LUAgam
109 verified skills
verification-loop
A comprehensive verification system for Claude Code sessions.
development
python-patterns
Pythonic idioms, PEP 8 standards, type hints, and best practices for building robust, efficient, and maintainable Python applications.
development
perl-testing
Perl testing patterns using Test2::V0, Test::More, prove runner, mocking, coverage with Devel::Cover, and TDD methodology.
development
market-research
Conduct market research, competitive analysis, investor due diligence, and industry intelligence with source attribution and decision-oriented summaries. Use when the user wants market sizing, competitor comparisons, fund research, technology scans, or research that informs business decisions.
testing
kotlin-testing
Kotlin testing patterns with Kotest, MockK, coroutine testing, property-based testing, and Kover coverage. Follows TDD methodology with idiomatic Kotlin practices.
testing
eval-harness
Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles
development
cpp-testing
Use only when writing/updating/fixing C++ tests, configuring GoogleTest/CTest, diagnosing failing or flaky tests, or adding coverage/sanitizers.
development
video-editing
AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.
development
strategic-compact
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
tools
content-engine
Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.
testing
mcp-server-patterns
Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.
tools
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
testing
coding-standards
Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.
development
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
testing
investor-outreach
Draft cold emails, warm intro blurbs, follow-ups, update emails, and investor communications for fundraising. Use when the user wants outreach to angels, VCs, strategic investors, or accelerators and needs concise, personalized, investor-facing messaging.
testing
everything-claude-code-conventions
Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.
development
x-api
X/Twitter API integration for posting tweets, threads, reading timelines, search, and analytics. Covers OAuth auth patterns, rate limits, and platform-native content posting. Use when the user wants to interact with X programmatically.
development
tdd-workflow
Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
development
nextjs-turbopack
Next.js 16+ and Turbopack — incremental bundling, FS caching, dev speed, and when to use Turbopack vs webpack.
development
android-clean-architecture
Clean Architecture patterns for Android and Kotlin Multiplatform projects — module structure, dependency rules, UseCases, Repositories, and data layer patterns.
data-ai
ai-regression-testing
Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code.
development
frontend-patterns
Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.
development
django-verification
Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.
development
kotlin-exposed-patterns
JetBrains Exposed ORM patterns including DSL queries, DAO pattern, transactions, HikariCP connection pooling, Flyway migrations, and repository pattern.
data-ai
kotlin-coroutines-flows
Kotlin Coroutines and Flow patterns for Android and KMP — structured concurrency, Flow operators, StateFlow, error handling, and testing.
testing
java-coding-standards
Java coding standards for Spring Boot services: naming, immutability, Optional usage, streams, exceptions, generics, and project layout.
development
perl-patterns
Modern Perl 5.36+ idioms, best practices, and conventions for building robust, maintainable Perl applications.
development
kotlin-patterns
Idiomatic Kotlin patterns, best practices, and conventions for building robust, efficient, and maintainable Kotlin applications with coroutines, null safety, and DSL builders.
development
tdd-workflow
Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
development
strategic-compact
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
tools
project-guidelines-example
Example project-specific skill template based on a real production application.
testing
skills/project-surface
# Skill: project-surface 项目承载面缩圈 — 在产品/领域影响扫描之后，明确后续需要重点分析的具体落点。 ## 目的 "项目承载面"不等于"代码仓库"。本 skill 负责将影响扫描的宏观影响面，落实到当前项目的具体承载面列表，并设定深挖优先级。这一步骤在 CLARIFY 阶段固定位于： ``` 需求本体澄清 → 产品/领域影响扫描 → [项目承载面缩圈] → 定点深挖 ``` ## 承载面类型 | 类型 | 典型例子 | |------|---------| | `code_repository` | src/, lib/, app/ 等代码目录 | | `api_definition` | OpenAPI spec, proto 文件, GraphQL schema | | `configuration` | .env.example, config/, 部署 YAML | | `documentation` | docs/, README, ARCHITECTURE.md | | `design_artifacts` | 设计稿、交互流程、原型
development
api-design
REST API design patterns including resource naming, status codes, pagination, filtering, error responses, versioning, and rate limiting for production APIs.
