
Interactive requirements discovery through Socratic dialogue and systematic exploration
Provide clear explanations of code, concepts, and system behavior with educational clarity
소프트웨어 아키텍처 패턴 및 설계 가이드를 실행합니다.
Review a feature and enhance it with purposeful animations, micro-interactions, and motion effects that improve usability and delight. Use when the user mentions adding animation, transitions, micro-interactions, motion design, hover effects, or making the UI feel more alive.
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks
Adapt designs to work across different screen sizes, devices, contexts, or platforms. Implements breakpoints, fluid layouts, and touch targets. Use when the user mentions responsive design, mobile layouts, breakpoints, viewport adaptation, or cross-device compatibility.
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
# Algorithmic Art This skill enables creation of **generative art using p5.js** with seeded randomness and interactive parameter exploration. ## Trigger - When user requests generative or algorithmic art - Creating interactive visualizations with p5.js - Building parametric design systems - Developing art with mathematical foundations ## Three-Step Process 1. **Algorithmic Philosophy** - Develop computational aesthetic manifesto - 4-6 paragraphs emphasizing emergent behavior - Mathemat
Comprehensive code analysis across quality, security, performance, and architecture domains
Execute project-specific verification rules. Validates business logic, architecture patterns, and naming conventions that linters cannot catch. Auto-suggests bootstrap if no rules exist. Triggers: audit, check rules, run audit, audit manage Do NOT use for: build/lint/test (/verify), design vs implementation (/gap-analysis)
인증/인가 설계를 위한 가이드를 실행합니다.
--- name: build-fix description: Expert skill for resolving build errors with minimal change principle. Use for build failures, type errors, compile errors. Keywords: build, fix, error, compile, typescript, type, resolve. --- ## Dynamic Context Last build output: !`cat .claude/state/last-build-error.log 2>/dev/null | tail -20 || echo "No cached build error"` # Build Fix Skill ## Purpose Resolve build/compile errors with **minimal changes**. Target only build passing - no architecture changes
Improve unclear UX copy, error messages, microcopy, labels, and instructions to make interfaces easier to understand. Use when the user mentions confusing text, unclear labels, bad error messages, hard-to-follow instructions, or wanting better UX writing.
캐싱 전략 설계를 위한 가이드를 실행합니다.
# Canvas Design Creates museum-quality visual art in PNG and PDF formats by establishing design philosophies that are then expressed visually. ## Trigger - When user needs professional visual design - Creating gallery-worthy artwork - Designing visual compositions - Building brand visual identity ## Core Process 1. **Design Philosophy Creation** (.md) - Develop aesthetic movement manifesto (4-6 paragraphs) - Emphasize visual expression over text - Conceptual depth and sophistication
--- name: checkpoint description: Save and restore work state with Git-based lightweight checkpoint system. Use before risky work, milestone completion, experimental changes. Keywords: checkpoint, save, restore, rollback, snapshot, backup, git, stash. --- ## Dynamic Context Current git state: !`git log --oneline -5 2>/dev/null` Existing stashes: !`git stash list 2>/dev/null || echo "No stashes"` # Checkpoint Skill ## Purpose Save, compare, and restore work state when necessary using Git sta
클린 코드 원칙 및 적용 가이드를 실행합니다.
Systematically clean up code, remove dead code, and optimize project structure
코드 품질과 PR 리뷰를 위한 체계적 체크리스트를 실행합니다.
Add strategic color to features that are too monochromatic or lack visual interest, making interfaces more engaging and expressive. Use when the user mentions the design looking gray, dull, lacking warmth, needing more color, or wanting a more vibrant or expressive palette.
일관된 커밋 메시지 작성을 위한 컨벤션 가이드를 실행합니다.
React composition patterns - Flexible and maintainable component structure. Prevent boolean prop abuse and build extensible architecture with Compound Components. Use proactively when: - Refactoring components with many boolean props - Building reusable component libraries - Designing flexible component APIs - Reviewing component architecture - Working with compound components or Context providers Triggers: composition, compound component, boolean props, component structure, architecture review, provider pattern, context, refactor component Do NOT use for: Performance optimization (→ react-best-practices), UI/UX inspection (→ web-design-guidelines)
Evaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing, automated anti-pattern detection, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design or component.
Domain-Driven Design 패턴 가이드를 실행합니다.
체계적 디버깅을 위한 구조화된 접근법을 실행합니다.
