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
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
writing-clearly-and-concisely
Apply Strunk's timeless writing rules to ANY prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Makes your writing clearer, stronger, and more professional.
verify_changes
Use before considering work done — run the read-only quality gate and tests, interpret failures, and confirm the change is correct. The verification step of the working loop.
validate_module_structure
Use when validating module placement, dependency direction, and structure against repository governance.
using-git-worktrees
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback
ui-ux-pro-max
UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, and check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, and mobile app. Elements: button, modal, navbar, sidebar, card, table, form, and chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, and flat design. Topics: color systems, accessibility, animation, layout, typography, font pairing, spacing, interaction states, shadow, and gradient. Integrations: shadcn/ui MCP for component search and examples.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code
systematic_debugging
Use when diagnosing a bug, failing test, or unexpected behavior — drive a methodical reproduce → isolate → hypothesize → fix → verify loop instead of guessing. Prevents thrashing and repeated edits to the same file.
subagent-driven-development
Use when executing implementation plans with independent tasks in the current session
retrospective
Use at the end of a unit of work to capture durable, non-obvious knowledge into project memory (memory/) and flag decisions worth an ADR. Turns one-off discoveries into compounding, persistent context.
research_current_info
Use when the user asks for up-to-date or current information, to confirm something is still accurate, or when a task depends on facts that may have changed since training (library versions, APIs, pricing, releases, news, current best practices). Runs a governed web search with a curated domain allow/deny policy and cited, recency-checked results.
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
refactor_to_clean_architecture
Use when refactoring modules to align dependency direction, responsibilities, and boundaries with clean architecture.
plan_and_execute_feature
Use when delivering a feature through explicit planning, phased execution, validation, and governed handoff — or when implementing/fixing already-scoped engineering work via the execute_only mode.
generate_migration_plan
Use when planning low-risk code, data, or architecture migrations with validation and rollback steps.
generate_implementation_docs
暂无简介
generate_e2e_tests
Use when generating end-to-end tests for critical user, API, CLI, or service flows.
finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup