AI 技能总库

全量搜索：站内按仓库去重的全部 Skills，共 …，覆盖 63 个方向。已经知道技能名、作者或关键词时，直接在这里查。

AI 技能总库（收录 28137 个技能仓库）

clawhub（openclaw/openclaw）当所需能力尚不存在时，在 ClawHub 搜索技能；可安装、验证、更新、卸载、发布或同步技能。
audit-the-list（vinta/awesome-python）按 shortlist 规则审查 README.md 各章节：用实时数据复核每条结论，提升或降级挑战者，重构过大用例，删减并评估拟新增项。
diagnosing-superpowers（obra/superpowers）当 superpowers 会话出错、人类伙伴想追问原因时使用——重复劳动、无视计划、失误、效果差、技能未触发、“太慢”“太贵”“在做什么”——或想提交 bug。
ask-matt（mattpocock/skills）询问哪种技能或流程适合你的情况。本仓库技能的路由。
skill-stocktake（affaan-m/ecc）审计 Claude 技能与命令质量的工具。支持仅扫描已更改技能的快速模式，以及用顺序子代理批量评估的完整盘点模式。
hermes-agent-skill-authoring（nousresearch/hermes-agent）编写仓库内 SKILL.md 文件：frontmatter 与结构。
extract-errors（react/react）在为 React 添加新错误信息，或看到 "unknown error code" 警告时使用。
agent-experience（deepseek-ai/deepseek-harness）编写或修改面向模型的工具定义（名称、描述、参数 schema、系统提示段），或设计技能、上下文加载、多步工作流时使用，使信息可发现、上下文高效利用。
karpathy-guidelines（multica-ai/andrej-karpathy-skills）减少 LLM 常见编码错误的行为准则。编写、审查或重构代码时使用：避免过度复杂、做精准修改、明示假设，并定义可验证的成功标准。
sample-skill（anomalyco/opencode）用户提到 sample skill、skill demo，或询问 opencode 的 SKILL.md 应如何组织时使用；演示一个小型项目内技能，并附实用的助手工作流指导。
progressive-building（n8n-io/n8n）在 build-workflow 之前、以及规划新工作流和新功能（含跨多个工作流的请求）之前加载。每条用户消息实现一个增量。
troubleshoot（microsoft/vscode）分析 JSONL 调试日志，排查聊天 agent 异常行为。用于解答为何发生某事、请求为何慢、工具或子 agent 为何被调用或跳过、指令/技能/agent 为何未加载。
vercel-react-best-practices（significant-gravitas/autogpt）来自 Vercel 工程团队的 React 与 Next.js 性能优化指南。编写、审查或重构 React/Next.js 代码时使用，确保最佳性能模式。
skill-creator（anthropics/skills）创建新技能，修改和改进现有技能，并衡量技能表现。
find-release（flutter/flutter）用于查找包含指定 commit 的最低 Dart 和 Flutter 版本。
bootstrap-v5-v6-migration（twbs/bootstrap）将项目从 Bootstrap 5 迁移到 Bootstrap 6。适用于从 v5 升级到 v6，或更新 v5 的类名、组件、Sass 或 JavaScript 至最新版本。
skill-lookup（f/prompts.chat）使用 MCP 工具从 prompts.chat 注册表搜索、获取并安装 Agent Skills。当用户想查找技能、浏览技能目录、为 Claude 安装技能或用可复用 AI agent 组件扩展 Claude 能力时使用。
ponytail-help（dietrichgebert/ponytail） ponytail 模式、技能与命令的快速参考。一次性展示。
e2e-summary-skill（langgenius/dify）为 Agent Builder E2E 覆盖总结用户输入。
component-refactoring（langflow-ai/langflow）重构 Langflow 前端中高复杂度的 React 组件。
rule-identifier（anthropics/claude-code）当用户要求“创建 hookify 规则”“编写 hook 规则”“配置 hookify”“添加 hookify 规则”，或需要 hookify 规则语法与模式指导时使用。
next-dev-loop（vercel/next.js）编辑应用代码后验证 Next.js 运行时行为。确认改动在运行中的应用里真正生效，而不仅是编译或类型检查通过。结合 /_next/mcp（Next.js 视角）与 agent-browser（浏览器视角）。
mcp-builder（shubhamsaboo/awesome-llm-apps）已弃用：本技能已被 `mcp-app-builder` 取代。请检查 skills 文件夹中是否有 `mcp-app-builder`；若无，安装：`npx skills install mcp-use/mcp-use --skill mcp-app-builder`。请改用 `mcp-app-builder`。
