md
Manages CLAUDE.md creation, improvement, and maintenance following 8 core principles (300-line limit, avoiding /init auto-generated boilerplate, delegating style rules to linters/formatters, 3 essential elements — one-line project summary, common commands, If-X-then-Y trap rules — progressive disclosure into rules/ and docs/, priority-first placement, long-term memory operation, living documentation). Covers an interactive improvement workflow (AskUserQuestion), scope design (project CLAUDE.md, claude.local.md, global ~/.claude/CLAUDE.md, monorepo per-package files), daily/weekly/monthly maintenance cycles, plus templates and validation checklists. Use when starting new projects, writing or reviewing a CLAUDE.md, splitting an oversized CLAUDE.md, adding If-X-then-Y trap rules, or when Claude repeatedly makes the same mistakes. For skill file (SKILL.md) authoring, use authoring-plugins instead. For capturing session learnings and errors into .learnings/, use capturing-learnings instead.
tools1
solving-algorithms
Comprehensive algorithm and data structure reference for competitive programming covering sorting, searching, trees, graphs, dynamic programming, computational geometry, and number theory with complexity analysis and language-agnostic implementations. Use when solving algorithmic problems, optimizing code for time/space complexity, or implementing classic data structures (stack, queue, heap, BST, union-find). For database-specific data structures (B-tree, LSM), use developing-databases instead.
development1
gws-slides
Read and write Google Slides presentations via the gws CLI (gws slides presentations create / get / batchUpdate, with gws schema for inspecting request parameters). Use when reading or programmatically editing Google Slides documents (batchUpdate requests, presentation retrieval) from the command line. For creating self-authored HTML presentation decks (themes, storytelling), use creating-slides instead. For generating PowerPoint .pptx files, use creating-pptx instead.
tools1
designing-training
Training program design and facilitation methodology covering needs analysis (participant analysis, stakeholder mapping), KSA framework, instructional design theory (ADDIE, TOTE, Gagné, mastery learning), objective setting, activity catalog, training operations (instructor, space, logistics), Off-JT training system design, brain science principles (7±2 rule, long-term memory, habit formation), learner-centered facilitation (90/20/8 rule, EAT), online/hybrid/blended delivery, skill map creation, training material development, innovation/project-based training, and Kirkpatrick 4-level evaluation. Use when designing training programs, facilitating workshops, creating training materials, building skill maps, measuring training effectiveness, or managing training operations. For behavior design→design:applying-behavior-design. For presentation content→creating-slides. For design thinking process (empathize/define/ideate/prototype/test)→design:practicing-design-thinking.
development1
testing-with-vitest
Vitest 4.x specialized testing guide covering the test runner core: v3 to v4 migration and breaking changes (maxWorkers, test.projects, module runner, coverage overhaul), configuration (environments, coverage v8/istanbul, reporters), CLI and test filtering/tags, parallelism and performance (pools, sharding), Browser Mode (stable in v4, visual regression), fixtures and test context (test.extend), lifecycle hooks (aroundEach/aroundAll, globalSetup), mocking (vi API, modules, timers, MSW), matchers, type testing, and in-source testing. Use when package.json contains vitest or vitest.config.* is present, or when configuring, migrating, or optimizing Vitest. For framework-agnostic test methodology (TDD, AAA, test pyramid, four pillars, anti-patterns), use devkit:testing-code. For React Testing Library and React component testing, use developing-react. For Playwright E2E, use testing-e2e-with-playwright.
tools1
styling-with-tailwind
Tailwind CSS styling methodology covering utility-first philosophy, v4 CSS-first config (@theme, directives), utility/modifier reference, dark mode implementation, component design patterns (className props, headless UI and animation library selection), customization (plugins, presets, JS API), migration strategies, and design system construction with design tokens. Use when styling web applications with Tailwind CSS or making CSS architecture decisions. For frontend code generation with shadcn/ui and Storybook, use designing-frontend instead. For general UI/UX design principles, use design:designing-ux instead. For design system strategy beyond CSS (pattern language, organizational adoption, UI pattern catalog, measurement), use design:building-design-systems instead.