Run technical quality checks across accessibility, performance, theming, responsive design, and anti-patterns. Generates a scored report with P0-P3 severity ratings and actionable plan. Use when the user wants an accessibility check, performance audit, or technical quality review. (Impeccable design audit — distinct from /audit which validates project rules.)
GoF 디자인 패턴 및 활용 가이드를 실행합니다.
AI/사람의 결정, 계획, 코드, 설계를 구조화된 프레임워크로 도전하는 비판적 리뷰 레이어. Pre-mortem, Inversion, Socratic 질문을 활용하여 블라인드 스팟과 숨겨진 가정을 발견합니다.
환경 설정 관리를 위한 가이드를 실행합니다.
Provide development estimates for tasks, features, or projects with intelligent analysis
이벤트 기반 아키텍처 설계 가이드를 실행합니다.
--- name: feature-planner description: Creates phase-based feature plans with quality gates and incremental delivery structure. Use when planning features, organizing work, breaking down tasks, creating roadmaps, or structuring development strategy. Keywords: plan, planning, phases, breakdown, strategy, roadmap, organize, structure, outline. --- # Feature Planner ## Purpose Generate structured, phase-based plans where: - Each phase delivers complete, runnable functionality - Quality gates enfo
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
Git operations with intelligent commit messages and workflow optimization
Git 브랜치 전략 및 워크플로우 가이드를 실행합니다.
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas
Analyze discrepancies between design documents and actual implementation code. Core component of PDCA Check phase, calculating Match Rate and generating Gap list. Use proactively when: - Post-implementation design comparison needed - "Does it match design?", "Is it correct?", "Verify" requests - Pre-PR/code review verification - PDCA Check phase execution Triggers: gap analysis, design-implementation comparison, verify, validate, verify implementation, compare design, check implementation, design vs code Do NOT use for: Simple code review, design document creation, bug fixes
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
Docker 및 컨테이너 설정을 위한 가이드를 실행합니다.
Design system architecture, APIs, and component interfaces with comprehensive specifications
스키마 설계 및 쿼리 최적화를 위한 가이드를 실행합니다.
클린 아키텍처 설계 가이드를 실행합니다.
CQRS (Command Query Responsibility Segregation) 패턴 가이드를 실행합니다.
--- name: confidence-check description: Pre-implementation confidence assessment (≥90% required). Verifies duplicate check, architecture compliance, official docs, OSS references, root cause understanding. Keywords: confidence, check, verify, before, implement. --- ## Dynamic Context Project dependencies: !`cat package.json 2>/dev/null | head -20 || cat pyproject.toml 2>/dev/null | head -20 || echo "No package manifest found"` # Confidence Check Skill ## Purpose Assess confidence **before**
Multi-expert business analysis with adaptive interaction modes
# Artifacts Builder **Artifacts Builder** is a toolkit for creating sophisticated Claude.ai HTML artifacts using modern frontend technologies. ## Trigger - When user requests complex interactive HTML interfaces - Building React-based applications within Claude - Creating self-contained bundled artifacts - Developing UI with Tailwind CSS and shadcn/ui ## Capabilities The suite leverages "React 18 + TypeScript + Vite + Parcel (bundling) + Tailwind CSS + shadcn/ui" to build multi-component inte
Build, compile, and package projects with intelligent error handling and optimization
# Brand Guidelines (Anthropic) Applies Anthropic's official visual identity to artifacts needing corporate branding. ## Trigger - When artifact needs Anthropic branding - Corporate identity and styling required - Post-processing designs with brand colors - Applying consistent visual identity ## Brand Elements **Color Palette:** - Primary Dark: `#141413` - Primary Light: `#faf9f5` - Accent Orange: `#d97757` - Accent Blue: `#6a9bcc` - Accent Green: `#788c5d` **Typography:** - Headings: Poppin
백업 및 복구 전략 가이드를 실행합니다.
REST/GraphQL API 설계를 위한 체계적 가이드를 실행합니다.
웹 접근성 체크 및 개선 가이드를 실행합니다.
Generate focused documentation for components, functions, APIs, and features
--- name: eval-harness description: Eval-Driven Development (EDD) framework for AI development. Use when implementing AI features, prompt engineering, or LLM integration. Keywords: eval, evaluation, test, AI, LLM, prompt, benchmark, quality, EDD. --- # Eval Harness Skill (Eval-Driven Development) ## Purpose Apply EDD (Eval-Driven Development) methodology when developing AI features: "Define evaluation first, then implement to pass the eval." **Core Principle**: Eval is the unit test of AI dev
에러 핸들링 패턴 및 전략을 위한 가이드를 실행합니다.
파일 업로드 처리 가이드를 실행합니다.
