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
ponytail-review
Review a diff for over-engineering. Finds what to delete: reinvented stdlib, needless deps, speculative abstractions. One line per finding.
polish-pass
Run a comprehensive end-of-design quality gate before a design is shown to stakeholders or shipped, covering hierarchy, AI-slop, interaction states, and accessibility. Use as the final review pass before delivery, or when the user asks to 'polish', 'finalize', or 'make it shippable'.
copywriting
When the user wants to write, rewrite, or improve marketing copy for any page — including homepage, landing pages, pricing pages, feature pages, about pages, or product pages. Also use when the user says "write copy for," "improve this copy," "rewrite this page," "marketing copy," "headline help," "CTA copy," "value proposition," "tagline," "subheadline," "hero section copy," "above the fold," "this copy is weak," "make this more compelling," or "help me describe my product." Use this whenever someone is working on website text that needs to persuade or convert. For email copy, see email-sequence. For popup copy, see popup-cro. For editing existing copy, see copy-editing.
greeting
Greets people properly.
writing
Structured writing guidance.
wireframe
Produce low-fidelity wireframes or storyboards to explore a flow, layout, or idea across multiple options before committing to hi-fi design. Use when the user wants to 'explore options', 'sketch something out', 'see a few directions', or when the problem is open enough that hi-fi work would be wasted.
video-test
Record a video test of any feature or user flow via Playwright. Use when the user says "record video test", "video test", "record a test", "show me the feature", "record the UI", "capture video", or wants a visual demo of a feature. Accepts a description of what to test as an argument (e.g., `/video-test the brainstorm creation flow`).
risk-assessment
Assess the delivery risk and ambiguity of an issue. Scores three anchored 1-5 risk dimensions — Code Blast Radius, Complexity, Business Blast Radius — into an overall risk level (Low/Medium/High) with safeguards, plus a separate Ambiguity score (how many open questions remain) with the open questions listed. Use this BEFORE work starts, whenever someone wants to know how risky, how big, how complex, or how well-specified an issue is, or asks to "assess risk", "risk assessment", "score this issue", "how risky is this", "what's the blast radius", "how complex is this", "how ambiguous is this", or "how many open questions are there". Accepts a Multica issue ID, a GitHub issue/PR, or a free-text description as the argument.
research
Deep parallel codebase research before planning or implementation. Spawns 4 specialized agents that explore behavior, architecture, coding standards, and test coverage simultaneously, then synthesizes findings into a structured RESEARCH.md document. Use this skill when the user says "research", "investigate", "explore the codebase", "understand the code", "deep dive", or wants thorough analysis of an area before making changes. Also use it as the first step of any complex feature — research first, then plan, then implement.
ponytail
Lazy senior dev mode for any coding task (write, refactor, fix, review): YAGNI, stdlib first, no unrequested abstractions. Not for non-coding requests.
ponytail-review
Review a diff for over-engineering. Finds what to delete: reinvented stdlib, needless deps, speculative abstractions. One line per finding.
virtual-piano
Show a virtual piano to play music
polish-pass
Run a comprehensive end-of-design quality gate before a design is shown to stakeholders or shipped, covering hierarchy, AI-slop, interaction states, and accessibility. Use as the final review pass before delivery, or when the user asks to 'polish', 'finalize', or 'make it shippable'.
restaurant-roulette
Show a roulette wheel to allow user to randomly select a restaurant based on location and cuisine.
copywriting
When the user wants to write, rewrite, or improve marketing copy for any page — including homepage, landing pages, pricing pages, feature pages, about pages, or product pages. Also use when the user says "write copy for," "improve this copy," "rewrite this page," "marketing copy," "headline help," "CTA copy," "value proposition," "tagline," "subheadline," "hero section copy," "above the fold," "this copy is weak," "make this more compelling," or "help me describe my product." Use this whenever someone is working on website text that needs to persuade or convert. For email copy, see email-sequence. For popup copy, see popup-cro. For editing existing copy, see copy-editing.
mood-music
A skill to suggest or play music based on the user's mood, including analyzing images or audio, by querying available genres and generating music via the Loudly API.
spec-consistency
Checklist that keeps every artifact of the Harnessfile spec in sync — spec prose, JSON Schemas, CLI validator, UI validation, examples, README. Run before closing any spec-facing change and during review of one.
text-spinner
Spin the given text on my head.