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 196628
accomplishment-report
Create a concise Forest Service executive accomplishment report when all work in an ExecPlan is completed, or update its existing report. Use at ExecPlan closeout and when asked to report completed work, agency alignment, and estimated AI-assisted versus human-only time and cost savings.
writing-for-agents
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
web-performance
Optimize web performance for faster loading and better user experience. Use when asked to "speed up my site", "optimize performance", "reduce load time", "fix slow loading", "improve page speed", or "performance audit".
web-best-practices
Apply modern web development best practices for security, compatibility, and code quality. Use when asked to "apply best practices", "security audit", "modernize code", "code quality review", or "check for vulnerabilities".
web-accessibility
Audit and improve web accessibility following WCAG 2.2 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible".
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets, and resolve them one at a time until the way to the destination is clear.
to-issues
Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices.
techdebt
Find and safely remove duplicated or redundant code in current context or a provided scope, e.g. `scope:git diff main..HEAD`.
teach
Teach the user a new skill or concept, within this workspace.
tdd
Mandatory whenever you design or edit source code files. Use when the user mentions implement, "red-green-refactor", test-first development, tdd, test driven development, or integration tests. DO NOT use when delegating design or implementation work to a subagent, but you MUST explicitly instruct the subagent to activate the tdd skill in your prompt.
subagent-model-router
Route subagent work to the cheapest capable model. Use before dispatching subagents, task tools, background agents, code reviewers, security reviewers, or parallel workers when a model must be selected.
spec-to-tasks
Use when the user wants to break down a SPEC, PRD, plan, or raw requirements into independent, bounded tasks. Do not use to write the spec or implement tasks.
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
show-me
Help the user understand the current topic visually with concise diagrams, code-shape sketches, and focused HTML artifacts.
saga
Run an autonomous, spec-driven development saga for a medium-to-large feature using an orchestrator and worker subagents. Use when the user invokes /saga, asks to autonomously build a sizable feature end-to-end, wants a comprehensive milestone and task spec before parallel implementation, or asks to continue or resume a saga under the target repository's brain/sagas directory.
retro
Conduct a retrospective on a coding session.
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.
prototype
Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.