tools1
developing-go
Comprehensive Go development guide covering clean code practices, design patterns (GoF/concurrency/DDD), and internals (type system/memory/reflection). MUST load when go.mod is detected or Go code is being written. Covers naming, error handling, concurrency, testing, project structure, function design, data structures, refactoring strategies, GoF patterns, architectural patterns, type system internals, and performance optimization. For application logging design and structured logging patterns, use implementing-observability.
development1
creating-countdown-icons
カウントダウンアプリ用アプリアイコン（512×512 PNG）を絵文字・背景パレット選択の対話フローで生成するスキル。テキスト・絵文字・斜めストライプ背景を組み合わせたデザインアイコンを出力し、clean版とプレビュー版（白数字重ね）の2枚を提供する。 Use when creating app icons for countdown apps, generating text-based app icons with emoji, selecting icon designs interactively, or producing 512x512 PNG icons with diagonal striped backgrounds. 絵文字候補4択 → 背景パレット4択の対話フローで、ユーザーの意図に合ったアイコンを段階的に確定する。詳細な手順は INSTRUCTIONS.md を参照。
development1
orchestrating-teams
Agent Teamオーケストレーション（planner-first 2フェーズ方式: planner タチコマによる要件分析・docs/plan 作成 → ドメイン別専門タチコマの並列実装）。非herdr環境の Agent（run_in_background）/ SendMessage / TaskCreate・TaskList と、HERDR_ENV=1 環境の `herdr pane split` + `agent start --kind <kind> --pane <id>` / read / prompt / wait --until によるペイン起動・進捗管理、ファイル所有権パターンによる競合防止をカバー。 Use when multiple files need parallel changes with independent concerns (2+ files, frontend+backend, UI+API+test). Triggers: 複数ファイル並列変更、マルチ関心事開発、フロントエンド+バックエンド同時変更。 HERDR_ENV=1 では operating-herdr を必ず併用し、Claude Code の split-pane を使わず herdr CLI でエージェントを起動する。 For Codex CLI orchestration (config.toml max_threads, agents/*.toml), use orchestrating-codex instead. For operating as a single Tachikoma implementation worker, use implementing-as-tachikoma instead.
tools1
collecting-whizlabs-exams
Whizlabs のコース practice test 一覧URLから、配下の全クイズ（Free Test・Practice Test 1〜N 等）を practice mode で巡回し、各問題（問題文・選択肢・正解・解説・参考資料）を取得して 1 クイズ 1 JSON ファイルに 保存する。出力は creating-flashcards スキルへ渡してクイズごとに Anki フラッシュカード化できる。 Use when Whizlabs のコースURL（/learn/course/<slug>/<course-id>/pt 形式）を渡され 「問題を全部保存したい」「Anki カードにしたい」等と言われたとき。 補足トリガー: whizlabs, ホイズラボ, 資格試験, 問題集, practice test, quiz 収集, JSON 保存, Anki 連携。 ブラウザ操作自体の汎用ガイドは web:automating-browser、E2E テストは web:testing-e2e-with-playwright を使う。 本スキルは Whizlabs 専用の収集ワークフロー + bundled script（scripts/collect-whizlabs.sh）＋ ログイン認証（agent-browser Auth Vault）を提供する。
development1
capturing-learnings
作業中の学び・エラー・ユーザー訂正・機能要望を `.learnings/` に構造化記録し継続的改善につなげるスキル。反復パターンを検出しプロジェクトメモリ（CLAUDE.md / Claude Code memory / AGENTS.md）や新スキルへ昇格する。 Use when: ユーザーが訂正した時 / 存在しない機能を求められた時 / 知識が古い・誤りと判明した時 / 反復タスクでより良い方法を発見した時 / 大きな作業前に過去の学びを振り返る時。devkit の hook（UserPromptSubmit・PostToolUse）が学び記録を自動リマインドする。 For improving sumik-claude-plugin's own skills, use authoring-plugins instead. For curating durable cross-project facts, use the Claude Code memory system / managing-claude-md.