development
api-design
REST API design patterns including resource naming, status codes, pagination, filtering, error responses, versioning, and rate limiting for production APIs.
development
bun-runtime
Bun as runtime, package manager, bundler, and test runner. When to choose Bun vs Node, migration notes, and Vercel support.
testing
mcp-server-patterns
Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.
tools
claude-api
Anthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended thinking, batches, prompt caching, and Claude Agent SDK. Use when building applications with the Claude API or Anthropic SDKs.
tools
coding-standards
Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.
development
compose-multiplatform-patterns
Compose Multiplatform and Jetpack Compose patterns for KMP projects — state management, navigation, theming, performance, and platform-specific UI.
testing
configure-ecc
Interactive installer for Everything Claude Code — guides users through selecting and installing skills and rules to user-level or project-level directories, verifies paths, and optionally optimizes installed files.
development
continuous-learning-v2
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination.
data-ai
cpp-coding-standards
C++ coding standards based on the C++ Core Guidelines (isocpp.github.io). Use when writing, reviewing, or refactoring C++ code to enforce modern, safe, and idiomatic practices.
development
crosspost
Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform using content-engine patterns. Never posts identical content cross-platform. Use when the user wants to distribute content across social platforms.
testing
deep-research
Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any topic with evidence and citations.
tools
django-patterns
Django architecture patterns, REST API design with DRF, ORM best practices, caching, signals, middleware, and production-grade Django apps.
development
django-tdd
Django testing strategies with pytest-django, TDD methodology, factory_boy, mocking, coverage, and testing Django REST Framework APIs.
development
dmux-workflows
Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.
development
springboot-tdd
Test-driven development for Spring Boot using JUnit 5, Mockito, MockMvc, Testcontainers, and JaCoCo. Use when adding features, fixing bugs, or refactoring.
development
documentation-lookup
Use up-to-date library and framework docs via Context7 MCP instead of training data. Activates for setup questions, API references, code examples, or when the user names a framework (e.g. React, Next.js, Prisma).
tools
documentation-lookup
Use up-to-date library and framework docs via Context7 MCP instead of training data. Activates for setup questions, API references, code examples, or when the user names a framework (e.g. React, Next.js, Prisma).
tools
e2e-testing
Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies.
testing
e2e-testing
Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies.
testing
eval-harness
Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles
development
exa-search
Neural search via Exa MCP for web, code, and company research. Use when the user needs web search, code examples, company intel, people lookup, or AI-powered deep research with Exa's neural search engine.
tools
fal-ai-media
Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.
tools
frontend-slides
Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.
development
frontend-slides
Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.
development
golang-patterns
Idiomatic Go patterns, best practices, and conventions for building robust, efficient, and maintainable Go applications.
development
investor-materials
Create and update pitch decks, one-pagers, investor memos, accelerator applications, financial models, and fundraising materials. Use when the user needs investor-facing documents, projections, use-of-funds tables, milestone plans, or materials that must stay internally consistent across multiple fundraising assets.
testing
investor-materials
Create and update pitch decks, one-pagers, investor memos, accelerator applications, financial models, and fundraising materials. Use when the user needs investor-facing documents, projections, use-of-funds tables, milestone plans, or materials that must stay internally consistent across multiple fundraising assets.
testing
investor-outreach
Draft cold emails, warm intro blurbs, follow-ups, update emails, and investor communications for fundraising. Use when the user wants outreach to angels, VCs, strategic investors, or accelerators and needs concise, personalized, investor-facing messaging.
testing
iterative-retrieval
Pattern for progressively refining context retrieval to solve the subagent context problem
data-ai
kotlin-ktor-patterns
Ktor server patterns including routing DSL, plugins, authentication, Koin DI, kotlinx.serialization, WebSockets, and testApplication testing.
tools
laravel-tdd
Test-driven development for Laravel with PHPUnit and Pest, factories, database testing, fakes, and coverage targets.
