Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
49,103 skills from 2,358 repositories · updated 28 minutes ago
10,564 skills
- mk-120backtrue/thinkwithblack-skill銷售頁一句話定位。用於需要清楚回答賣給誰與解決什麼的工作；依本項方法處理已指定資料並核對交付OtherNo warnings★ 252↓ —
- mk-121backtrue/thinkwithblack-skill銷售頁痛點開場。用於需要以原始需求為基礎的開頭的工作；依本項方法處理已指定資料並核對交付OtherNo warnings★ 252↓ —
- mk-340backtrue/thinkwithblack-skill四句式答案段落草稿。用於需要依原始事實重排的回答模組的工作；依本項方法處理已指定資料並核對交付OtherNo warnings★ 252↓ —
- mk-116backtrue/thinkwithblack-skill活動名單累積設計。用於需要明確告知用途的參與與訂閱路徑的工作；依本項方法處理已指定資料並核對交付OtherNo warnings★ 252↓ —
- mk-147backtrue/thinkwithblack-skill廣告素材需求單。用於需要交給設計或拍攝的規格與證據需求的工作；依本項方法處理已指定資料並核對交付OtherNo warnings★ 252↓ —
- 特殊程序pa1nrui1/legal-skills刑事特殊程序辩护与代理Skill，覆盖违法所得没收程序、精神病人强制医疗程序、再审申诉程序的启动条件、材料审查、听证或开庭准备、文书生成和与各刑事阶段Skill衔接。当用户提及"违法所得没收"、"强制医疗"、"精神病鉴定"、"再审"、"申诉"、"生效判决错误"等关键词时触发使用。OtherNo warnings★ 112↓ —
- mk-108backtrue/thinkwithblack-skill滿額贈門檻規劃。用於需要客單、贈品成本與門檻試算的工作；依本項方法處理已指定資料並核對交付OtherNo warnings★ 252↓ —
- mk-343backtrue/thinkwithblack-skill品牌一句與三句介紹。用於需要可供外部引用的標準介紹的工作；依本項方法處理已指定資料並核對交付OtherNo warnings★ 252↓ —
- mk-104backtrue/thinkwithblack-skill檔後接續計畫。用於需要交付、教學、回購與名單整理的工作；依本項方法處理已指定資料並核對交付OtherNo warnings★ 252↓ —
- mk-093backtrue/thinkwithblack-skill淡旺季節奏整理。用於依歷史資料標示季節性假說，或季節性電商詢問如何檢查旺季需求假設、安排全年工作與季末觀察；一般方法請教直接交條件式節奏，不因提到 PPC 或 CAC 就啟動實際帳戶診斷OtherNo warnings★ 252↓ —
- mk-354backtrue/thinkwithblack-skill搜尋結果版型盤點。用於需要實際結果中的文章、影片與通路的工作；依本項方法處理已指定資料並核對交付OtherNo warnings★ 252↓ —
- mk-339backtrue/thinkwithblack-skill弱段落優先序。用於需要最值得先改的段落及依據的工作；依本項方法處理已指定資料並核對交付OtherNo warnings★ 252↓ —
- decision-makerNickCrew/Claude-CortexUse this skill when you face a complex or high-stakes decision and need a structured framework to evaluate options objectively. Ideal for career choices, product prioritization, vendor selection, or any multi-criteria trade-off. Not for trivial daily decisions or situations that require licensed professional advice.OtherNo warnings★ 63↓ —
- self_awarenesswin4r/MuseAI-SkillsGround self-referential answers in the agent's actual filesystem. Use when the user asks who the agent is, what it can do, what it knows, what it remembers, what it has built, what services are connected, or what rules it follows.OtherNo warnings★ 408↓ —
- defense-in-depthNickCrew/Claude-CortexUse when invalid data causes failures deep in execution, requiring validation at multiple system layers - validates at every layer data passes through to make bugs structurally impossibleOtherNo warnings★ 63↓ —
- incident-responseNickCrew/Claude-CortexIncident triage, cascade prevention, and postmortem methodology. Use when handling production incidents, designing resilience patterns, or conducting chaos engineering exercises.OtherNo warnings★ 63↓ —
- build-optimizationNickCrew/Claude-CortexBuild system optimization covering compilation, caching, incremental builds, and developer tooling. Use when improving build times, configuring CI pipelines, or designing developer tools.OtherNo warnings★ 63↓ —
- reasoning-controlsNickCrew/Claude-CortexUse when adjusting reasoning depth, budgets, or metrics visibility - provides guidance for selecting and applying reasoning controls safely.OtherNo warnings★ 63↓ —
- knowledge-synthesisNickCrew/Claude-CortexExtract insights from multi-agent interactions, identify patterns, and build collective intelligence through cross-agent learning and knowledge management. Use when synthesizing findings, building knowledge bases, or improving system-wide practices.OtherNo warnings★ 63↓ —
- idea-labNickCrew/Claude-CortexTimeboxed divergent ideation that outputs ranked options plus day-one experiments.OtherNo warnings★ 63↓ —
- development-estimationNickCrew/Claude-CortexUse when estimating time, effort, or complexity for features or projects - provides structured estimation workflows with breakdowns, risks, and confidence intervals.OtherNo warnings★ 63↓ —
- wearables_commswin4r/MuseAI-SkillsRequired for every call or text-message request originating on a wearable: resolve named recipients from synced device contacts and invoke the originating wearable, not a paired phone.OtherNo warnings★ 408↓ —
- template-skill-enhancedNickCrew/Claude-CortexEnhanced skill template with progressive disclosure, bundled resources, and quality rubrics. Use when creating new skills that need structured tiers, reference files, validation rubrics, or advanced bundling patterns beyond the basic template.OtherNo warnings★ 63↓ —
- pre-mortemNickCrew/Claude-CortexImagine failure first to surface guardrails and feature mitigations.OtherNo warnings★ 63↓ —
mk-267
backtrue/thinkwithblack-skill
OtherUpdated 23 hours ago
From the author
需求開發任務定義。用於需要本次活動需驗證的商業問題的工作；依本項方法處理已指定資料並核對交付
Install
npx skills add backtrue/thinkwithblack-skill --skill mk-267 -a claude-code
Installs to .claude/skills/mk-267/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Download .zip
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
What it can touch
Runs bundled scriptsNo network use seenLicence: MIT
Safety checks on SKILL.md
- Ships scripts we have not reviewedLow
Why 79
Security85
Provenance69
Maintenance100
Licence100
Adoption40
Files (3)
- SKILL.md
- assets/check-context.py
- assets/context-contract.json