GITHUB AGENT SKILLS / 技能收录

给你的 AI 助手
装上专业技能

我们从 GitHub 持续收录、审核并分类优质的 Agent Skills,按职业与使用场景整理,复制一行命令即可安装到 Claude Code、Cursor 等智能体。

01 /

按职业浏览 Agent Skills

为不同岗位挑选的高频技能

全部职业
02 /

按使用场景浏览 Agent Skills

从你要完成的任务出发

全部场景
03 /

按创作者浏览 Agent Skills

按 GitHub Stars 排序的优秀创作者

全部创作者

全部 Skills 482556

laurac8r
laurac8r/claude-damn

pause

Use when wrapping up a session, parking work at a clean stop, or reaching a natural boundary where you want to close out current progress without starting new work

★ 3
laurac8r
laurac8r/claude-damn

listen

Execute instructions while listening for and invoking every skill referenced within them

Skill与智能体开发
★ 3
laurac8r
laurac8r/claude-damn

lets-make-a-skill

Use when creating or improving a skill that must both perform well on real prompts AND hold under rationalization pressure (discipline rules, process guardrails, workflows agents might shortcut under time or sunk-cost pressure).

Skill与智能体开发
★ 3
hugmouse
hugmouse/skills

value

Returns one fixed acknowledgment and stops. Use only when doing any actual work.

Skill与智能体开发
★ 3
laurac8r
laurac8r/claude-damn

legal-visual-aid

Use when the user gives a contract (text, file, or paste) and wants both an analysis AND an at-a-glance visual — "review this contract and make me a one-pager", "summarize this agreement visually", "give me a visual of the contract risks", "review + visualize this NDA/MSA/lease/EULA". Composes a risk-scored contract review with a single-page HTML visual aid.

律师与法务
★ 3
laurac8r
laurac8r/claude-damn

learn

Use when you want to review the current session for skills that misfired (skipped, invoked-but-ignored, or triggered user corrections) and update them — scans the active transcript, classifies findings, and delegates fixes to /lets-make-a-skill with per-finding approval

★ 3
laurac8r
laurac8r/claude-damn

jcvd

Open the best Jean-Claude Van Damme movie in your browser. Muscles from Brussels, activate.

★ 3
laurac8r
laurac8r/claude-damn

fixer

Systematic debugging (alias for /superpowers:systematic-debugging)

★ 3
laurac8r
laurac8r/claude-damn

fast-pr-final-self-review

Self-review to verify all PR peer feedback has been addressed on current branch

★ 3
laurac8r
laurac8r/claude-damn

fast-pr-feedback-to-others

Give code review feedback on current PR

代码审查
★ 3
laurac8r
laurac8r/claude-damn

fast-pr-feedback-to-me

Process code review feedback received on current PR

代码审查
★ 3
laurac8r
laurac8r/claude-damn

expert-tdd-review

Expert-level review, then fix using TDD

★ 3
laurac8r
laurac8r/claude-damn

expert-tdd-cat-review

Expert-level review with subagents, then fix using TDD with subagents

★ 3
laurac8r
laurac8r/claude-damn

expert-super-tdd-review

Expert-level review, then brainstorm and fix using TDD

★ 3
laurac8r
laurac8r/claude-damn

expert-super-tdd-cat-review

Expert-level review with subagents, then brainstorm and fix using TDD with subagents

★ 3
laurac8r
laurac8r/claude-damn

expert-super-review

Expert-level review, then brainstorm and fix

★ 3
laurac8r
laurac8r/claude-damn

expert-super-duper-tdd-review

Expert-level review, then brainstorm and fix using TDD in an isolated git worktree

★ 3
laurac8r
laurac8r/claude-damn

expert-super-duper-tdd-cat-review

Expert-level review with subagents, then brainstorm and fix using TDD in an isolated git worktree with subagents

★ 3