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.
48,168 skills from 2,325 repositories · updated 15 hours ago
10,174 skills
- mk-038backtrue/thinkwithblack-skill合理下一步設計。用於需要與需求成熟度相符的行動的工作;依本項方法處理已指定資料並核對交付OtherNo warnings★ 249↓ —
- mk-039backtrue/thinkwithblack-skill搜尋需求地圖建立。用於需要事件到行動的可檢查路徑表的工作;依本項方法處理已指定資料並核對交付OtherNo warnings★ 249↓ —
- mk-356backtrue/thinkwithblack-skill外部入口回官網路徑檢查。用於需要站外到節點與交易頁的承接的工作;依本項方法處理已指定資料並核對交付OtherNo warnings★ 249↓ —
- 调解与和解pa1nrui1/legal-skills提供调解与和解全流程支持,包括可行性分析、调解方案起草、调解书/和解协议审查、撤诉管理等功能。当用户发送客户编号并提及"调解"、"和解"、"撤诉"、"调解方案"、"调解书"等指令时触发使用。OtherNo warnings★ 112↓ —
- validateyahor-punko/mavericks-osRun the MavP validator to check artifact sync between BACKLOG.md and TASK_STATUS.md. Use after any backlog changes or to confirm healthy state before starting new work.OtherNo warnings★ 225↓ —
- mk-040backtrue/thinkwithblack-skill需求與廣告形式配對。用於需要搜尋、影片等方式的任務分工的工作;依本項方法處理已指定資料並核對交付OtherNo warnings★ 249↓ —
- clawteam-directors-orchestratormomozi1996/awesome-ai-persona-skillsClawTeam导演智囊团——基于ClawTeam多智能体框架的世界著名导演协同创作系统。 整合31位全球顶级导演的风格思想,通过多智能体协作机制(顺序链、辩论投票、主席团模式) 辅助剧本创作、影像风格设计和叙事决策。 触发词:「导演智囊团」「ClawTeam」「多导演协作」「剧本创作」「影像风格」 适用场景:编剧、导演、创意策划、影视教育、AI影像创作OtherNo warnings★ 1.1K↓ —Also in 1 other repo
- oma-loopJoonghyun-Lee-Frieren/oh-my-antigravityEnforce execution/verify/fix loops until acceptance criteria pass or blockers are explicit.OtherNo warnings★ 214↓ —
- 劳动争议仲裁程序管理pa1nrui1/legal-skills劳动争议仲裁程序全流程管理Skill,覆盖仲裁前置强制检测、仲裁时效计算、一裁终局自动判断、仲裁申请书/答辩书生成(W/E双角色)、仲裁请求清单、仲裁→诉讼衔接路由(L9五分支)、仲裁策略报告和用人单位仲裁前风险敞口评估。当用户发送客户编号并提及"仲裁申请"、"仲裁答辩"、"仲裁策略"、"仲裁时效"、"公司仲裁风险"、"风险敞口"等指令时触发使用。OtherNo warnings★ 112↓ —
- university-exam-prepstaruhub/ClaudeSkills大学备考苏格拉底式学习助手,专为应对"面向课本和PPT考试"设计。当用户说"帮我复习"、"准备考试"、"备考"、"期末复习"、"模拟学习"、"突击复习"等时触发。核心特点:(1)强制要求用户上传课本/PPT/考纲等原始材料——没有材料就无法有效辅导;(2)使用苏格拉底式提问法,不直接灌输而是引导思考;(3)专注于应用型和理解型内容,而非纯概念记忆;(4)模拟真实考试场景进行针对性练习;(5)分析材料识别高频考点和重难点。适用于大学各科目期中期末考试备考、突击复习、考前模拟。OtherNo warnings★ 731↓ —
- mk-070backtrue/thinkwithblack-skill降價所需增量試算。用於需要維持利潤需要補足的銷量的工作;依本項方法處理已指定資料並核對交付OtherNo warnings★ 249↓ —
- mk-078backtrue/thinkwithblack-skill引流款選品。用於需要適合取得新客的商品候選的工作;依本項方法處理已指定資料並核對交付OtherNo warnings★ 249↓ —
- tool-foundation-sprint-founding-hypothesisproduct-on-purpose/pm-skillsDay 2 end capstone move of a Foundation Sprint. Compresses the sprint's full strategic frame into a single canonical sentence (the Founding Hypothesis) plus an assumption scorecard, why-we-believe, what-could-prove-us-wrong, and recommended next validation step. Use after Magic Lenses is signed. Strict canonical template; paraphrase is not accepted in v0.1.0. The Founding Hypothesis is the spine artifact the sprint exists to produce.OtherReview first★ 774↓ —
