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
orient
Use when entering a vault cold, starting any work, or needing to understand what is in the vault. Orients to vault identity, strategic priorities, and assembles topic-focused context. Activates on "orient", "load context", "what is in the vault", or "vault status".
orient-session
Use when the user wants to continue prior work, resume a topic, or pick up where they left off on a recurring subject. Recalls prior session context before opening a new session. Activates on "continue work on X", "resume research on X", "pick up where I left off on X", or "start session with context on X".
graph-intelligence
Use when analyzing vault structure, finding connections between ideas, identifying knowledge gaps, or understanding the shape of a knowledge base. Guides interpretation of graph analysis results.
garden-health
Use when the user wants to maintain vault health, garden the knowledge base, check for orphans, find what is stale, audit structural gaps, or see a vault health report. Composes analysis tools into a full health picture before proposing any remediation.
decision-support
Use when the user wants to evaluate options, assemble decision context, get a structured briefing before deciding, or understand what their vault says about a decision. Activates on "help me decide X", "decision context for X", "what do my notes say about X decision", "decision briefing", or "evaluate options".
capture
Use when the user wants to capture research, create a note about a topic, ingest an external source, or add knowledge to the vault. Guides structured content creation with duplicate detection and automatic linking.
align
Use when the user asks whether a decision, action, or direction aligns with their priorities. Checks proposed actions against polaris strategic priorities and presents a structured alignment analysis.
websocket-engineer
Use when building real-time communication systems with WebSockets or Socket.IO. Invoke for bidirectional messaging, horizontal scaling with Redis, presence tracking, room management.
websocket-engineer
Use when building real-time communication systems with WebSockets or Socket.IO. Invoke for bidirectional messaging, horizontal scaling with Redis, presence tracking, room management.
websocket-engineer
Use when building real-time communication systems with WebSockets or Socket.IO. Invoke for bidirectional messaging, horizontal scaling with Redis, presence tracking, room management.
websocket-engineer
Use when building real-time communication systems with WebSockets or Socket.IO. Invoke for bidirectional messaging, horizontal scaling with Redis, presence tracking, room management.
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.
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.
train
Launch a new max_llm training run on both GPUs (RTX 4090 + RTX 3090 Ti) through torchrun DDP, resolving the TOML config by name or path. Use only when the user explicitly asks to start, launch or begin a run — "resume", "continue" or "keep training" mean the existing run; takes an optional config name or path.
serve-live
Before a person looks at a running service, make sure what is running IS the code in the checkout. Restart the services your change actually touched — not every service — and verify each is serving the current commit rather than merely answering; check the remaining dependencies are up without bouncing them. Use whenever you finish work a person will view in a browser or client, whenever you say a page or service is ready, after any commit that changes served code, and when asked to 'restart', 'refresh the services', 'is it live', or 'serve the latest'. Also covers waiting for lazy warm-up before calling a service ready.
review
Review a local change, branch, pull request, or stack for correctness, regressions, security, tests, and unnecessary complexity. Use when asked to review rather than implement.
regression-coverage
Reshape a slow or brittle test suite around observable user journeys and published contracts. Use when pruning tests, repairing weak smoke coverage, or addressing repeated feature regressions.
pr-babysit
Monitor selected pull requests and report or safely act on review, CI, mergeability, and stack state.