Strip designs to their essence by removing unnecessary complexity. Great design is simple, powerful, and clean. Use when the user asks to simplify, declutter, reduce noise, remove elements, or make a UI cleaner and more focused.
FastAPI 백엔드 패턴 가이드를 실행합니다.
코드 스멜 감지 및 개선 가이드를 실행합니다.
CI/CD 파이프라인 설계 및 구성을 위한 가이드를 실행합니다.
SuperClaude++ 설정 유효성 검증. AGENT.md frontmatter, skill-rules.json, hook 스크립트 경로 등 전체 설정을 진단합니다.
PR 리뷰 코멘트를 자동 수집하고, 해당 코드를 수정하여 재커밋합니다. GitHub PR 피드백 루프를 자동화합니다.
Add moments of joy, personality, and unexpected touches that make interfaces memorable and enjoyable to use. Elevates functional to delightful. Use when the user asks to add polish, personality, animations, micro-interactions, delight, or make an interface feel fun or memorable.
Replace with description of the skill and when Claude should use it.
GraphQL 스키마 설계 가이드를 실행합니다.
--- name: harden description: Make interfaces production-ready: error handling, empty states, onboarding flows, i18n, text overflow, and edge case management. Use when the user asks to harden, make production-ready, handle edge cases, add error states, design empty states, improve onboarding, or fix overflow and i18n issues. version: 2.1.1 user-invocable: true argument-hint: "[target]" --- Strengthen interfaces against edge cases, errors, internationalization issues, and real-world usage scenar
Feature and code implementation with intelligent persona activation and MCP integration
Session lifecycle management with Serena MCP integration for project context loading
Improve layout, spacing, and visual rhythm. Fixes monotonous grids, inconsistent spacing, and weak visual hierarchy. Use when the user mentions layout feeling off, spacing issues, visual hierarchy, crowded UI, alignment problems, or wanting better composition.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
에이전트 체이닝 워크플로우를 실행합니다. 복잡한 작업을 여러 전문 에이전트가 순차적으로 처리합니다.
네이밍 컨벤션 가이드를 실행합니다.
--- name: note description: Persistent memo system surviving session compaction. Save critical context to .claude/notepad.md preventing information loss in long sessions. Keywords: note, memo, remember, context, save. --- # Note Skill ## Purpose Persistent memo system surviving session compaction. Prevents critical context loss through compression in long sessions. **Core Principle**: Critical info → Save memo → Persist after compaction → Available in next session ## Storage Location - **Pro
Diagnoses and fixes UI performance across loading speed, rendering, animations, images, and bundle size. Use when the user mentions slow, laggy, janky, performance, bundle size, load time, or wants a faster, smoother experience.
Performs a final quality pass fixing alignment, spacing, consistency, and micro-detail issues before shipping. Use when the user mentions polish, finishing touches, pre-launch review, something looks off, or wants to go from good to great.
레이트 리밋 설계 가이드를 실행합니다.
Tones down visually aggressive or overstimulating designs, reducing intensity while preserving quality. Use when the user mentions too bold, too loud, overwhelming, aggressive, garish, or wants a calmer, more refined aesthetic.
Intelligent MCP tool selection based on complexity scoring and operation analysis
Plan the UX and UI for a feature before writing code. Runs a structured discovery interview, then produces a design brief that guides implementation. Use during the planning phase to establish design direction, constraints, and strategy before any code is written.
SOLID 원칙 적용 가이드를 실행합니다.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
API 버저닝 전략 가이드를 실행합니다.
Improves typography by fixing font choices, hierarchy, sizing, weight, and readability so text feels intentional. Use when the user mentions fonts, type, readability, text hierarchy, sizing looks off, or wants more polished, intentional typography.
헥사고날 아키텍처 (Ports & Adapters) 설계 가이드를 실행합니다.
Create distinctive, production-grade frontend interfaces with high design quality. Generates creative, polished code that avoids generic AI aesthetics. Use when the user asks to build web components, pages, artifacts, posters, or applications, or when any design skill requires project context. Call with 'craft' for shape-then-build, 'teach' for design context setup, or 'extract' to pull reusable components and tokens into the design system.
국제화/다국어 지원을 위한 가이드를 실행합니다.