development
.cursor/skills/laravel-verification
--- name: laravel-verification description: Verification loop for Laravel projects: env checks, linting, static analysis, tests with coverage, security scans, and deployment readiness. origin: ECC --- # Laravel Verification Loop Run before PRs, after major changes, and pre-deploy. ## When to Use - Before opening a pull request for a Laravel project - After major refactors or dependency upgrades - Pre-deployment verification for staging or production - Running full lint -> test -> security ->
development
market-research
Conduct market research, competitive analysis, investor due diligence, and industry intelligence with source attribution and decision-oriented summaries. Use when the user wants market sizing, competitor comparisons, fund research, technology scans, or research that informs business decisions.
testing
springboot-patterns
Spring Boot architecture patterns, REST API design, layered services, data access, caching, async processing, and logging. Use for Java Spring Boot backend work.
development
python-testing
Python testing strategies using pytest, TDD methodology, fixtures, mocking, parametrization, and coverage requirements.
development
rust-patterns
Idiomatic Rust patterns, ownership, error handling, traits, concurrency, and best practices for building safe, performant applications.
development
rust-testing
Rust testing patterns including unit tests, integration tests, async testing, property-based testing, mocking, and coverage. Follows TDD methodology.
development
security-review
Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.
development
.cursor/skills/skill-stocktake
Use when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation.
testing
springboot-verification
Verification loop for Spring Boot projects: build, static analysis, tests with coverage, security scans, and diff review before release or PR.
development
verification-loop
A comprehensive verification system for Claude Code sessions.
development
skills/clarify
# Skill: clarify ## CLI Bootstrap 在执行任何 `harnessctl` 命令前，校验环境变量 `HARNESSCTL` 是否已配置： ```bash test -n "${HARNESSCTL:-}" && test -x "$HARNESSCTL" || { echo "ERROR: HARNESSCTL 环境变量未设置或不可执行。请先执行: export HARNESSCTL=/path/to/stage-harness/scripts/harnessctl" >&2 exit 1 } ``` Multi-role CLARIFY engine — converts a raw idea into a structured, validated problem statement. ## Purpose Before writing any spec, we must understand the problem deeply. The CLARIFY stage uses a Lead Orchestrator + **do
tools
skills/decision-bundle
# Skill: decision-bundle Compress all decisions from CLARIFY into a minimal user interrupt set. ## Purpose The most disruptive part of AI-driven development is constant interruptions. This skill implements the Decision Bundle pattern: collect ALL pending decisions, classify them, and condense `must_confirm` items into a single structured packet — maximizing autonomy while preserving control on what matters. ## Decision Categories ### must_confirm Decisions where: - Wrong assumption causes i
development
skills/re-spec
# Skill: re-spec ## CLI Bootstrap 在执行任何 `harnessctl` 命令前，校验环境变量 `HARNESSCTL` 是否已配置： ```bash test -n "${HARNESSCTL:-}" && test -x "$HARNESSCTL" || { echo "ERROR: HARNESSCTL 环境变量未设置或不可执行。请先执行: export HARNESSCTL=/path/to/stage-harness/scripts/harnessctl" >&2 exit 1 } ``` Incremental SPEC revision — amends epic specification based on upstream CLARIFY changes. ## Purpose When re-clarify produces new requirements or surfaces, the SPEC must be updated to include acceptance criteria, constrain
tools
skills/impact-scan
# Skill: impact-scan Identify all codebase surfaces affected by an incoming change request. ## Purpose Before writing a spec, we need to know: what already exists that this epic will touch, modify, or depend on? The impact scan produces a blast-radius map that prevents missing cross-cutting concerns. ## Scan Categories ### 1. High Impact Surfaces Files/modules the epic will definitely modify: - Identified by requirement routing - Existing code that will change behavior - Usually tagged `P0`
development
backend-patterns
Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.
development
frontend-patterns
Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.
development
backend-patterns
Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.
development
content-engine
Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.
testing
continuous-learning
Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.
development
golang-testing
Go testing patterns including table-driven tests, subtests, benchmarks, fuzzing, and test coverage. Follows TDD methodology with idiomatic Go practices.
development
laravel-patterns
Laravel architecture patterns, routing/controllers, Eloquent ORM, service layers, queues, events, caching, and API resources for production apps.
