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 196852
bmad-teach-me-testing
Teach testing progressively through structured sessions. Use when user says "lets learn testing" or "I want to study test practices"
research-paper-craft
Use when writing, structuring, or revising a state-of-the-art scientific research paper, review, preprint, or thesis chapter and you want it to read well and land. Covers the craft of paper architecture, the narrative spine, the title and abstract, figures as the paper UI, reproducible methods.
bmad-tea
Master Test Architect and Quality Advisor. Use when the user asks to talk to Murat or requests the Test Architect.
research-ops
Thin router for the research stack. Use when you want fresh facts, comparisons, enrichment, or evidence-backed recommendations -- it picks the right skill. NOT the full multi-source pass (use deep-research).
bmad-sprint-status
Summarize sprint status and surface risks. Use when the user says "check sprint status" or "show sprint status"
bmad-sprint-planning
Generate sprint status tracking from epics. Use when the user says "run sprint planning" or "generate sprint plan"
research-integrity-forensics
Use when checking a paper, corpus, or draft for integrity risks such as citation abuse, duplication, image problems, implausible claims, or unsupported certainty.
bmad-shard-doc
Splits large markdown documents into smaller, organized files based on level 2 (default) sections. Use if the user says perform shard document
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
bmad-review-edge-case-hunter
Walk every branching path and boundary condition in content, report only unhandled edge cases. Orthogonal to adversarial review - method-driven not attitude-driven.
bmad-review-adversarial-general
Perform a Cynical Review and produce a findings report. Use when the user requests a critical review of something
reporting-guideline-router
Use when the manuscript or protocol needs the correct reporting guideline lane such as PRISMA, CONSORT, STROBE, ARRIVE, STARD, CARE, or COREQ.
bmad-retrospective
Post-epic review to extract lessons and assess success. Use when the user says "run a retrospective" or "lets retro the epic [epic]"
repomix
Use when packing a repository into an AI-friendly bundle with Repomix, or when exposing Repomix as an MCP server to Codex, Claude Code, or Gemini CLI.
bmad-quick-dev
Implements any user intent, requirement, story, bug fix or change request by producing clean working code artifacts that follow the project's existing architecture, patterns and conventions. Use when the user wants to build, fix, tweak, refactor, add or modify any code, component or feature.
render-deploy
Use when deploying an application to Render.com, generating render.yaml Blueprints, or getting Render Dashboard deeplinks ; do NOT use for Vercel (use vercel-deploy), Netlify (use netlify-deploy), or Cloudflare (use cloudflare-deploy) ; returns Render Blueprint and deployment status.
bmad-qa-generate-e2e-tests
Generate end to end automated tests for existing features. Use when the user says "create qa automated tests for [feature]"
regex-vs-llm-structured-text
Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.