List all available /sc commands and their functionality
Apply systematic improvements to code quality, performance, and maintainability
--- name: learn description: Extract reusable patterns from sessions and save them as skills. Use after solving complex problems, discovering useful workarounds, or establishing project-specific conventions. Keywords: learn, pattern, extract, skill, knowledge, save, remember. --- # Learn Skill ## Purpose Analyze problem-solving patterns, debugging techniques, and workarounds from sessions to save them as reusable skills. **Core Principle**: Recurring problem-solving → Pattern extraction → Ski
Generate comprehensive project documentation and knowledge base with intelligent organization
Next.js 14+ App Router 패턴 가이드를 실행합니다.
마이크로서비스 아키텍처 설계 가이드를 실행합니다.
NestJS 백엔드 패턴 가이드를 실행합니다.
데이터베이스/스키마 마이그레이션을 위한 가이드를 실행합니다.
모니터링 및 알림 시스템 설계 가이드를 실행합니다.
모노레포 설정 가이드를 실행합니다.
성능 분석 및 최적화를 위한 체계적 가이드를 실행합니다.
Project Manager Agent - Default orchestration agent that coordinates all sub-agents and manages workflows seamlessly
# PowerPoint (PPTX) Presentation Skill Enable creation, editing, and analysis of PowerPoint presentations (.pptx files). ## Trigger - When user needs PowerPoint presentation creation or editing - Converting content to presentation format - Modifying existing presentations - Creating slide decks from templates - Designing visual presentations ## Core Capabilities **Reading & Analysis:** - Extract text content via markdown conversion - Access raw XML for comments, speaker notes, layouts, and a
페이지네이션 패턴 설계 가이드를 실행합니다.
# PDF Document Skill Comprehensive toolkit for PDF manipulation tasks including text/table extraction, document creation, merging, splitting, and form handling. ## Trigger - When user needs PDF creation or manipulation - Text or table extraction from PDF documents - Merging or splitting PDF files - PDF form filling or processing - OCR processing of scanned documents ## Core Capabilities **Text & Table Operations:** - Extract text with layout preservation using pdfplumber - Automated table de
로깅 및 모니터링 전략을 위한 가이드를 실행합니다.
Python code review and best practices validation. Comprehensive analysis including type hints, testing, linting, and package management.
메시지 큐 설계 가이드를 실행합니다.
Progressive Web App 구현 가이드를 실행합니다.
Execute and analyze pytest-based tests. Includes coverage reports, failure analysis, and fixture debugging.
Vercel Engineering's React & Next.js performance optimization guide. Use when writing React components, implementing data fetching, reviewing code for performance, refactoring, or optimizing bundle size. Contains 40+ rules across 8 priority categories.
Task reflection and validation using Serena MCP analysis capabilities
정규표현식 작성 및 테스트를 위한 가이드를 실행합니다.
Comprehensive security audit with OWASP Top 10, STRIDE threat model, and LLM/AI-specific security analysis. Covers traditional web security plus AI-era attack surfaces: prompt injection, tool call validation, skill supply chain, and cost amplification. Use proactively when: - Security review requested - Auth/authz implementation - API endpoint exposure - LLM/AI integration code - Dependency updates - Pre-deployment audit Triggers: security audit, security review, vulnerability check, pentest, threat model, OWASP, security scan Do NOT use for: performance optimization, code style review
Session lifecycle management with Serena MCP integration for session context persistence
리팩토링 패턴 및 기법 가이드를 실행합니다.
Remix 풀스택 웹 프레임워크 패턴 가이드를 실행합니다.
확장성 설계 가이드를 실행합니다.
Diagnose and resolve issues in code, builds, deployments, and system behavior
Meta-system task orchestration with intelligent breakdown and delegation
AI-powered UI/UX design intelligence with BM25 search engine. 67 styles, 96 color palettes, 57 font pairings, 100 reasoning rules, 13 tech stacks. Use proactively when: - Building landing pages, dashboards, or web apps - Choosing UI style, colors, or typography - Designing for specific industries (SaaS, fintech, healthcare, etc.) - Need design system recommendations Triggers: design system, UI style, color palette, font pairing, landing page design, glassmorphism, minimalism, brutalism, design intelligence, style recommendation Do NOT use for: backend code, API design, database, code review
상태 관리 패턴 가이드를 실행합니다.
--- name: spec-panel description: Multi-expert specification review and improvement using renowned specification and software engineering experts user-invocable: true argument-hint: "[specification_content|@file] [--mode discussion|critique|socratic] [--experts "name1,name2"] [--focus requirements|architecture|testing|compliance] [--iterations N] [--format standard|structured|detailed]" --- # Expert Specification Review Panel ## Triggers - Specification quality review and improvement requests
# Slack GIF Creator Toolkit for creating animated GIFs optimized for Slack, whether for messages or custom emojis, starting from creative descriptions. ## Trigger - When user needs animated GIFs for Slack - Creating custom Slack emojis - Designing animated messages - Converting creative ideas to optimized animations ## Key Capabilities **Three Tool Categories:** - Validators that check GIFs against Slack's strict requirements - Animation primitives (shake, bounce, spin, pulse, fade, zoom, et
반응형 디자인 가이드를 실행합니다.
