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
revid-product-description-to-ad
Turn a product description (free-form text — no URL needed) into a punchy 15–30 second AI-generated ad with hooks, CTA, and visuals. Use when the user pastes copy or specs but doesn't have a live page to scrape. Calls the Revid MCP server (render_video → get_project_status).
revid-pdf-to-video
Turn a PDF (whitepaper, ebook chapter, slide deck export, research paper) into a short summary video. Use when the source is a PDF URL or a PDF the agent can upload to public storage first. Calls the Revid MCP server (render_video → get_project_status).
revid-news-to-daily-short
Generate a daily news short on a topic Revid researches itself. Use for a recurring "news of the day in <niche>" channel — the user only supplies the topic; Revid fetches fresh news, writes the script, and produces the video. Calls the Revid MCP server (render_video → get_project_status).
revid-blog-to-avatar-video
Turn a blog post URL into a talking-head avatar video — the avatar reads a summarized script of the post against a clean background. Use when the user wants a personal/expert delivery vs an edited promo. Calls the Revid MCP server (render_video → get_project_status).
revid-article-to-short
Turn any news article or long-form post URL into a 30–60 second 9:16 short with stock visuals, narration, and captions. Use when the user shares a link and wants an edited summary, not a talking-head. Calls the Revid MCP server (render_video → get_project_status).
revid-api-foundations
Foundation knowledge for every Revid skill — MCP server install, the render_video / get_project_status / export_video tools, the workflow discriminator, and the response envelope. Load this once at session start; specific skills build on it.
remotion-video-builder
Use when building, reviewing, or refactoring a Remotion project, especially parameterized launch or demo videos with shared props schemas, calculateMetadata, Sequence and Series timing, multiple aspect ratios, terminal or footage layers, and render scripts. Prefer official Remotion docs or MCP for API details because package behavior may change.
figma-slop-check
Review the craft and technical precision of a requested Figma scope with project canon, measures and visual evidence; classify swap/snap/ask while respecting existing correction authorization.
figma-preflight
Read-only preflight for an authorized Figma write: correct live target, applicable DS/API context, states and single-writer lock; also supports requested flow-graph audits.
figma-orient
Map a new or unfamiliar Figma scope without canvas writes, reuse verified project maps, and record pages/screens/DS plus coverage. Persistence follows project privacy and the actual runtime's authorization.
figma-handoff-gate
Audit a Figma handoff for action/state completeness, readable annotations, recipient use and valid proof. Read-only review and already authorized correction remain distinct; no fixed review-role ritual.
figma-comment-fix-loop
Apply requested Figma review comments to their pinned screens with scoped discovery, idempotent fixes and private evidence. Existing authorization governs writes; public replies need an explicit request.
figma-click-flow
Draw or refresh a static click-flow overlay on laid-out Figma screens from prototype reactions or explicit pairs, using the existing SVG recipe and verified targets.
figma-canon
Read-only Figma technical canon and production gotchas. Load the reference needed for the current inspection, write, design-system operation or handoff; project rules and authorization prevail.
figma-bridge-doctor
Diagnose or restore the figma-console Desktop Bridge with a minimal state-based action and verified pairing. Recovery is session-safe; macOS scripts, restart and persistent helpers keep their own permissions.
watch-competitors
Watch an AI plugin's competitors over time: ranks, installs, featuring, listing rewrites, MCP tool changes and the countries that list them, side by side, and what changed since last time. Use when naming rivals in the ChatGPT, Claude or Cursor stores, comparing who's gaining in a category, or for a weekly check or monitor. Not for a one-off chart lookup.
track-launch
Track an AI plugin from submission to live and after: how its wait compares with similar ChatGPT apps that went live, which ChatGPT countries list it, what gets apps like it delisted and whether delisted apps come back. Use when asking whether a review wait is normal, why an approved app isn't showing in a country, whether a just-launched app is at risk, or what to check after a delisting. Not for preparing a submission or answering a reviewer's reasons.
submit-plugin
Submit an AI plugin to the ChatGPT, Claude or Cursor stores: a store-ready kit with first-listing copy, assets, reviewer answers and the choices that can't change later, such as MCP origin, slug and countries. Use when preparing a plugin for submission, checking a repo is ready before uploading a plugin zip, asking how to get a plugin or MCP server listed in a store or connectors directory, or after a rejection.