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
llm-caching
Implement multi-layer LLM caching with exact match, semantic similarity, and provider-side prompt caching.
frontend-testing
Generate or review Vitest and React Testing Library tests for frontend components, hooks, and utilities. USE FOR: "write Vitest tests for a React component", "review coverage gaps in a React hook spec", "review an existing frontend Vitest spec". DO NOT USE FOR: backend or API tests, Playwright or Cypress end-to-end tests, or conceptual questions without frontend code context.
frontend-code-review
Review pending frontend changes or specific frontend files against code-quality, performance, and business-logic checklists. USE FOR: "review a React component diff", "review pending .tsx changes", "review only a .tsx file". DO NOT USE FOR: creating new React components or implementing changes without a review request.
component-refactoring
Refactor high-complexity React components by reducing branching, extracting hooks, or splitting components. USE FOR: "reduce high measured complexity in a large React component", "extract stateful logic into hooks and split a complex component". DO NOT USE FOR: simple or well-structured components, third-party wrappers, or requests that explicitly ask for tests without refactoring.
why
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.
llm-app-security
Secure LLM-powered applications with input validation, output controls, tenant isolation, and abuse prevention.
unslop
Cut AI tells from any writing.
typescript-best-practices
TypeScript best practices. Use when reading or editing any .ts or .tsx file.
technical-writing
Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.
teach
Explain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.
tdd
Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target. Skip when the test path is unclear, expensive, integration-heavy, or not requested.
swarm
Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.
linux-hardening
Apply CIS benchmarks and secure Linux servers.
show-me-your-work
Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail to trust the result. Use for /show-me-your-work, autonomous or multi-phase runs, or work a human reviews after stepping away.
sharpen
Sharpen a task before starting: the expert approach, what the user is really after, and the right level of specification. Use for /sharpen.
linux-administration
System administration for Linux servers. Manage packages, services, and system configuration. Use when administering Linux systems.
tvfetch-quant
Quantitative analysis variant — always includes indicators and stats
tvfetch-minimal
Minimal data-only variant — fetch and print, nothing else