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
shop-pack
Everything a small online shop needs from one product list and the seller's own photos: square product images, a store banner and collection header, a care or thank-you card for the parcel, and a launch post, all in one style and filled per product.
shader-dev
GLSL shader techniques for ray marching, fluid simulation, particle systems, and procedural generation. Useful for hero visuals and motion stills.
shadcn-ui
Build UI components with shadcn/ui. Pairs with the Stitch design loop to ship structured, accessible components quickly.
screenshots-marketing
Generate marketing screenshots with Playwright. Useful for landing-page hero shots, App Store screenshots, and changelog visuals.
screenshot
Capture desktop, app windows, or pixel regions across OS platforms. Useful for marketing screenshots, design reviews, and bug reports.
rfc
A request for comments: the problem, goals and non-goals, the proposal with the alternatives considered, risks, rollout and open questions, with a status banner, grounded in the code and docs it changes.
review-animations
Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy. Default to flagging; approval is earned.
resume-modern
Modern minimal resume, single A4 page, ready for print or PDF export.
research-decision-room
Turn messy user research notes, interviews, support tickets, surveys, and product context into an evidence-backed decision room: a single HTML artifact with an evidence ledger, theme map, confidence heatmap, opportunity matrix, decision memo, and experiment queue. Use when teams need to move from qualitative signals to product or design decisions without fabricating certainty.
replicate
Discover, compare, and run AI models using Replicate's API. Strong fit for image, audio, and video generation pipelines that swap models frequently.
remotion
Programmatic video creation with React. Useful for branded explainers, social cuts, dashboards-to-video, and reproducible motion graphics.
release-notes-one-pager
Release notes one-page HTML with highlights, Added, Fixed, Breaking changes, Known issues, and Upgrade note. Writes explicit "None" style sections whenever the user does not provide details.
reference-design-contract
Turn vague taste, screenshots, URLs, product notes, or "make it feel like this" references into a grounded DESIGN.md plus an implementation handoff. Use it before prototypes, decks, redesigns, or image remix work when the user needs a reusable visual direction rather than a one-off prompt.
redesign-existing-projects
Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.
pr-feedback-quality-gate
Safely track pull request feedback, resolve review comments or merge conflicts, validate fixes, and use a read-only cross-review before committing or pushing follow-up changes.
pr-explainer
A pull request explained for reviewers: what changed and why, a before and after, risks and the test plan, and a guided tour of the files, drawn from the branch commits and diff.
pptx
Read, generate, and adjust PowerPoint slides, layouts, and templates. Useful for executive decks, training material, and product reviews.
pptx-html-fidelity-audit
Audit a python-pptx export against its source HTML deck, identify layout/content drift (footer overflow, cropped content, missing italic/em, lost styling, off-rhythm spacing), and re-export with strict footer-rail + cursor-flow layout discipline. Use this skill whenever the user has a .pptx that was generated from an HTML slide deck and asks to compare/audit/verify/fix the export — including phrases like "compare ppt with html", "fidelity audit", "fix the pptx", "ppt is cut off", "footer overlap", "italic missing in pptx", "re-export the deck", "pptx-html-fidelity-audit", or any case where a python-pptx → HTML round-trip needs verification or repair. Also trigger when the user shows you a deck.html and a deck.pptx side by side and is debugging visual differences.