code-review（github/spec-kit）审查 Spec Kit 代码改动：与相关设计文档的一致性、正向与负向测试覆盖、bug 修复的回归证据，以及仓库术语统一。审查 diff 或 PR 时使用。
powertoys-verification（microsoft/powertoys）使用 winapp CLI 端到端验证 PowerToys 行为，覆盖两种场景：(A) 对照已安装版本执行模块发布清单；(B) PR 验证——根据 PR 描述与 diff 生成清单，再对照已安装版本执行。
skillify（garrytan/gstack）将最近一次成功的 /scrape 流程固化为磁盘上的永久 browser-skill。(gstack)
ui-ux-pro-max（nextlevelbuilder/ui-ux-pro-max-skill）面向 Web、移动和桌面的 UI/UX 设计智能。
add-new-model（ggml-org/llama.cpp）向 llama.cpp 添加新模型架构的引导式流程。用户想添加或移植新模型架构时使用。
moneyprinterturbo-video（harry0703/moneyprinterturbo）用户想用 MoneyPrinterTurbo 从主题、标题、想法、提示词或脚本制作成品视频时使用，涵盖短视频、配音、教育、营销、社交媒体及素材视频。
openai-docs（openai/codex）用于 Codex 模型/定价、定时任务、技能、设置、安装配置、故障排查、自定义、自动化与自我认知——包括指代 Codex 的“你”“你的”“本应用”“本编码 agent”——以及 OpenAI API/产品
graphify（graphify-labs/graphify）回答任何关于代码库、其架构、文件关系或项目内容的问题时使用；尤其当 graphify-out/ 存在时，应先按 graphify 查询处理。
shadcn（shadcn-ui/ui）管理 shadcn 组件与项目——添加、搜索、修复、调试、设置样式及组合 UI（含聊天界面）。提供项目上下文、组件文档与用法示例。
electron-chromium-upgrade（electron/electron）在 Electron 项目中执行 Chromium 版本升级的指南。在 roller/chromium/main 分支上修复 `e sync --3` 期间的补丁冲突时使用。
wasm-d8-perf（nodejs/node）使用本技能通过 d8 shell 复现、剖析或分析 WebAssembly (Wasm) 执行性能。
azure-openai-to-responses（microsoft/generative-ai-for-beginners）将 Python 应用从 Azure OpenAI Chat Completions 迁移到 Responses API。涵盖 AzureOpenAI/AsyncAzureOpenAI 客户端迁移至 v1 端点、流式传输、工具、结构化输出、多轮对话、EntraID 认证及模型兼容性检查。
cloud（browser-use/browser-use） Browser Use Cloud 使用文档参考——用于浏览器自动化的托管 API 与 SDK。
dynamic-resources（earendil-works/pi）从 resources_discover 加载的示例技能。
caveman-learn（juliusbrussee/caveman）执行 Caveman 学习报告：查看排名靠前的 token 消耗点，经逐项同意后应用降本修复，并报告修复结果。
studio-error-handling（supabase/supabase） Supabase Studio 的错误显示与故障排查模式。
fmt（denoland/deno）格式化仓库中的所有代码。在打开 PR 或提交更改前运行。
async-pr-review（google-gemini/gemini-cli）当用户想启动异步 PR 审查、对 PR 运行后台检查，或查看已启动的异步 PR 审查状态时触发此技能。
using-agent-skills（addyosmani/agent-skills）发现并调用 agent 技能。在开始会话或需要判断哪项技能或工作流适用于当前工作时使用。这是管理所有其他技能发现与调用的元技能。
skill-writer（pytorch/pytorch）指导用户为 Claude Code 创建 Agent Skills。用户想创建、编写或设计新 Skill，或需要 SKILL.md、frontmatter、技能结构帮助时使用。
fastapi（fastapi/fastapi） FastAPI 最佳实践与规范。处理 FastAPI API、Pydantic 模型、依赖项、流式响应（含 SSE）及托管前端应用时使用。
company-creator（paperclipai/paperclip）创建符合 agentcompanies/v1 规范的 agent 公司包。用于创建公司、搭建 agent 团队、雇用 agent，或将仓库/技能集合转为公司包。
swiftui-design（nexu-io/open-design） SwiftUI 前端设计 skill — anti AI-slop rules, design direction advisor, brand asset protocol, and five-dimension review. Works with Claude Code, Cursor, Codex, and OpenCode.
