Normalize legacy repositories by moving scattered documentation into docs-legacy/ (git-aware) and generating a docs-legacy/summary.md before generating new docs/plans.
cmux ターミナル内での操作スキル。ペイン分割、サブエージェント起動・監視・結果回収、コマンド送信、画面読み取り、通知に使用。CMUX_* 環境変数が存在する場合にトリガーされる。
백엔드 도메인 knowledge. Node.js/TypeScript API 설계, PostgreSQL/Drizzle ORM, 인증/보안, 캐싱(Redis), 메시지 큐(BullMQ), 동시성, 분산 시스템, 마이크로서비스, 성능 최적화, 장애 대응, 배포, 모니터링 시 활성화. 서버 로직, DB 쿼리, API endpoint 작성/수정/리뷰 시, 백엔드 설계 판단이 필요할 때 사용한다. 사용자가 API endpoint, DB 스키마, 쿼리 최적화, 인증 플로우, 캐시 전략, 큐 처리, 배포 파이프라인, 서버 에러를 언급하면 반드시 이 스킬을 활성화하라. 명시적으로 '백엔드'라고 말하지 않더라도 서버 사이드 로직, 인프라, .controller.ts/.service.ts/.module.ts/.entity.ts 파일을 다루는 작업이면 활성화한다. --- # BE Domain Knowledge 매핑 테이블의 참조 파일에는 프로젝트 고유의 아키텍처 결정, 검증된 패턴, 안티패턴이 담겨 있다. 이를 읽지 않으면 기존 시스템 설계와 충돌하는 코드를 작성하게 되고, 리뷰에서 반려된다. 코드를 작성하거나 리뷰하기 전에 아래 매핑 테이블에서 태스크에 해당하는 파일을 반드시 Read하라. **기본 경로**: `~/.claude/skills/be/` — 아래 테이블의 파일명 앞에 이 경로를 붙여서 Read한다. ## 핵심 원칙 - 시스템 철학: "견고하고 확장 가능한 시스템" - 4대 원칙: 안정성(Reliability), 확장성(Scalability), 관찰 가능성(Observability), 보안(Security) - 기술 스택: TypeScript strict, Node.js, Fastify 5, PostgreSQL 16+, Drizzle ORM, Redis, BullMQ, Pino, Vitest - API 계약: RFC 9457 Problem Details 표준, Breaking change는 versioning - 안티패턴: Happy path만 구현, 추측 기반 최적화, "나중에 보안 처리", 로그 없는 시스템 ## 태스크-지식 매핑 | 태스크 유형 | 판단 기준 | Read할 파일 | |---|---|---| | API 설계/구현 | endpoint 정의·요청/응답 스키마·라우팅 | `api-design.md` + `error-handling.md` | | DB 스키마/쿼리 | 테이블 설계·마이그레이션·raw 쿼리 | `database.md` + `postgresql.md` | | Drizzle ORM 작업 | ORM 스키마·쿼리 빌더·관계 정의 | `drizzle-orm.md` + `database.md` | | 프로젝트 구조/설계 | 디렉토리·모듈·레이어 구조 결정 | `architecture.md` | | 인증/인가/보안 | 로그인·토큰·권한·암호화 | `security.md` + `api-design.md` | | 테스트 작성 | 단위·통합·E2E 서버 테스트 | `testing.md` | | 로깅/모니터링 | 로그 수집·메트릭·알럿·트레이싱 | `observability.md` | | 에러 처리 | 예외 설계·에러 응답·복구 전략 | `error-handling.md` + `observability.md` | | 성능 최적화 | 응답 시간·쓰루풋·병목 해결 | `performance.md` + `nodejs-internals.md` + `postgresql.md` | | 배포/인프라 | CI/CD·컨테이너·환경 설정 | `deployment.md` + `architecture.md` + `observability.md` | | 시스템 설계 | 대규모 아키텍처·서비스 간 통신 | `system-design.md` + `distributed-systems.md` + `microservices.md` | | 캐싱 | Redis·캐시 전략·무효화 정책 | `caching.md` + `performance.md` | | 메시지 큐 | 비동기 처리·이벤트·BullMQ | `message-queues.md` + `distri
Use whenever the user needs to log in to a website on their phone and reuse that authenticated session locally, especially for Playwright storageState JSON, cookies/localStorage capture, MFA, SMS codes, passkeys, or mobile-first login flows that are awkward in headless automation. You run Cookey CLI in your current environment; the user signs in on their iPhone in the Cookey app; the relay only transports encrypted blobs. Trigger even if the user asks more loosely for help logging in, reusing an authenticated browser state, exporting cookies, or getting a local automation session from a phone login.