development
plankton-code-quality
Write-time code quality enforcement using Plankton — auto-formatting, linting, and Claude-powered fixes on every file edit via hooks.
development
bun-runtime
Bun as runtime, package manager, bundler, and test runner. When to choose Bun vs Node, migration notes, and Vercel support.
testing
nextjs-turbopack
Next.js 16+ and Turbopack — incremental bundling, FS caching, dev speed, and when to use Turbopack vs webpack.
development
skills/council
# SKILL: council ## CLI Bootstrap 在执行任何 `harnessctl` 命令前，校验环境变量 `HARNESSCTL` 是否已配置： ```bash test -n "${HARNESSCTL:-}" && test -x "$HARNESSCTL" || { echo "ERROR: HARNESSCTL 环境变量未设置或不可执行。请先执行: export HARNESSCTL=/path/to/stage-harness/scripts/harnessctl" >&2 exit 1 } ``` 分层议会调度技能。根据议会类型动态选择 reviewer 列表，并行执行所有审查，汇总 verdict，自动裁决放行或阻断。 --- ## 触发条件 由其他 SKILL 调用，传入 `council_type` 参数： - `light_council` — 由 `spec/SKILL.md` 调用（SPEC 阶段） - `plan_council` — 由 `plan/SKILL.md` 调用（PLAN 阶段） - `accepta
tools
skills/worktree
# Skill: worktree ## CLI Bootstrap 在执行任何 `harnessctl` 命令前，校验环境变量 `HARNESSCTL` 是否已配置： ```bash test -n "${HARNESSCTL:-}" && test -x "$HARNESSCTL" || { echo "ERROR: HARNESSCTL 环境变量未设置或不可执行。请先执行: export HARNESSCTL=/path/to/stage-harness/scripts/harnessctl" >&2 exit 1 } ``` Manage git worktrees for isolated epic execution. ## Purpose Each epic can optionally run in a dedicated git worktree, giving workers an isolated branch without affecting the main workspace. This prevents in-progress wo
tools
skills/runtime-harness
# SKILL: runtime-harness ## CLI Bootstrap 在执行任何 `harnessctl` 命令前，校验环境变量 `HARNESSCTL` 是否已配置： ```bash test -n "${HARNESSCTL:-}" && test -x "$HARNESSCTL" || { echo "ERROR: HARNESSCTL 环境变量未设置或不可执行。请先执行: export HARNESSCTL=/path/to/stage-harness/scripts/harnessctl" >&2 exit 1 } ``` 运行时 Harness 技能，定义持续控偏规则。在整个 EXECUTE 阶段持续运行，在 5 个检查点介入，确保实现不偏离 spec，证据完整，失败可追溯。 --- ## 概述 runtime-harness 不是一个单独运行的阶段，而是嵌入到 `work/SKILL.md` 内循环的控偏层。每个检查点在特定时机触发，发现问题时立即阻断。 --- ## 5 个检查点 --- ### Checkpoint 1 —
tools
skills/re-plan
# Skill: re-plan ## CLI Bootstrap 在执行任何 `harnessctl` 命令前，校验环境变量 `HARNESSCTL` 是否已配置： ```bash test -n "${HARNESSCTL:-}" && test -x "$HARNESSCTL" || { echo "ERROR: HARNESSCTL 环境变量未设置或不可执行。请先执行: export HARNESSCTL=/path/to/stage-harness/scripts/harnessctl" >&2 exit 1 } ``` Incremental PLAN revision — amends task graph based on upstream SPEC changes. ## Purpose When re-spec adds new acceptance criteria or changes scope, the task plan must be updated. This skill performs task graph merge: add
tools
skills/re-clarify