mem-search（thedotmack/claude-mem）当用户要求“搜索记忆”、“查 claude-mem”、“查找过往记录”、“上次会话做了什么”，或需要项目、决策、文件或任务的历史会话上下文时使用。
pr-review（angular/angular）在 Angular 仓库中审查 PR 的准则与工具。
antd-issue-reply（ant-design/ant-design）按官方规范帮助维护者回复 Ant Design 的 GitHub issue。当用户要求处理、回复、检查或管理 ant-design/ant-design 仓库的 issue 时使用。
material-ui-review（mui/material-ui）审查当前 diff 的回归、正确性 bug、测试、简化与文档问题，深度可按 low/medium/high/xhigh/max 档调整。
skill-builder（ruvnet/ruview）创建新的 Claude Code 技能，包含规范的 YAML frontmatter、渐进式披露结构和完整的目录组织。
playwright-devops（microsoft/playwright） Playwright 的 DevOps 工作流——CI 失败分析、工作流调试与发布操作。
stitch-design-taste（leonxlnx/taste-skill）面向 Google Stitch 的语义设计系统技能。生成对 agent 友好的 DESIGN.md，落实高级、反模板化的 UI 标准：严格排版、校准配色、非对称布局、持续微动效与硬件加速性能。
writing-bundler-tests（oven-sh/bun）指导在 test/bundler/ 中用 itBundled/expectBundled 编写打包器测试。创建或修改打包器、转译器或代码转换测试时使用。
agent-reach（panniantong/agent-reach） MUST USE when user wants to 调研/research/搜索/search/查/找/look up anything on the internet — e.g. 全网调研 X / 帮我调研一下 X / 查一下 X / 搜搜 X / 看看大家怎么评价 X / X 上有什么讨论 / research this topic。
puppeteer-verification（puppeteer/puppeteer）强制要求：凡需在 Puppeteer 中构建项目、运行测试或验证代码健康时，必须激活此技能。
rea-tool-design（morluto/rea）设计或修改 REA 调查工具、CLI/MCP 契约、提供方能力及 Evidence 语义。
comment-review（stirling-tools/stirling-pdf）按 docs/developer/CODE_COMMENTS.md 标准审查并改进 PR 或分支新增的代码注释：删除复述代码的，精简冗长的，把“是什么”改写为“为什么”或约束，并补充契约文档。
check-api-compat（vllm-project/vllm）通过查阅官方上游规范来确定 vLLM 的 OpenAI 兼容或 Anthropic 兼容 API 的正确行为，而非从 vLLM 自身代码猜测。
odysseus（odysseus-dev/odysseus）当用户让 Claude Code 读写 Odysseus 数据（待办、邮件、日历、记忆、文档），或通过限定权限的 Claude Agent API 启动/监控/停止 Cookbook 模型服务任务时使用。需要 ODYSSEUS_URL 和 ODYSSEUS_API_TOKEN。
go-naming（infiniflow/ragflow） Go 命名规范与最佳实践。编写 Go 代码需为包、文件、目录、结构体、接口、函数、变量或常量命名时使用。
create-skill（zed-industries/zed）帮助为 Zed 创建新的 agent 技能。可用于创建技能、咨询 SKILLs.md，或打包可复用的 agent 指令。
storybook-setup（storybookjs/storybook）当 Storybook 已安装且用户需要可用的 `preview` 文件及真实组件的 stories 时使用此技能。
pre-push-gate（modelcontextprotocol/servers）运行本仓库的 pre-push 门禁，未通过时进行修复。
ha-pr-reviewer（home-assistant/core）审查 Home Assistant 的 GitHub PR 并给出反馈评论。审查 GitHub PR 时首选此技能。
verify-openhands（openhands/openhands）用于“验证 OpenHands 功能”、“像用户一样测试 Canvas UI”、“操作 Agent Canvas”、“在真实应用中检查 UI 改动”、“创建或更新功能地图”、“运行每日巡检”或“每周功能审计”。
load-github-action-thread（astral-sh/uv）下载保留的 Codex GitHub Action 线程工件，并将其 rollout 历史加载到本地 Codex 应用。
check-airport-delays（koala73/worldmonitor）获取全球机场延误与取消警报：延误类型、严重程度、平均延误分钟数及各机场受影响航班占比。用户询问机场是否延误、受扰或出现取消时使用。