tools1
architecting-infrastructure
Vendor-neutral infrastructure and system architecture patterns. Infrastructure: 127 patterns for availability (HA, DR, backup), security, performance/scalability, operations, network/storage configuration, and cloud. Modernization: socio-technical strategy, domain redesign, trade-off analysis (code/API/system/meta levels). Microservices: CQRS, Event Sourcing, Saga, distributed transactions, service granularity, data ownership, resilience, messaging. Use when designing infrastructure, evaluating non-functional requirements, modernizing legacy systems, making architectural trade-offs, or designing microservices. For security-architecture design methodology (threat modeling, zero trust) use architecting-security instead.
development1
searching-files-with-fff
High-performance file search via the fff MCP server (fff-mcp, frecency-ranked results with a persistent in-memory index). Covers the three fff tools — grep (file CONTENTS, the default), find_files (fuzzy file NAME search), multi_grep (OR across multiple literal patterns) — plus inline constraint syntax, core search rules (search bare identifiers, avoid regex, stop after 2 greps and read), DB persistence, and when to use fff vs serena / Glob / ripgrep. Use when searching code or files in a repository and the fff MCP server is available, or when deciding which file-search tool fits. For semantic symbol-level search/edit (definitions, references, rename) use serena; for plain path-pattern listing use Glob; for Claude Code plugin MCP configuration use authoring-plugins.
tools1
automating-browser
Browser Agent CLIによるブラウザ操作自動化（セマンティックロケーター、状態永続化、ネットワーク傍受）。 Use when automating browser interactions via agent-browser CLI (NOT for E2E testing). E2Eテストは testing-e2e-with-playwright スキルを参照。
tools1
developing-bash
Comprehensive Bash shell scripting and automation guide covering fundamentals, control flow, I/O pipelines, process control, system administration automation, testing/debugging, security, design patterns, and penetration testing automation (Nmap, web scanning, exploitation, Wi-Fi assessment, reporting). MUST load when .sh files are detected or shell scripts are being written. For Docker-specific patterns, use practicing-devops instead. For broader DevOps methodology, use practicing-devops instead.
tools1
developing-fullstack-javascript
Full-stack JavaScript development covering backend (NestJS/Express), frontend (React), deployment (CI/CD), and quality; also covers JavaScript language fundamentals (types, closures, prototypes, async/await, modules, and metaprogramming). MUST load when package.json contains Express, NestJS, or similar backend frameworks. Covers API design, state management, caching, and testing. Also use when working with JavaScript language-level concerns — type coercion, scoping, this binding, Promise patterns, Proxy/Reflect, or iterator protocols. Also covers V8 engine internals (hidden classes, inline caches, string/number repr), event loop model, JS/Node error model, and Express 5 + Drizzle ORM CRUD APIs.
development1
developing-go
Comprehensive Go development guide covering clean code practices, design patterns (GoF/concurrency/DDD/CQRS), production patterns (net/http server & client with chi, database/sql with sqlc/GORM, JSON/CSV/Excel formats, html/text templates, slog/zap/zerolog logging, graceful shutdown, distroless containers), and internals (type system/memory layout/reflection/G-M-P scheduler). MUST load when go.mod is detected or Go code is being written. Covers naming, error handling, goroutine/channel concurrency, table-driven testing, nil handling, project structure, function design, data structures, Functional Options, refactoring strategies, and performance optimization. For application logging design and structured logging patterns, use cloud:implementing-observability. For language-agnostic clean code/SOLID and refactoring, use devkit:writing-clean-code. For Clean Architecture/DDD strategic design, use devkit:applying-clean-architecture. For algorithm/data-structure complexity analysis, use solving-algorithms.
tools1
creating-countdown-icons
カウントダウンアプリ用アプリアイコン（512×512 PNG）を絵文字・背景パレット選択の対話フローで生成するスキル。テキスト・絵文字・斜めストライプ背景を組み合わせたデザインアイコンを出力し、clean版とプレビュー版（白数字重ね）の2枚を提供する。 Use when creating app icons for countdown apps, generating text-based app icons with emoji, selecting icon designs interactively, or producing 512x512 PNG icons with diagonal striped backgrounds. 絵文字候補4択 → 背景パレット4択の対話フローで、ユーザーの意図に合ったアイコンを段階的に確定する。詳細な手順は INSTRUCTIONS.md を参照。For AIツールによるバナー・SNS画像・ポスター等の広告ビジュアル制作, use creating-content instead.
development1