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
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.
prd
Create an implementation-ready PRD for a feature. Use for product requirements, feature specs, user stories, planning, or preparing for `/spec-to-tasks`. Do not implement or write code.
prd-ralph-loop
Orchestrate the implementation of a PRD with subagents. Use for completing all PRD tasks/stories, not a single task.
pr
Use when writing a PR body.
official-sources
Use when code or guidance depends on a named framework, library, SDK, platform, or versioned API. Use when the user wants official documentation or authoritative sources. Use when the user mentions 'official docs', 'official sources', 'official documentation', or similar.
improve-skill
Use when a mistake is made, a failure occurs, a user corrects you, a user points out a mistake, a user provides steering, negative code review results are provided, a workaround is discovered, a code review reveals a gap in understanding, or a gap exists in a skill's instructions.
improve-repo-harness
Improve the repo harness by adding new features, fixing bugs, and enhancing performance.
improve-codebase-architecture
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
handoff
Maintain concise, current task handoffs. MANDATORY first action whenever a task mentions a handoff or handoff.md, or involves resume, continue, pick up, next step, checkpoint, or context transfer. Load before touching handoff files; loading the skill does not authorize file changes.
guidance-review
Review guidance for contradictions, ambiguity, duplication, omissions, and opportunities for concise wording.
grilling
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, record an architectural decision, or uses any 'grill' trigger phrases.