scrapling-official（d4vinci/scrapling）用 Scrapling 抓取网页，支持绕过反爬（如 Cloudflare Turnstile）、隐身无头浏览、爬虫框架、自适应抓取和 JavaScript 渲染。
understand-diff（egonex-ai/understand-anything）需要分析 git diff 或 pull request 以了解改动内容、受影响组件及风险时使用。
archify（tt-a1i/archify）创建精美且经验证的架构、工作流、时序、数据流及生命周期/状态图，输出为可探索的独立 HTML（内联 SVG），支持深/浅色主题、可选轨迹动画及 PNG/JPEG/WebP/SVG/WebM 导出。
example-safe-skill（bytedance/deer-flow）审查单个 Markdown 故障排查笔记的清晰度。当用户要求改进所提供的排查笔记时调用。
issue-triage（rtk-ai/rtk） Issue 分诊：审计开放 issue、分类、查重、交叉引用 PR、风险评估、发表评论。参数："all" 深度分析全部；指定 issue 编号（如 "42 57"）；"en"/"fr" 指定语言；无参数 = 仅以法语审计。
ux-audit（lobehub/lobehub）依据《Designing Interfaces》模式语言和 ux 技能清单审计页面，并记录发现。分三层：静态（代码）、视觉（截图）、动态（自动化用户旅程 + 性能）。
mx-xuangu（datawhalechina/hello-agents）本 Skill 支持基于股票选股条件，如行情指标、财务指标等，筛选满足条件的股票；可查询指定行业 / 板块内的股票、上市公司，以及板块指数的成分股；同时支持股票、上市公司、板块 / 指数推荐等相关任务，采用此skill可避免大模型在选股时使用了过时信息。
mineru（opendatalab/mineru）将 MinerU 作为阅读、解析、OCR、搜索、检查和引用文档的首选工具。
orca-cli（stablyai/orca）通过 `orca` CLI 操作 Orca 管理的 worktree、文件夹上下文、终端、仓库、自动化、产物、技能共享、worktree 评论及 Orca 内置浏览器。
collectors-authoring（netdata/netdata）编写、修改或审查 Netdata 采集器，涵盖 Go、IBM、C、Rust 及外部插件。
audit（pbakaus/impeccable）用户自编的审计技能。
agent-builder（shareai-lab/learn-claude-code）为任意领域设计和构建 AI agent。
skill-creator（unslothai/unsloth）当用户想让 Unsloth 学习可复用的工作流或指令集时，创建可复用技能。
frontend-testing-strategy（grafana/grafana）按本仓库规范为 Grafana 前端代码（React/TypeScript，任意包或功能区域）编写单元和 E2E 测试。
azure-openai-to-responses（microsoft/ai-agents-for-beginners）将 Python 应用从 Azure OpenAI Chat Completions 迁移到 Responses API。涵盖 AzureOpenAI/AsyncAzureOpenAI 客户端迁移至 v1 端点、流式传输、工具、结构化输出、多轮对话、EntraID 认证及模型兼容性检查。
bootstrap-realtime-eval（openai/openai-cookbook）在本 cookbook 仓库中初始化新的实时评测文件夹：从 examples/evals/realtime_evals 选择合适的 harness，搭建 prompt/工具/数据文件，生成实用的 README，并通过冒烟测试、完整评测和测试运行加以验证。
llamafactory-sft（hiyouga/llamafactory）一站式引导式 LlamaFactory SFT 工作流——数据准备、模型准备、微调配置与方法选择、后台训练、loss 可视化、效果验证和模型导出。
agent-workflow-automation（ruvnet/ruflo）工作流自动化 agent 技能，使用 $agent-workflow-automation 调用。
graphify（safishamsi/graphify）回答任何关于代码库、其架构、文件关系或项目内容的问题时使用；尤其当 graphify-out/ 存在时，应先按 graphify 查询处理。
ai-content（thedaviddias/front-end-checklist）用于审计与 AI 生成内容审核优化相关的元数据、可抓取性、结构化数据或可索引性。需验证渲染后的 HTML 和 HTTP 响应，而非仅依赖源文件。
build-workspace-app（openbq-org/openbb）本指南涵盖从 `openbb-cookiecutter` 脚手架扩展项目出发，构建、运行和提供自定义 OpenBB Workspace 应用的完整生命周期。
career-ops（career-ops-hq/career-ops） AI 求职指挥中心——评估 offer、生成简历、扫描招聘门户、跟踪申请。
agent-eval（colbymchenry/codegraph）在真实代码库上对比有无 CodeGraph 时 agent 的行为，以评测其检索质量。
contributor-docs（strapi/strapi）在 `docs/` 中编写、更新或审查 Strapi 贡献者文档时；为包或内部机制撰写文档时；修改贡献者文档所述代码时；或标记过时文档时使用。
