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
frappe-builder
Frappe Builder website and page-building guidance for pages, blocks, components, forms, routing, CMS-style content, SEO, and web UX. Use when work touches Frappe Builder, website pages, landing pages, or content-driven experiences.
frappe-bench
Bench-aware Frappe operations guidance for app installs, branch switching, updates, migrations, site inspection, ports, and process state. Use when a task involves bench commands or local environment operations.
frappe-backend
Frappe backend guidance for Python and backend-adjacent JavaScript surfaces such as client interaction patterns, hooks, APIs, patches, scheduler logic, reports, and server-side review. Use when implementing or reviewing Frappe backend behavior.
rekall
Compact the current Codex VS Code extension thread through Rekall with a verified handoff and optional one-time continuation. Use on an explicit compaction request or after a substantial completed stage; standalone Codex CLI sessions are unsupported.
design-helper
Use when several visual variants need to be compared side by side — mockups, layouts, or a range of one value (spacing, radius, shadow, color, motion) — or when you are about to ask the user to pick between visual options in prose. Renders every candidate in one HTML file, opens it in a browser, lets the user choose by eye, then applies the choice to the code. Not a design generator — it lays out a range, it does not invent a look. Triggers on "5가지 버전으로 보여줘" · "A 랑 B 중에 뭐가 나아" · "시안 여러 개 비교해줘" · "나란히 놓고 보자". Do not use for ordinary UI coding, bug fixes, or implementing a design that is already decided.
codetruss
Operate CodeTruss local acceptance gates for coding-agent changes. Use when a developer asks to bind an agent task to allowed or denied files, configure repository verification, install or diagnose Claude Code or Codex hooks, review a working-tree or staged diff before commit, interpret or verify a signed CodeTruss receipt, repair a failed verdict, or explicitly opt into provider-backed review or receipt sync.
x-api
X/Twitter API integration for posting tweets, threads, reading timelines, search, and analytics. Covers OAuth auth patterns, rate limits, and platform-native content posting. Use when the user wants to interact with X programmatically.
workspace-surface-audit
Audit the active repo, MCP servers, plugins, connectors, env surfaces, and harness setup, then recommend the highest-value ECC-native skills, hooks, agents, and operator workflows. Use when the user wants help setting up Claude Code or understanding what capabilities are actually available in their environment.
workflow-forensics
对失败或卡住的团队工作流进行事后调查:时间线重建、角色交接审计、 产出缺失定位、重复循环检测和根因归类。 与 systematic-debugging(代码级调试)互补,本 skill 面向工作流级诊断。
wave-execution
基于依赖关系的波次并行执行策略,融合 GSD wave-execution 模式。 将任务按依赖图分组为有序波次,同一波次内的任务可安全并行, 增强现有 parallel-execution 技能的任务编排能力。
visa-doc-translate
Translate visa application documents (images) to English and create a bilingual PDF with original and translation
videodb
See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio, video), and create real time alerts for events from live streams or desktop capture.
video-editing
AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.
verification-loop
A comprehensive verification system for Claude Code sessions.
ui-ux-promax
最强 UI/UX 设计智能技能(源自 UI UX Pro Max,github.com/nextlevelbuilder/ui-ux-pro-max-skill)。 内置 67 种 UI 风格、161 个行业配色方案、57 套字体组合、161 条产品类型推理规则、99 条 UX 准则、 25 种图表类型,覆盖 15 种技术栈(React、Next.js、Vue、Svelte、SwiftUI、React Native、Flutter、 Tailwind、shadcn/ui、Angular、Laravel 等)。 触发关键词:设计页面、创建 UI 组件、选配色、选字体、响应式布局、无障碍审查、 动效设计、表单交互、落地页、dashboard、mobile app、UI review、build landing page、 design dashboard、create component、styling、glassmorphism、minimalism 等任何 UI/UX 请求。
ui-demo
Record polished UI demo videos using Playwright. Use when the user asks to create a demo, walkthrough, screen recording, or tutorial video of a web application. Produces WebM videos with visible cursor, natural pacing, and professional feel.
token-budget-advisor
Offers the user an informed choice about how much response depth to consume before answering. Use this skill when the user explicitly wants to control response length, depth, or token budget. TRIGGER when: "token budget", "token count", "token usage", "token limit", "response length", "answer depth", "short version", "brief answer", "detailed answer", "exhaustive answer", "respuesta corta vs larga", "cuántos tokens", "ahorrar tokens", "responde al 50%", "dame la versión corta", "quiero controlar cuánto usas", or clear variants where the user is explicitly asking to control answer size or depth. DO NOT TRIGGER when: user has already specified a level in the current session (maintain it), the request is clearly a one-word answer, or "token" refers to auth/session/payment tokens rather than response size.
testcontainers-integration-testing
提供基于 Testcontainers 的 Java 集成测试工作流,用于数据库、中间件和外部依赖的接近真实行为验证。 当任务涉及持久化、消息、缓存、对象存储或多依赖编排时使用。