# Skill: re-clarify ## CLI Bootstrap 在执行任何 `harnessctl` 命令前，校验环境变量 `HARNESSCTL` 是否已配置： ```bash test -n "${HARNESSCTL:-}" && test -x "$HARNESSCTL" || { echo "ERROR: HARNESSCTL 环境变量未设置或不可执行。请先执行: export HARNESSCTL=/path/to/stage-harness/scripts/harnessctl" >&2 exit 1 } ``` Incremental CLARIFY re-run — amends existing CLARIFY artifacts based on feedback without full re-execution. ## Purpose When a feedback-driven reopen targets CLARIFY, this skill performs an incremental amendment rather
tools
skills/bridge-spec
# SKILL: bridge-spec ShipSpec → deep-plan 桥接技能。将 ShipSpec 产物（PRD、SDD、TASKS、unknowns-ledger）合并为 deep-plan 可接受的统一输入格式（bridge-spec.md）。 --- ## 触发条件 - 收到 `/stage-harness:bridge` 命令 - 在 PLAN 阶段开始前，需要将 ShipSpec 产出桥接到 stage-harness 体系时 --- ## 桥接步骤 运行 `scripts/bridge-shipspec-to-deepplan.sh <feature-name> <epic-id>`： ```bash ./scripts/bridge-shipspec-to-deepplan.sh <feature-name> <epic-id> ``` ### Step 1 — 从 PRD.md 提取需求摘要与优先级 读取 `.shipspec/planning/<feature>/PRD.md`，提取： - 核心需求（User Stories / A
tools
skills/plan
# SKILL: plan ## CLI Bootstrap 在执行任何 `harnessctl` 命令前，校验环境变量 `HARNESSCTL` 是否已配置： ```bash test -n "${HARNESSCTL:-}" && test -x "$HARNESSCTL" || { echo "ERROR: HARNESSCTL 环境变量未设置或不可执行。请先执行: export HARNESSCTL=/path/to/stage-harness/scripts/harnessctl" >&2 exit 1 } ``` PLAN 阶段计划生成技能。将 SPEC 产物转化为可执行的任务图谱，建立覆盖矩阵，确保每个已知风险都有对应的 task、验证手段和证据要求。 --- ## 触发条件 - 当前 epic state = `PLAN` - 收到 `/stage-harness:plan` 命令 - 从 EXECUTE 回流（`$HARNESSCTL state transition <epic-id> PLAN`） --- ## 核心流程 ### St
tools
skills/build
# SKILL: build ## CLI Bootstrap 在执行任何 `harnessctl` 命令前，先解析本地 CLI 路径： ```bash if [ -z "${HARNESSCTL:-}" ]; then candidates=( "./stage-harness/scripts/harnessctl" "../stage-harness/scripts/harnessctl" "$(git rev-parse --show-toplevel 2>/dev/null)/stage-harness/scripts/harnessctl" ) for candidate in "${candidates[@]}"; do if [ -n "$candidate" ] && [ -x "$candidate" ]; then HARNESSCTL="$candidate" break fi done fi test -n "${HARNESSCTL:-}" && test -x "$HA
tools
skills/review
# SKILL: review ## CLI Bootstrap 在执行任何 `harnessctl` 命令前，校验环境变量 `HARNESSCTL` 是否已配置： ```bash test -n "${HARNESSCTL:-}" && test -x "$HARNESSCTL" || { echo "ERROR: HARNESSCTL 环境变量未设置或不可执行。请先执行: export HARNESSCTL=/path/to/stage-harness/scripts/harnessctl" >&2 exit 1 } ``` VERIFY 阶段审查引擎技能。通过跨模型多维审查、spec compliance 核查、安全审查、对抗补盲和验收议会，确保交付物满足规格要求，无遗漏风险。 --- ## 触发条件 - 当前 epic state = `VERIFY` - 收到 `/stage-harness:review` 命令 - 从 FIX 阶段完成后重新进入 VERIFY --- ## 核心流程 ### Step 1 — 汇总 runtime receip
tools
skills/auto
# Skill: auto Autonomous execution mode — runs CLARIFY → SPEC → PLAN → EXECUTE → VERIFY → BUILD → DEPLOY → E2E → DONE without user interrupts (low/medium risk only). ## Purpose For epics where risk is `low` or `medium` and requirements are clear, `/stage-harness:auto` allows the pipeline to run end-to-end with minimal user involvement. The Interrupt Budget still enforces hard limits, but stage gates are auto-approved. ## Eligibility Check Before entering auto mode: ``` 1. Read .harness/proj
development