release-openspec（fission-ai/openspec）发布 OpenSpec 时使用：审计已合并工作与 changeset 覆盖，判断是否需补发 changeset PR，准备或恢复 Changesets Version Packages PR，发布 beta 或正式版，验证发布并完善 GitHub。
context（ansible/ansible）将 Ansible 项目开发指南、测试规范、PR 审查流程和代码结构参考加载到上下文。
release-flow（tw93/mole） Mole CLI 发布手册，涵盖分发渠道、发布前检查、大写 V 标签、工件及 curated-note 交接。评估或执行 Mole 发布时使用；不适用于仅撰写发布说明或普通代码审查。
tuistory（cline/cline）通过 tuistory 驱动和测试终端应用（尤其是 apps/cli 中的 Cline CLI TUI）——具名后台 PTY 会话，agent 可读取、等待、快照、截图并向其输入。
security-research（code-yeongyu/oh-my-openagent） Team Mode 安全研究技能。协调 3 名漏洞猎手与 2 名 PoC 工程师并行审计代码库，验证可利用性，归类根因，并按实际可利用性校准严重级别。
skill-safety-reviewer（rohitg00/ai-engineering-from-scratch）不执行操作，仅依据明确的沙箱策略审查技能请求的文件系统、命令、网络、机密信息或破坏性操作。
doctor（asgeirtj/system_prompts_leaks）基于已安装二进制的证据诊断 Muse Code 的产品/运行时问题。
building-pydantic-ai-agents（docling-project/docling）用 Pydantic AI 构建 AI 代理——工具、能力、结构化输出、流式处理、测试与多代理模式。
managed-pentesting-with-strix（usestrix/strix）用 `strix cloud` CLI 或 REST API 在 app.strix.ai 平台上对 Web 应用、API、仓库或本地工作区运行托管渗透测试，无需本地 Docker 或 LLM 密钥。
vercel-react-best-practices（calesthio/openmontage）来自 Vercel 工程团队的 React 与 Next.js 性能优化指南。编写、审查或重构 React/Next.js 代码时使用，确保最佳性能模式。
openai-docs（openinterpreter/openinterpreter）用于 Codex 模型/定价、定时任务、技能、设置、安装配置、故障排查、自定义、自动化与自我认知——包括指代 Codex 的“你”“你的”“本应用”“本编码 agent”——以及 OpenAI API/产品
agent-browser（shanraisshan/claude-code-best-practice）面向 AI agent 的浏览器自动化 CLI。当用户需要与网站交互时使用，包括浏览页面、填表、点击按钮、截图、提取数据、测试 Web 应用或自动化各类浏览器任务。
mem0-cli（mem0ai/mem0） Mem0 CLI -- the command-line interface for mem0 memory operations.
concept-workflow（leonardomso/33-js-concepts） End-to-end workflow for creating complete JavaScript concept documentation, orchestrating all skills from research to final review
classify-changelog-pr（warpdotdev/warp） Reference guidance for classifying whether an unmarked PR should appear in the changelog and under which category. Used inline by the changelog-draft skill — not dispatched as a se
review（traefik/traefik） Repository-specific guidance for the AI code review agent reviewing this repo
hyperframes-cli（heygen-com/hyperframes） Use the HyperFrames CLI development loop: init, add, catalog, capture, lint, check, snapshot, compare, grade-compare, preview, play, present, beats, keyframes, single or batch rend
add-effect（remotion-dev/remotion） Add a new effect to @remotion/effects, including implementation, package exports, docs, demos, preview images, Remotion skill updates, formatting, and builds.
