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
clone-site
Clone any website from a URL into a pixel-faithful Next.js codebase — recon, asset/CSS extraction, parallel section builders, animation porting, and automated fidelity verification. Use whenever the user pastes a URL and asks to clone, copy, replicate, rebuild, reverse-engineer, or "make me a version of" a website or landing page — even if they don't say the word "clone". Also triggers on "/clone-site <url>". For multi-page sites it discovers and clones every page via the sitemap.
clipsmith
Plan and run a custom video-editing pipeline from a plain-language brief — clip, cut, trim, montage, reframe, or caption any footage. Use this whenever the user wants to edit or auto-clip video: make a highlight reel, a montage, a supercut, a beat-synced edit, a vertical/TikTok/Reels/Shorts clip, remove silences or dead air, do jump-cuts, add captions/subtitles, mix or duck music under footage, speed-ramp, or pull the best / most interesting moments out of one or more videos — even when they don't say "edit" and just say things like "turn these clips into something postable", "find the good bits", "make this shorter", or "cut me a reel". Composes ffmpeg with audio / scene / motion analysis, optional speech transcription, and the agent's OWN VISION for judging which moments are actually good. Not domain-specific — works on any footage (sports, vlogs, gameplay, talking-head, b-roll).
chatlog
Query the user's own WeChat (微信) history through the local chatlog HTTP API (http://127.0.0.1:5030). Use whenever the user wants to read, search, summarize, or export their WeChat messages, contacts, or group chats — e.g. "what did 张三 say last week", "summarize the 车队群 group today", "find messages about 练车", "看看我和某人的聊天记录", "export this chat to CSV", "who's in this 群". Resolves people/groups to a talker, then queries chatlog by time range. Personal, read-only data already decrypted on this machine.
chat-adapter-imessage
Connect the Vercel AI SDK to iMessage. Build AI agents and assistants that communicate over iMessage using chat-adapter-imessage, the official Photon adapter. Local mode (runs on your Mac) and remote mode (Photon's production infrastructure). Covers createiMessageAdapter, postMessage, editMessage, deleteMessage, react, startGatewayListener, types, and integration with the Chat SDK. Keywords: vercel ai sdk, imessage, chat adapter, ai agent, chatbot, conversational ai, messaging, apple messages, vercel, nextjs, ai assistant, chat sdk, real-time, macos.
burrow-system-tools
Diagnose and fix the user's Mac with Burrow's local MCP tools (burrow_doctor, burrow_snapshot, burrow_top_processes, burrow_process_usage, burrow_ports, burrow_analyze, burrow_disk_forecast, burrow_dupes, burrow_anomalies, burrow_agent_audit, burrow_clean, …). Use whenever the Mac is slow, hot, loud, low on disk, draining battery, or misbehaving; when the user asks what's using CPU/memory, what's listening on a port, what's eating disk space, where the duplicate or leftover files are, whether anything is behaving unusually, or what an agent already changed; AND proactively — if you notice a system problem mid-task (low disk, a runaway process, a port conflict), reach for these tools to diagnose and offer a fix without being asked. Requires Burrow's MCP server connected (burrow_* tools available).
buildspace-ci-cd
Configure and troubleshoot BuildSpace reusable GitHub Actions workflows and blocks for automated releases. Covers Rust, TypeScript (single package and monorepo), Go, Swift package, macOS .pkg (binary and payload-only), dylib (Xcode and Makefile), generic release, AI-based versioning/release notes, README freshness checks, skills documentation checks, labels, permissions, secrets, Homebrew tap updates, Jamf uploads, dry-run testing, and custom block composition. Use when users mention BuildSpace, release automation, reusable workflows, GitHub Actions CI/CD, or publishing to npm/crates/Homebrew/Jamf. Keywords: buildspace, ci/cd, github actions, release automation, reusable workflows, npm, crates, homebrew, rust, typescript, go, swift, monorepo, dylib, macOS, pkg, jamf, skills.
bro
Restate the last message in plain human language, with no jargon.
brandkit
Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional logo concepting, refined composition, sparse typography, strong symbolic meaning, premium mockups, art-directed imagery, and flexible grid layouts.
blast-radius
Find what a code, schema, API, config, or behavior change could break beyond its visible diff, then prove the safety-critical assumption with real code. Use whenever the user asks what could break, requests a blast-radius review, or distrusts a deceptively small change.
baseline-ui
Quickly deslop UI code by fixing spacing, hierarchy, typography, and small layout issues. Use when the interface needs a fast cleanup or polish pass.
awesome-design-md
A library of 74 real-brand DESIGN.md design systems (Stripe, Apple, Vercel, Linear, Notion, Spotify, Figma, and more). Use when the user wants UI that matches a known brand's design language, asks to "build a page that looks like <brand>", needs design tokens/typography/color rules for a recognizable product aesthetic, or mentions DESIGN.md. Each brand folder under references/ holds a self-contained DESIGN.md (colors, type, spacing, components) an agent reads to generate visually consistent UI.
app-store-preflight-compliance
Pre-submission compliance scanner workflow for Apple App Store apps. Use when reviewing iOS, macOS, tvOS, watchOS, or visionOS projects (Swift, Objective-C, React Native, Expo) for App Store rejection risks, submission readiness, privacy compliance, or guideline violations.
app-screenshots
Capture and curate screenshots of a GUI desktop app for a README, landing page, app-store listing, or docs. Use when the user wants to take or refresh app screenshots — especially after a UI/redesign change. The user "records" the app's flows once (driving the GUI) while the agent continuously screenshots; the agent then identifies each screen, dedupes, selects, compresses, and places the right shots for the target — automatically by convention, or to the user's specific request. Triggers: "take/update/refresh screenshots", "shoot the landing page / README", "screenshots for the app store", "capture the app's screens", "record the app for screenshots".
anthropic-skill-creator
Create, improve, and evaluate portable or Claude-oriented agent skills with Anthropic's skill-authoring workflow. Use when drafting or optimizing a non-Codex-system skill, running skill evals, benchmarking behavior, or improving trigger descriptions. Codex's product-managed `skill-creator` remains separate.
agents-sdk
Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, chat applications, voice agents, or browser automation. Covers Agent class, state management, callable RPC, Workflows, durable execution, queues, retries, observability, and React hooks. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
1-1-prep
Prepare for a 1:1 meeting with context from person file, meeting history, and shared projects
pmo-quality-release
Valid fixture skill description.
pmo-intake
暂无简介