- mk-043backtrue/thinkwithblack-skill網站接不住需求辨識。用於需要不存在或不足的承接頁清單的工作;依本項方法處理已指定資料並核對交付OtherNo warnings★ 249↓ —
- oma-stopJoonghyun-Lee-Frieren/oh-my-antigravityStop guarded work while preserving evidence and locks.OtherNo warnings★ 214↓ —
- oma-teamJoonghyun-Lee-Frieren/oh-my-antigravityRun OmA's full team lifecycle with optional dynamic team assembly and verify/fix loops.OtherNo warnings★ 214↓ —
- situational-awarenesszero-lab-ai/skillsAssesses a freshly compromised host quietly before acting — who/where/what's here/what's watching/what's around — using local reads and living-off-the-land so the SOC never sees the recon. Use right after gaining a foothold, before privilege escalation or lateral movement, or when deciding whether an enumeration command is quiet enough to run.OtherNo warnings★ 285↓ —
- oma-modeJoonghyun-Lee-Frieren/oh-my-antigravityInspect or set OmA operating mode/profile (balanced, speed, deep, autopilot, ralph, ultrawork).OtherNo warnings★ 214↓ —
- mk-075backtrue/thinkwithblack-skill成本指標口徑健檢。用於需要名單、人數、訂單是否混用的檢查的工作;依本項方法處理已指定資料並核對交付OtherNo warnings★ 249↓ —
- mk-044backtrue/thinkwithblack-skill搜尋假說驗證清單。用於需要各假說所需訪談、字詞或頁面證據的工作;依本項方法處理已指定資料並核對交付OtherNo warnings★ 249↓ —
- check-citationsbrycewang-stanford/Auto-Empirical-Research-SkillsVerify academic citations against CrossRef, Semantic Scholar, and OpenAlex. Detects AI-hallucinated references, chimeric citations, and suspicious patterns.OtherNo warnings★ 4.8K↓ —
- mk-344backtrue/thinkwithblack-skill品牌跨平台介紹對照。用於需要官網與各平台不一致處的工作;依本項方法處理已指定資料並核對交付OtherNo warnings★ 249↓ —
- mk-345backtrue/thinkwithblack-skill品牌類別與服務核對。用於需要被描述成錯誤類別的問題的工作;依本項方法處理已指定資料並核對交付OtherNo warnings★ 249↓ —
- 法律文章quai味道pa1nrui1/legal-skills检测并去除文章中的AI化表述模式,用于写作润色、文本优化、去AI腔。OtherNo warnings★ 112↓ —
situational-awareness
zero-lab-ai/skills
From the author
Assesses a freshly compromised host quietly before acting — who/where/what's here/what's watching/what's around — using local reads and living-off-the-land so the SOC never sees the recon. Use right after gaining a foothold, before privilege escalation or lateral movement, or when deciding whether an enumeration command is quiet enough to run.
Install
npx skills add zero-lab-ai/skills --skill situational-awareness -a claude-code
Installs to .claude/skills/situational-awareness/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
What it can touch
Safety checks on SKILL.md
- Ships scripts we have not reviewedLow
Why 79
Files (5)
- SKILL.md
- agents/openai.yaml
- assets/zero-lab-mark.svg
- references/noise-levels.md
- scripts/classify_enum.py