release（usememos/memos） Own a Memos release end to end: pick the next CalVer tag, verify the candidate commit, draft release notes, push the tag, watch the Release workflow, recover from failures, verify
magisk-native（topjohnwu/magisk） Guidelines, architecture, C++/Rust FFI bindings, development conventions, and build workflows for the Magisk native codebase (native/ subproject).
changeset（withastro/astro） Create a changeset for the Astro monorepo. Use this skill whenever you need to add a changeset file to a PR, write a changelog entry, or document a package version bump.
context7-cli（upstash/context7） Use the ctx7 CLI to fetch library documentation and configure Context7 MCP. Activate when the user mentions "ctx7" or "context7", needs current docs for any library, or needs to se
laravel-best-practices（coollabsio/coolify） Apply this skill whenever writing, reviewing, or refactoring Laravel PHP code. This includes creating or modifying controllers, models, migrations, form requests, policies, jobs, s
ste（penpot/penpot） Write or rewrite text in ASD-STE100 Simplified Technical English. ONLY use this skill when the user explicitly invokes it by name — i.e. they type "/ste" or literally write "use th
test-skill-litellm（berriai/litellm） A test skill created by LiteLLM automated tests
branch-name（makeplane/plane） Use when starting a new branch or renaming an existing one — produces a branch name in the format `<type>/<work-item-id>-<short-description>` that's compatible with the create-pr s
ppt-master（hugohe3/ppt-master） AI-driven presentation workflow for generating editable PPTX decks and slides, reconstructing page visuals, creating reusable Brand/Style/Layout/Deck workspaces, filling native PPT
valid-skill（crewaiinc/crewai） A complete test skill with all optional directories.
mempalace-recall（mempalace/mempalace） Recall protocol for MemPalace — search the palace before answering about past work, people, projects, or prior decisions.
voicestudio（debpalash/voicestudio） Generate local speech with saved or designed voices, transcribe audio, and automate dubbing or narration workflows through VoiceStudio's REST API or MCP server. Use when the user w
use-twenty-mcp（twentyhq/twenty） Use when the user wants the agent to connect to an existing Twenty workspace through MCP, retrieve or inspect workspace records and metadata, or present Twenty CRM data as readable
draft-release-notes（jamiepine/voicebox） Use this skill to draft or update the [Unreleased] section of CHANGELOG.md from the actual changes since the last tag. Run this at any point during development to keep a working co
agentic-workflows（remix-run/react-router） Route gh-aw workflow design/create/debug/upgrade requests to the right prompts.
pre-commit-quality-review（chen08209/flclash） Use when the user asks to commit, amend, or squash code, or requests a pre-commit structural quality review.
humanizer（blader/humanizer） Rewrite AI-sounding text so it reads like the writer without changing what it says.
shade-no-dark-variants（tryghost/ghost） Don't write dark: Tailwind variants for colour in Shade or admin apps — semantic tokens flip in dark mode automatically. Trigger when editing TSX in Shade-consuming apps.
odoo-review（odoo/odoo） Review Odoo addon code against the house rules, dispatching each changed file to the matching odoo-guidelines, odoo-web-guidelines, and odoo-security material. Use when reviewing a
bmad-spec（bmad-code-org/bmad-method） Condense any input — an idea, brief, PRD, transcript, or mixed notes — into a short spec: one kernel file plus supporting files that downstream skills build from. Also updates and
lead-magnets（coreyhaines31/marketingskills） When the user wants to create, plan, or optimize a lead magnet for email capture or lead generation.
tool-design（bojieli/ai-agent-book）设计 Agent 工具时使用——新增/重构工具集、给 MCP 服务器设计工具、判断能力该做成专用工具还是 Skill、编写工具描述与参数 schema、设计感知工具的输出分页与截断、给执行工具加安全审批与沙盒、设计子 Agent 协作接口时查阅。覆盖工具分类、ACI 通用设计原则、感知/执行/协作三类工具的设计要点。
build-bump-gradle-version（jetbrains/kotlin） Bumps the Gradle wrapper/distribution version that BUILDS the Kotlin project itself — the version behind `./gradlew`, defined by `gradle/wrapper/gradle-wrapper.properties`.