SEO 최적화 가이드를 실행합니다.
Svelte 5 (Runes) 패턴 가이드를 실행합니다.
--- name: research description: Deep web research with adaptive planning and intelligent search user-invocable: true argument-hint: ""[query]" [--depth quick|standard|deep|exhaustive] [--strategy planning|intent|unified]" --- # Deep Research Command > **Context Framework Note**: This command activates comprehensive research capabilities with adaptive planning, multi-hop reasoning, and evidence-based synthesis. ## Triggers - Research questions beyond knowledge cutoff - Complex research questio
Execute tests with coverage analysis and automated quality reporting
테스트 전략 및 구현 가이드를 실행합니다.
Test-Driven Development workflow with RED-GREEN-REFACTOR cycle enforcement. Ensures tests are written before production code, with Git checkpoints at each phase. Use proactively when: - New feature implementation with testable behavior - Bug fix (write reproduction test first) - User explicitly requests TDD approach Triggers: TDD, test-driven, test first, red green refactor, write test first, failing test, reproduction test Do NOT use for: config changes, documentation, simple renames, UI-only changes
Execute complex tasks with intelligent workflow management and delegation
복잡한 문제를 단계별로 분석하는 구조화된 사고 프로세스를 실행합니다.
UI code review skill based on Vercel's Web Interface Guidelines. Inspects accessibility, performance, and UX with 100+ rules. Use proactively when: - UI code review requested - Accessibility (a11y) check requested - Design audit requested - UX review requested - Best practices check requested Triggers: review UI, check accessibility, audit design, review UX, check best practices, UI review, accessibility check, design review, UX review, web guidelines, a11y check Do NOT use for: backend code, API design, database
# Web Application Testing This toolkit enables testing of local web applications through native Python Playwright scripts, supporting frontend verification, UI debugging, screenshot capture, and browser log inspection. ## Trigger - When user requests testing of web applications - Frontend verification and UI debugging needed - Screenshot capture or visual validation required - Browser console log inspection needed ## Capabilities **Available Helper Scripts:** - `scripts/with_server.py` - Man
Vue 3 Composition API 패턴 가이드를 실행합니다.
Generate structured implementation workflows from PRDs and feature requirements
# Excel (XLSX) Spreadsheet Skill Claude Code supports comprehensive spreadsheet operations through the **xlsx** skill, enabling creation, editing, and analysis of Excel files (.xlsx, .xlsm, .csv, .tsv). ## Trigger - When user needs Excel spreadsheet creation or editing - Financial modeling or data analysis required - Spreadsheet formulas and calculations needed - Data import from CSV/TSV files ## Core Capabilities **Primary functions include:** - Creating new spreadsheets with formulas and f
Utilize uv package manager. Manage dependencies, virtual environments, project initialization, and lock files.
--- name: verify description: Ensure code quality with systematic 6-phase verification loop. Use after feature completion, before PR creation, after refactoring, or for periodic quality checks. Keywords: verify, verification, check, validate, quality, build, lint, test, security, pr-ready. --- ## Dynamic Context Current working state: !`git status --short 2>/dev/null` Recent changes: !`git diff --stat 2>/dev/null | tail -5` # Verification Loop Skill ## Purpose Ensure quality through systema
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
Pushes interfaces past conventional limits with technically ambitious implementations — shaders, spring physics, scroll-driven reveals, 60fps animations. Use when the user wants to wow, impress, go all-out, or make something that feels extraordinary.
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
Amplify safe or boring designs to make them more visually interesting and stimulating. Increases impact while maintaining usability. Use when the user says the design looks bland, generic, too safe, lacks personality, or wants more visual impact and character.
사용자 계획을 기존 도메인 모델에 대해 stress-test하는 인터뷰 세션. 용어를 날카롭게 다듬고, 결정이 굳어질 때마다 CONTEXT.md(도메인 어휘 사전)와 ADR을 인라인으로 갱신한다. 새 기능 요구사항 탐색은 `/brainstorm`을, 기존 도메인 모델·용어와의 정합성 점검은 이 스킬을 사용한다.
실시간 통신 설계 가이드를 실행합니다.