skills/deploy
# SKILL: deploy ## CLI Bootstrap 在执行任何 `harnessctl` 命令前，先解析本地 CLI 路径： ```bash if [ -z "${HARNESSCTL:-}" ]; then candidates=( "./stage-harness/scripts/harnessctl" "../stage-harness/scripts/harnessctl" "$(git rev-parse --show-toplevel 2>/dev/null)/stage-harness/scripts/harnessctl" ) for candidate in "${candidates[@]}"; do if [ -n "$candidate" ] && [ -x "$candidate" ]; then HARNESSCTL="$candidate" break fi done fi test -n "${HARNESSCTL:-}" && test -x "$H
tools
skills/feedback-triage
# SKILL: feedback-triage ## CLI Bootstrap ```bash test -n "${HARNESSCTL:-}" && test -x "$HARNESSCTL" || { echo "ERROR: HARNESSCTL 环境变量未设置或不可执行。请先执行: export HARNESSCTL=/path/to/stage-harness/scripts/harnessctl" >&2 exit 1 } ``` --- ## 概述 Feedback Triage Council 调度技能。当 stage-reminder hook 自动提交 feedback 后， 本 skill 负责完整执行多 agent 评审流程，决定是否 reopen 及返回哪个阶段。 --- ## 触发条件 - stage-reminder.sh 检测到 feedback_candidate 并自动提交 HFB-xxx - additionalContext 注入 `[Feedback - AUTO SUBMITTED]` 指令 - 也可手动触发
tools
skills/memory
# Skill: memory Persist, retrieve, and evolve harness knowledge across sessions and epics. ## Purpose The memory system enables stage-harness to improve over time: patterns from completed epics are preserved, common mistakes are avoided, and successful approaches are promoted to reusable skills. ## Memory Storage Layout ``` .harness/memory/ ├── project-patterns.json # Patterns learned from this project ├── codemaps/ # Hotspot module notes (reuse across epics); templates/co
development
skills/skill-evolution
# Skill: skill-evolution ## CLI Bootstrap 在执行任何 `harnessctl` 命令前，校验环境变量 `HARNESSCTL` 是否已配置： ```bash test -n "${HARNESSCTL:-}" && test -x "$HARNESSCTL" || { echo "ERROR: HARNESSCTL 环境变量未设置或不可执行。请先执行: export HARNESSCTL=/path/to/stage-harness/scripts/harnessctl" >&2 exit 1 } ``` Candidate skill lifecycle: mine → shadow validate → auto-refine → human promotion. ## Purpose Skills improve over time through evidence from real epics. Rather than writing skills manually, stage-harness mines pa
tools
skills/stage-gate
# SKILL: stage-gate ## CLI Bootstrap 在执行任何 `harnessctl` 命令前，校验环境变量 `HARNESSCTL` 是否已配置： ```bash test -n "${HARNESSCTL:-}" && test -x "$HARNESSCTL" || { echo "ERROR: HARNESSCTL 环境变量未设置或不可执行。请先执行: export HARNESSCTL=/path/to/stage-harness/scripts/harnessctl" >&2 exit 1 } ``` 阶段门禁技能。在每个阶段出口执行产物完整性检查，确保进入下一阶段所需的所有产物齐备、决策已处理、议会已通过。 --- ## 触发条件 - 每次调用 `$HARNESSCTL state transition` 前自动检查 - 收到 `/stage-harness:gate` 命令时手动触发 - 由各阶段 SKILL 的出口条件检查调用 --- ## 阶段产物清单 ### CLARIFY 出口 | 产物 | 路径 | 说明
tools
skills/project-profile