One-shot escape hatch to temporarily disable no-vibe write guard for a single scoped task, then restore the marker.
Configure the cc-context-awareness context window warning system. Use when the user wants to change context warning thresholds, messages, or other cc-context-awareness settings.
分析已提取的小红书收藏内容，做 AI 总结、对比、提炼
Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI, Anthropic, Google, etc.), streaming, tool calling, structured output, or embeddings, (4) Use React hooks like useChat or useCompletion. Triggers on: "AI SDK", "Vercel AI SDK", "generateText", "streamText", "add AI to my app", "build an agent", "tool calling", "structured output", "useChat".
Create and configure Neuron AI agents with providers, tools, instructions, and memory. Use this skill whenever the user mentions building agents, creating AI assistants, setting up LLM-powered chat bots, configuring chat agents, or wants to create an agent that can talk, use tools, or handle conversations. Also trigger for any task involving agent configuration, provider setup, tool integration, or chat history management in Neuron AI.
Analyze project dependencies for security, updates, and optimization. Keywords: dependency, npm, pip, maven, gradle, 依赖分析, 包管理
Bundle a Tidybot skill and its dependencies into a single executable Python script for robot submission. Use when (1) submitting a multi-dependency skill to the robot, (2) preparing code for the /code/execute API, (3) resolving deps.txt dependency chains into one file.
Use when writing or modifying OCaml code to annotate AI involvement. Triggers on any code generation, editing, or autonomous agent output in .ml/.mli files. Also use when creating or updating .opam files for packages containing AI-involved code.
skill-sample/ ├─ SKILL.md ⭐ Required: skill entry doc (purpose / usage / examples / deps) ├─ manifest.sample.json ⭐ Recommended: machine-readable metadata (index / validation / autofill) ├─ LICENSE.sample ⭐ Recommended: license & scope (open source / restriction / commercial) ├─ scripts/ │ └─ example-run.py ✅ Runnable example script for quick verification ├─ assets/ │ ├─ example-formatting-guide.md 🧩 Output conventions: layout / structure / style │ └─ example-template.tex 🧩 Templates: quickly generate standardized output └─ references/ 🧩 Knowledge base: methods / guides / best practices ├─ example-ref-structure.md 🧩 Structure reference ├─ example-ref-analysis.md 🧩 Analysis reference └─ example-ref-visuals.md 🧩 Visual reference
More Agent Skills specs Anthropic docs: https://agentskills.io/home
├─ ⭐ Required: YAML Frontmatter (must be at top) │ ├─ ⭐ name : unique skill name, follow naming convention │ └─ ⭐ description : include trigger keywords for matching │ ├─ ✅ Optional: Frontmatter extension fields │ ├─ ✅ license : license identifier │ ├─ ✅ compatibility : runtime constraints when needed │ ├─ ✅ metadata : key-value fields (author/version/source_url...) │ └─ 🧩 allowed-tools : tool whitelist (experimental) │ └─ ✅ Recommended: Markdown body (progressive disclosure) ├─ ✅ Overview / Purpose ├─ ✅ When to use ├─ ✅ Step-by-step ├─ ✅ Inputs / Outputs ├─ ✅ Examples ├─ 🧩 Files & References ├─ 🧩 Edge cases ├─ 🧩 Troubleshooting └─ 🧩 Safety notes
Skill files are scattered across GitHub and communities, difficult to search, and hard to evaluate. SkillWink organizes open-source skills into a searchable, filterable library you can directly download and use.
We provide keyword search, version updates, multi-metric ranking (downloads / likes / comments / updates), and open SKILL.md standards. You can also discuss usage and improvements on skill detail pages.
Quick Start:
Import/download skills (.zip/.skill), then place locally:
~/.claude/skills/ (Claude Code)
~/.codex/skills/ (Codex CLI)
One SKILL.md can be reused across tools.
Everything you need to know: what skills are, how they work, how to find/import them, and how to contribute.
A skill is a reusable capability package, usually including SKILL.md (purpose/IO/how-to) and optional scripts/templates/examples.
Think of it as a plugin playbook + resource bundle for AI assistants/toolchains.
Skills use progressive disclosure: load brief metadata first, load full docs only when needed, then execute by guidance.
This keeps agents lightweight while preserving enough context for complex tasks.
Use these three together:
Note: file size for all methods should be within 10MB.
Typical paths (may vary by local setup):
One SKILL.md can usually be reused across tools.
Yes. Most skills are standardized docs + assets, so they can be reused where format is supported.
Example: retrieval + writing + automation scripts as one workflow.
Some skills come from public GitHub repositories and some are uploaded by SkillWink creators. Always review code before installing and own your security decisions.
Most common reasons:
We try to avoid that. Use ranking + comments to surface better skills:
