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
keep-mac-awake
Keep a Mac awake and prevent sleep, also with the lid closed, while an agent or a long task runs, with the keepmacawake command of the Keep Mac Awake app (Apple silicon, macOS 26 or later). Use it when the Mac must stay awake through work likely to run 15 minutes or more or that the user may leave running (an agent run, a build, a test suite, a migration, a download or upload, a render, a backup); when the user says they will close the lid, step away, go to bed or check in from their phone (Claude Code Remote Control, Codex in the ChatGPT app, Cursor, Antigravity, SSH); when a remote session went offline because the Mac slept; when local scheduled work, such as a Claude desktop scheduled task or a Codex automation, must run while the lid is closed; and when the user asks to keep the Mac awake or stop it from sleeping. On a Mac with Keep Mac Awake, use it rather than a caffeinate command of your own.
bankbridge
Answer questions about the user's own money with live, read-only data from their connected US banks, credit cards and brokerages through the BankBridge MCP server. Use when the user says "how much did I spend on restaurants last month", "what subscriptions am I paying for", "find subscriptions I forgot about", "am I making more than I spend", "what's my balance", "check my bank account", "what is this charge on my card", "did my paycheck come in", "how much do I spend on groceries", "compare this month to last month", "draft a budget from my real spending", "any duplicate charges", "did a subscription go up in price", "how are my investments doing", "how much did I get in dividends", "export my transactions for taxes", or "what's my credit card utilization". For moving money, paying bills or trading, say BankBridge is read-only and can't. For general money advice that needs no account data, answer without this skill.
checking-a-page
Check that a web page you wrote or changed actually works, by opening it in a browser and driving every control on it. Use after creating or editing an HTML page, or the JavaScript or CSS that a page loads.
langfuse
Investigate AI traces, observations, exceptions, latency, sessions, prompts, datasets, annotation queues, and scores through Langfuse MCP. Use when the request names Langfuse or asks to diagnose recorded AI behavior.
rules
暂无简介
tailtest
Generate test scenarios, write the test file, and run it for a specific source file using the tailtest R1-R15 rule layer. When the agent needs to (1) cover a file the Stop hook skipped, (2) regenerate tests after refactoring, (3) test a legacy file Codex did not modify this session, or (4) explicitly run tailtest on a named file.
seo-content-brief
Generate competitive SEO content briefs with per-section word counts, competitor scoring, keyword density guidance, and page-type templates. Supports both new page briefs and improve-existing-page briefs. Use when user says "content brief", "write a brief", "content outline", "blog brief", "service page brief", "brief for", "writing brief", "content plan", or "outline for".
tearitapart
Critical pre-implementation review. Find what AI breaks. Verdict: PROCEED, REVISE, or RETHINK. Triggers: review plan, tear apart, critique, analyze.
simplify
Simplify code, plans and systems without losing required outcomes; delete machinery that earns nothing; for code, AST-measured complexity with regression gates. Triggers: simplify, refactor, complexity, overengineered, dead code, useless guard.
ship
Release-gate sequence: validate → review → push → tag. Wraps kernel:git mechanics with the pre-ship safety chain. Triggers: ship, release, push to main, ready to merge, deploy.
review
Code review for PRs or staged changes. >80% confidence threshold. Verdict: APPROVE, REQUEST CHANGES, or COMMENT. Triggers: review, pr, code review.
retrospective
Audit whether prior learnings actually fired, then install mechanisms for this run's recurrences. No finding without an install path and a firing test. Triggers: retrospective, reflect, what did we learn, patterns, post-mortem, why does this keep happening.
quality
AI code quality checks. The Big 5: input validation, edge cases, error handling, duplication, complexity. Triggers: quality, big 5, ai code, review, validate.
orchestration
Multi-agent orchestration: lane contracts, worker-model doctrine, fault tolerance. Triggers: orchestrate, coordinate, agents, parallel, spawn, contract, tier 2, tier 3.
metrics
Observability dashboard. Session stats, agent tracking, hook performance, learning health. Triggers: metrics, stats, dashboard, observability.
marketing-site
Honest marketing-site method: audience, offer, proof, objections, privacy, art direction, handoff. Triggers: marketing site, landing page, company website, portfolio, campaign page, conversion, positioning, value proposition, CTA, social proof, privacy policy.
landing-page
Explicit landing-page build and deploy operator. Loads marketing and frontend judgment, scaffolds the smallest suitable site, verifies it rendered, deploys to the configured target.
knowledge-graph
Build, refresh and query a deterministic code knowledge graph to cut orientation-token cost. Triggers: knowledge graph, graphify, code graph, god nodes, orientation cost, map the codebase, what connects, callers of, blast radius.