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
@microsoftopenclaw
@openclawAnthropic
@anthropicsOpenAI
@openaiThe Apache Software Foundation
@apacheGitHub
@githubAutoGPT
@Significant-GravitasGarry Tan
@garrytan全部 Skills 482556
seo-audit
Audit or diagnose site SEO, rankings/traffic losses, crawl/indexing issues, metadata, page speed, and Core Web Vitals, including general requests for SEO help. Programmatic pages, schema markup, and AI search have separate workflows.
releasepr
Adopt, configure, run, or troubleshoot compozy/releasepr in a consuming repository, including Actions, beta/stable/legacy plans, notes, dry-runs, and publication. Excludes pr-release internals and general versioning advice.
refactoring-analysis
Audit code quality and architectural health or plan refactoring using Fowler code smells and techniques; write prioritized findings to docs/_refacs/. Excludes formatting, performance, and security audits.
react
Build React 19 components and hooks under React Compiler: state, Effects, memoization, props/refs, Actions, use(), compiler/lint setup, and Vitest tests. Excludes React Native, other frameworks, and backend-only Node.js.
react-doctor
Use when finishing a feature, fixing a bug, before committing React code, or when the user types `/doctor`, asks to scan, triage, or clean up React diagnostics. Covers lint, accessibility, bundle size, architecture. Includes a regression check and a full local-triage workflow that fetches the canonical playbook.
qmd
Search markdown knowledge bases, notes, and documentation using QMD. Use when users ask to search notes, find documents, or look up information.
qa-report
Create or update living QA docs, journey/scenario plans, persona session charters, and the durable bug registry. qa-execution owns live sessions, browser evidence, and fix loops.
qa-execution
Run requested dogfooding through public product interfaces. Use existing QA journeys or qa-report to plan them; excludes routine code edits and CI-only verification.
proto
Author, set up and debug @compozy/proto prototypes, drafts, flows, existing Storybook stories and the canvas. Use when editing `*.proto.tsx`, `src/drafts/`, `*.flow.ts`, `proto.canvas.tsx` or `proto.config.ts` and its Vite, Storybook or Vitest guards, when running the `proto` CLI or MCP tools, or when `proto check`, `proto dev` or a capture fails. Not for UI edits that touch no prototype, nor for gallery review comments (proto-apply-comments).
proto-apply-comments
Apply @compozy/proto gallery review comments to the code that renders them, verify the reviewed state and answer each thread. Use for a comment id such as `login-form-7` or `flow-checkout-2` or `story--ui-button-3`, a gallery link with `comment=`, or a request to address open prototype review comments. For authoring prototypes or setting up proto, use the proto skill.
performance-optimization
Optimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks.
no-workarounds
Evaluate a proposed fix that suppresses errors, diagnostics, or symptoms. Use for suspected workarounds and unavoidable external defects; not as a mandatory stage for every bug fix.
next-best-practices
Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling
mermaid-diagrams
Create Mermaid diagrams for software architecture, data models, code, processes, and user flows. Use for diagramming, visualization, flow explanations, and class, sequence, ER, C4, state, Git, chart, or timeline representations.
impeccable
Design, redesign, review, or improve frontend interfaces and design systems. Covers UX, visual hierarchy, accessibility, responsive behavior, performance, copy, theming, motion, edge cases, browser iteration, and ambitious effects. Excludes non-UI work.
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases. Credits: Original skill by @blader - https://github.com/blader/humanizer
herdr
Control Herdr, a terminal multiplexer for coding agents. Use only when the user explicitly mentions Herdr or asks to use Herdr to inspect or control panes, tabs, workspaces, commands, or another agent. Do not use merely because a task could benefit from a background terminal, delegation, or parallel work. Requires HERDR_ENV=1.
herdr-orchestration
Orchestrate Claude and Codex worker TUIs from a controller agent — one worker per named herdr tab, driven over the herdr socket CLI.