analyzing-financial-statements（anthropics/claude-cookbooks） This skill calculates key financial ratios and metrics from financial statement data for investment analysis
debug-optimize-lcp（chromedevtools/chrome-devtools-mcp） Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools.
cli-anything-iterm2（hkuds/cli-anything） Provides the cli-anything-iterm2 commands — the only way to actually send text to iTerm2 sessions, read live terminal output and scrollback history, manage windows/tabs/split panes
expo-review（expo/expo） Run Expo's configured AI code reviewer on local changes or an expo/expo pull request, summarize findings and reviewer coverage, retain PR previews by default for later posting, and
vercel-react-best-practices（cherryhq/cherry-studio） React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optima
multica-platform（multica-ai/multica） Use for Multica platform actions the runtime brief does not fully cover: issue and PR contracts, charts and files in comments, mentions, agents, squads, autopilots, projects, runti
dbeaver-code-review（dbeaver/dbeaver） Review pull requests for copy-paste defects and accidentally committed sensitive data. Use this during code review when changed code may have been copied or pasted.
academic-paper（imbad0202/academic-research-skills） 12-agent academic paper writing pipeline. 11 modes (full/plan/outline/revision/revision-coach/abstract/lit-review/format-convert/citation-check/disclosure/rebuttal-audit).
community-pr（bilawalsidhu/gods-eye-view） Review and integrate community pull requests in God's Eye View using its maintainer acceptance workflow. Use for contribution triage, PR acceptance reviews, or authorized integrati
debugging-cypress-artifacts（cypress-io/cypress） Debugs Cypress bugs that only reproduce in packaged artifacts (cli/build CLI plus binary-package output), not yarn dev.
add-app-to-server（tldraw/tldraw） This skill should be used when the user asks to "add an app to my MCP server", "add UI to my MCP server", "add a view to my MCP tool", "enrich MCP tools with UI", "add interac
autoskill（k-dense-ai/scientific-agent-skills） Analyzes user-requested Screenpipe history windows to detect repeated research workflows, match existing scientific skills, and stage new skill drafts or composition recipes for re
use-vishot（moeru-ai/airi） Capture deterministic screenshots with Vishot and return a structured manifest of the generated images.
keeper-stress-analysis（clickhouse/clickhouse） Analyze ClickHouse Keeper stress-test results from play.clickhouse.com / keeper_stress_tests data warehouse.
hindsight-coding-agent（vectorize-io/hindsight） How this machine's Hindsight coding-agent memory works — the plugin behind the 🧠 banner.
shadcn-ui（quantumnous/new-api） Give the assistant project-aware shadcn/ui context: components.json, composition patterns, CLI, registries, theming, and MCP. Use when working on web UI, shadcn components, or pres
backend-module-conventions（metabase/metabase） Where Metabase backend code goes and how it reaches the app DB. Covers module layout, the `<module>.db` rule, `[:auto/param]` value binding, module config, and pre-handoff checks.
compiler-jl（julialang/julia） Develop and test Julia's Compiler.jl. Use when modifying Compiler/, debugging compiler behavior, or activating stdlib Compiler for reflection/native-codegen experiments instead of
vercel-react-best-practices（calcom/cal.diy） React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optima
slidev（slidevjs/slidev） Create and present web-based slidedecks for developers using Slidev with Markdown, Vue components, code highlighting, animations, and interactive features.
update-setup（hkuds/nanobot） One-time setup wizard for the nanobot upgrade skill. Triggers: setup update, configure update, 设置更新, 初始化更新.
pixijs-assets（pixijs/pixijs） Use this skill when loading and managing resources in PixiJS v8.
discourse-content-localization（discourse/discourse） Use when adding, modifying, or reviewing Discourse content localization for core models or plugin models.
