Use when the user wants to practice LeetCode problems, submit solutions, or set up LeetCode integration. Covers MCP server installation, learning-guided practice flow, solution submission, and authentication.
외부 기여자 PR 검토 절차를 적용한다. PR 정보 수집, mydocs/pr/pr_{N}_review.md 작성, 검증, pr_{N}_report.md 작성, 처리 완료 시 archives/ 이동을 수행한다. 외부 기여자 PR 전용 (내부 타스크에는 사용 금지). --- # 외부 기여자 PR 검토 ## 트리거 - 작업지시자가 "PR #N 리뷰" 또는 "외부 PR 검토"를 명시 지시한 경우 - 본 SKILL을 직접 호출한 경우 ## 사전 조건 - 검토 대상 PR이 외부 기여자 fork에서 본 저장소 `{BASE_BRANCH}`(또는 합의된 base)로 열린 상태 - 내부 타스크 PR(`publish/task{N}`)에는 본 SKILL 사용 금지 — 내부 타스크는 일반 단계 절차로 검토 - `gh` CLI 인증 ## 절차 1. PR 메타 수집 ```bash gh pr view {N} --json number,title,state,baseRefName,headRefName,headRepository,mergeable,mergeStateStatus,reviewDecision,labels,body gh pr diff {N} | head -200 gh pr checks {N} ``` - 이슈 연결, base/head, mergeable, CI 상태 모두 확인 2. 검토 문서 작성: `mydocs/pr/pr_{N}_review.md` - 중앙 템플릿 `mydocs/_templates/external_pr_review.md`를 기준으로 작성한다. - 템플릿을 읽을 수 없는 경우에만 다음 최소 섹션을 fallback으로 사용한다: - PR 정보 (번호, 작성자, base/head, 연결 이슈) - 변경 요약 - 영향 범위와 호환성 (FFI, build, 문서) - 코드/문서 점검 결과 - 검증 계획 (필요한 추가 검증) - 권고 (merge / 수정 요청 / 닫기) - 작업지시자 승인 요청 3. 작업지시자 승인 요청 (검토 방향 결정) 4. 필요 시 수정·검증 계획 문서 작성: `mydocs/pr/pr_{N}_review_impl.md` - 중앙 템플릿 `mydocs/_templates/external_pr_review_impl.md`를 기준으로 작성한다. - 본 저장소에서 추가 검증을 직접 수행할 때 사용 - 작성 후 작업지시자 승인 요청 5. 검증 수행 (해당하는 경우만) - 검증은 변경 유형에 따라 `{PROJECT_VALIDATION_GUIDE}` 정책 적용 6. 최종 보고서 작성: `mydocs/pr/pr_{N}_report.md` - 중앙 템플릿 `mydocs/_templates/external_pr_report.md`를 기준으로 작성한다. - 검토 결과, 검증 결과, 최종 권고, GitHub PR 코멘트 본문(또는 링크) 7. 작업지시자 승인 후 GitHub PR에 코멘트/리뷰 등록 (merge 결정은 작업지시자가 수행) 8. 처리 완료 시 문서 보관 이동 ```bash git mv mydocs/pr/pr_{N}_review.md mydocs/pr/archives/ git mv mydocs/pr/pr_{N}_review_impl.md mydocs/pr/archives/ # 존재 시 git mv mydocs/pr/pr_{N}_report.md mydocs/pr/archives/ ``` 9. 단일 또는 단계별 커밋 (외부 PR 검토는 내부 단계 형식 강제 아님) ```bash git commit -m "PR #{N} 검토: {요약}" ``` ## 검증 - `mydocs/pr/pr_{N}_review.md`가 `mydocs/_templates/external_pr_review.md`의 필수 섹션을 채움 - `mydocs/pr/pr_{N}_review_impl.md`를 작성했다면 `mydocs/_templates/external_pr_review_impl.md`의 필수 섹션을 채움 - `mydocs/pr/pr_{N}_report.md`가 `mydocs/_templates/external_pr_report.md`의 필수 섹션
Use stacklit.json to navigate codebases without burning tokens on file exploration
Algorithm analysis with parallel multi-model reasoning — qwen_algo, qwen_reason, and minimax_code tackle your problem from different angles
Operation identity and scoped guidance for Conflux acceptance review. The fixed acceptance procedure remains defined by the .opencode/commands/cflx-accept.md command template. CRITICAL - This skill CANNOT ask questions or request user input.
Translate changed English locale keys into all other languages
General-purpose ClawProbe spend digest skill for OpenClaw. Use when the user needs a daily, weekly, or monthly cost digest, top spenders, token totals, daily breakdowns, or previous-period comparisons based on local OpenClaw and clawprobe data. This skill is guidance plus a runnable Node script: read this file, then use exec with node to generate the digest.
Provides domain knowledge and guidance for Flare FAssets—wrapped tokens (FXRP, FBTC, etc.), minting, redemption, agents, collateral, and smart contract integration. Use when working with FAssets, FXRP, FBTC, FAssets minting or redemption, Flare DeFi, agent/collateral flows, or Flare Developer Hub FAssets APIs and contracts.
Generic bioinformatics reproduction playbook for data discovery, execution planning, degradation, and auditable negative or partial results without paper-specific shortcuts.
你是一位专业的微短剧编剧，精通短视频平台的爆款短剧创作方法论。你将引导用户从选题到完稿，完成一部 50-100 集的完整微短剧剧本。
學使用者的 Facebook 個人貼文語氣，依 14 天內容策略日曆，自動產出並發佈到 FB / Instagram / Threads / X。使用時機：使用者說「發文」、「幫我寫一篇貼文」、「用我的風格發」、「今天發一篇」、「PO 一下」、「學我的語氣」、「分析我的貼文風格」、「重新規劃內容」、「排貼文」時一律觸發；即使只說「發一篇」、「PO 文」、「PO 個廢文」也要觸發。
Search Memex long-term memory for relevant information. Returns facts, notes, and entities matching the query.
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:
