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
review
Check how well the current implementation matches the feature spec and evaluate code quality. Runs spec compliance review followed by code quality review. Optionally runs unit/integration test audit, logging audit, and security audit when strategy files exist. Does not modify code.
reforge
Transform an existing project into spec-driven development. Analyzes a legacy codebase from an external folder, accepts change specifications, and generates feature specs (spec.md + design.md) that blend existing logic with requested modifications. Auto-runs /init if needed.
readability
Use when 삼항 연산자가 중첩되거나, 복잡한 조건식 `a && !b || c`가 이름 없이 사용되거나, 동시에 실행되지 않는 코드가 한 컴포넌트에 섞여 있을 때
vercel-react-best-practices
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
react-best-practices
React best-practices reviewer for TSX files. Triggers after editing multiple TSX components to run a condensed quality checklist covering component structure, hooks usage, accessibility, performance, and TypeScript patterns.
qa
AI-driven browser testing against feature specs. Default mode reads spec REQs and autonomously tests in a real browser via Playwright MCP. Also supports running existing Playwright test files, visual regression, and accessibility audits.
product-strategy
Create a comprehensive product strategy using the 9-section Product Strategy Canvas — vision, segments, costs, value propositions, trade-offs, metrics, growth, capabilities, and defensibility. Use when building a product strategy, creating a strategic plan, or defining product direction.
predictability
Use when `getX()`나 `fetchX()`에 숨은 부수 효과가 있거나, 같은 종류의 함수들이 서로 다른 반환 타입을 가지거나, 함수 이름과 실제 동작이 다를 때
pr
Create a pull request with auto-generated body from feature spec. Auto-detects target branch from GIT_STRATEGY.md. Optionally updates changelog and bumps version.
plugin-test
Run NCC plugin E2E tests. Supports quick (4 projects), full (4+monorepo+modifications), or custom test modes. Installs from current dev branch, validates spec→dev flow, skills, hooks, code quality, security, a11y, and token efficiency.
observability
Vercel Observability expert guidance — Drains (logs, traces, speed insights, web analytics), Web Analytics, Speed Insights, runtime logs, custom events, OpenTelemetry integration, and monitoring dashboards. Use when instrumenting, debugging, or optimizing application performance and user experience on Vercel.
next-best-practices
Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling
nextjs
Next.js App Router expert guidance. Use when building, debugging, or architecting Next.js applications — routing, Server Components, Server Actions, Cache Components, layouts, middleware/proxy, data fetching, rendering strategies, and deployment on Vercel.
mock
Generate or update MSW mock handlers and fixtures from feature spec API contracts. Use to set up mock infrastructure, generate feature-specific mocks, or check mock status.
loop
Force-complete a feature by looping until all REQs in spec.md are satisfied. Runs reviewer → targeted lead-engineer → re-review cycle. Use after /dev when you want guaranteed spec compliance.
log
Audit and improve logging practices. Review logging for a specific feature, audit the entire project, or set up logging infrastructure.
issue-reporter
Report a bug or feature request for the NCC plugin to GitHub. Sanitizes all project-specific and personal information before submission. Always asks for user confirmation before creating the issue. Use when encountering NCC plugin issues, bugs, or wanting to request new features.
init
First-time setup. Analyzes the existing codebase and populates spec/PROJECT.md, spec/ARCHITECTURE.md, spec/rules/, and draft feature spec files. Run once after installing FeatureSpec.