# Skill: project-profile Detect and describe the project's profile from codebase signals. ## Purpose Classify the project into one of 8 profile types and extract key tech-stack facts that all downstream stages (CLARIFY → SPEC → PLAN) rely on. ## Profile Types | Type | Signals | |------|---------| | `application` | main entry point, GUI, user-facing pages | | `backend-service` | HTTP server, REST/gRPC endpoints, Dockerfile | | `frontend` | framework components (React/Vue/Svelte), build pipel
development
skills/spec
# Skill: spec ## CLI Bootstrap 在执行任何 `harnessctl` 命令前，校验环境变量 `HARNESSCTL` 是否已配置： ```bash test -n "${HARNESSCTL:-}" && test -x "$HARNESSCTL" || { echo "ERROR: HARNESSCTL 环境变量未设置或不可执行。请先执行: export HARNESSCTL=/path/to/stage-harness/scripts/harnessctl" >&2 exit 1 } ``` Generate structured PRD + SDD + TASKS via ShipSpec, with Stop hooks disabled. ## Purpose The SPEC stage converts CLARIFY's problem statement into machine-parseable task artifacts using ShipSpec's proven 7-phase workflow. st
tools
verify-and-fix-cases
在 generate-test-cases 阶段之后执行，逐个验证测试用例并在失败时修复项目代码、重新编译部署、再次验证， 直到通过或达到最大修复次数。覆盖 UI / API / API+UI / 性能测试四个维度，UI 测试通过浏览器真实模拟用户操作并截图， API 测试根据项目代码生成可执行的接口脚本，性能测试调用现有性能/质量技能全量执行。 涉及真实用户登录信息（如手机号+验证码、账号密码、JWT）时必须中断要求用户提供，禁止编造无效凭证。 所有 case 状态变更必须通过 e2e-case-tracker.sh 脚本持久化，确保中途崩溃可恢复、无 case 遗漏。
development
skills/e2e
# SKILL: e2e > **核心原则**： > 1. 测试范围跟着本次变动走。后端接口改了，对应的前端流程必须做联调验证；与本次需求无关的功能不测。对于涉及算法、转换准确率等质量敏感型需求，需额外生成专项质量测试。 > 2. **覆盖完整性优先于执行便利性**。不得以"链路复杂"、"需要外部依赖"为由跳过本次变动相关的用例；凡是受变动影响的接口和 UI 流程，都必须生成真实调用/操作用例。 > 3. **UI 测试必须模拟真实用户操作**（定位元素、点击、键入、等待渲染、断言可见文本/状态）。**禁止**将 UI 套件退化为浏览器上下文里的 `page.evaluate(fetch(...))` API 验证——那只是把 API 测试换了执行环境，没有额外价值，不算 UI 测试。 > 4. **通用性**：本 skill 不假设具体业务域，所有规则均以抽象变动面（文件、接口、页面、用户动作）为单位组织，不针对任何特定项目的数据库/领域词汇。 > 5. **E2E 套件必须验证运行时行为**。严禁把"读取源码/配置文件并做字符串/结构匹配"的检查封装成独立 E2E 套件——这类检
development
skills/interrupt-budget
# Skill: interrupt-budget ## CLI Bootstrap 在执行任何 `harnessctl` 命令前，校验环境变量 `HARNESSCTL` 是否已配置： ```bash test -n "${HARNESSCTL:-}" && test -x "$HARNESSCTL" || { echo "ERROR: HARNESSCTL 环境变量未设置或不可执行。请先执行: export HARNESSCTL=/path/to/stage-harness/scripts/harnessctl" >&2 exit 1 } ``` Track and enforce the hard limit on user interrupts per epic. ## Purpose Autonomy is valuable only if it doesn't create more work. The Interrupt Budget is a hard constraint that forces the AI pipeline to batch q
tools
skills/work
# SKILL: work ## CLI Bootstrap 在执行任何 `harnessctl` 命令前，校验环境变量 `HARNESSCTL` 是否已配置： ```bash test -n "${HARNESSCTL:-}" && test -x "$HARNESSCTL" || { echo "ERROR: HARNESSCTL 环境变量未设置或不可执行。请先执行: export HARNESSCTL=/path/to/stage-harness/scripts/harnessctl" >&2 exit 1 } ``` EXECUTE 阶段开发执行技能（Worker 循环）。严格按序完成每个 task 的 5-Phase 内循环，确保实现与 spec 对齐，每个 task 有可验证的证据，新发现问题按规则分类处理。 > **受控产物写入协议**：`.harness/tasks/*.json`、`.harness/features/*/state.json`、`.harness/epics/*.json` 等受 write-guard hook 保护，禁止直接
tools