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。
按职业浏览 Agent Skills
为不同岗位挑选的高频技能
按使用场景浏览 Agent Skills
从你要完成的任务出发
按创作者浏览 Agent Skills
按 GitHub Stars 排序的优秀创作者
Microsoft
@microsoft
openclaw
@openclaw
OpenAI
@openai
The Apache Software Foundation
@apache
GitHub
@github
Anthropic
@anthropics
AutoGPT
@Significant-Gravitas
Garry Tan
@garrytan全部 Skills 192262
tdd
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
simple-english
Write or rewrite technical text with the rules of ASD-STE100 Simplified Technical English so it is clear, unambiguous, and free of AI slop. Use for documentation, READMEs, runbooks, procedures, error messages, release notes, incident reports, and API guides. Also use when the user says "STE", "Simplified Technical English", "ASD-STE100", "de-slop", "make this readable", "write for non-native readers", or asks for docs that translate well. Enforces the standard's 53 rules: 20/25-word sentence limits, one word one meaning, simple tenses, active voice, condition before command.
show-me
Help the user understand the current topic visually with concise diagrams, code-shape sketches, and focused HTML artifacts.
setup-ts-deep-modules
Wire dependency-cruiser into a TypeScript repo so each package is a deep module, with implementation hidden in subfolders and reachable only through its entry-point files. User-invoked.
setup-pre-commit
Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.
setup-matt-pocock-skills
Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
scaffold-exercises
Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section.
sandi-metz-rules
Apply Sandi Metz's four rules for maintainable Ruby code. Use when reviewing or refactoring Ruby code, or when the user mentions 'Sandi Metz', 'code quality', or 'refactoring'.
rex
Use the rex CLI to manage Rex sessions, open tabs, arrange panes, run commands, inspect terminal output, and control connected Rex apps.
reverse-engineer-anything
Reverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.
retro
Conduct a retrospective on a coding session.
resolving-merge-conflicts
Use when you need to resolve an in-progress git merge/rebase conflict.
research
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.
readme-writer
Write READMEs for software projects. The skill should be used when writing or revising a README or README.md file.
rails-programmer
Rails 8 development guidelines following DHH's philosophy and Rails conventions. Use when writing, reviewing, or modifying Rails code to ensure idiomatic, convention-driven implementations.
pr
Open a Pull Request with an interview process. Use when the user wants to create a PR, open a pull request, or ship changes to a branch.
pr-fixup
Review the current PR, then fix warranted review feedback, with each phase in a fresh subagent.
miren-house-style
Write Go that is indistinguishable from the Miren runtime team's house style, and review code/PRs the way Miren maintainers phinze and evanphx do — the substantive code adjustments they request and how the house style turns into review findings (not just comment tone). Use when writing, editing, or reviewing Go in the mirendev/runtime codebase (or any Miren repo), when a change needs to "look like Miren wrote it," when deciding what to flag or request in a Miren PR review, or when drafting review comments and replies to suggestions. Built from an evidence-backed survey of the codebase and ~1,600 real review comments.