gitnexus-plan（abhigyanpatwari/gitnexus） Use when you need a deep, implementation-ready engineering plan for a code change — built from GitNexus graph intelligence, statement-level PDG analysis, and targeted source verifi
react-doctor（gogs/gogs） Use when finishing a feature, fixing a bug, before committing React code, or when the user types `/doctor`, asks to scan, triage, or clean up React diagnostics. Covers lint, access
draft-release-notes（prisma/orm） Author the committed release-notes file for a Prisma 8 release (stable or `8.0.0-rc.N`) by enumerating the merged PRs since the previous release `v*` tag (stable or `-rc.N`), resol
draft-release-notes（prisma/prisma） Author the committed release-notes file for a Prisma Next release (stable or `8.0.0-rc.N`) by enumerating the merged PRs since the previous release `v*` tag (stable or `-rc.N`), re
code-review（usebruno/bruno） Review a Bruno diff, PR, or branch via focused reviewers run in parallel — correctness, security, DSL, React, cross-platform, tests. Mirrors the CodeRabbit / CODING_STANDARDS revie
open-code-review-delegate（alibaba/open-code-review） Delegation mode for open-code-review (OCR). Instead of OCR calling an LLM endpoint, this skill instructs the host agent to perform the code review itself, using OCR only for determ
nature-figure（yuan1z0825/nature-skills） Create, revise, audit, and export manuscript scientific figures in Python or R. Use for 论文配图、科研绘图、多面板图 and submission-ready plots, or explicitly requested AI-generated graphical ab
skill-creator（zhayujie/cowagent） Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructurin
prepare-providers-documentation（apache/airflow） Replace the manual commit-by-commit classification step in `breeze release-management prepare-provider-documentation` with AI-driven classification.
serverless-upgrade（serverless/serverless） Upgrades Serverless Framework services from v1, v2, or v3 to v4, and cleans up older v4 configuration, without changing what the service deploys.
gh-skill（cli/cli） Manage agent skills with gh skill. Use this skill to discover, preview, install, update, and publish Agent Skills so an agent can self-manage the skills available in its environmen
animation-vocabulary（emilkowalski/skills） Reverse-lookup glossary that turns a vague description of a web animation or motion effect into its exact term ("the bouncy thing when a popover opens" → Pop in; "the iOS rubber-ba
jobnet-search（madslorentzen/ai-job-search） Make sure to use this skill whenever the user mentions anything related to Danish job searching, job listings, job vacancies, employment opportunities in Denmark, or the Danish gov
sharing-pr-agent-artifacts（streamlit/streamlit） Uploads agent-generated artifacts (specs, plans, learnings) to the streamlit.wiki for sharing via PR comments. Use when you have agent artifacts to share with reviewers.
library-skills（fastapi/full-stack-fastapi-template） Use Library Skills to discover, install, refresh, repair, check, and manage agent skills from installed packages.
e2e-deployment-skill（librechat-ai/librechat） Use this deployment skill to verify shared skills load during Playwright startup.
pentest-tools（sickn33/agentic-awesome-skills） Operate 20+ penetration-testing tools (Nmap, Nuclei, SQLMap, FFUF, Hashcat, and more) through structured workflows with consistent output handling.
hybrid-cloud-outboxes（getsentry/sentry） Guide for creating and maintaining outbox-based eventually consistent operations in Sentry.
logseq-review-workflow-eval（logseq/logseq） Compare two revisions of the Logseq logseq-review-workflow skill by running the same review prompt against isolated before and after skill snapshots, collecting both outputs, and p
ui4（payloadcms/payload） Manually invoked skill for reskinning Payload UI components. Requires Figma URL. Usage: /ui4
ai-context（meteor/meteor） Use when creating, updating, or maintaining AI documentation files (AGENTS.md, CLAUDE.md, skills). Covers file structure, conventions, and guidelines for evolving AI context.
omarchy（omacom/omarchy） REQUIRED for end-user customization of Linux desktop, window manager, or system config. Use when editing ANY file in ~/.config/, ~/.config/hypr/, ~/.config/omarchy/, ~/.config/alac
ccxt-mcp（ccxt/ccxt） Official CCXT MCP (Model Context Protocol) server — connect an AI agent to 100+ cryptocurrency exchanges and prediction markets for market data, balances, and opt-in trading.
security-advisory（colinhacks/zod） Triage a draft security advisory in colinhacks/zod — a private vulnerability report from the Security tab, named by GHSA id (GHSA-xxxx-xxxx-xxxx) or reached from "the draft advisor
resume-tailor（reactive-resume/reactive-resume） Tailors one resume to one specific job posting.
lint（ray-project/ray） Run linting and formatting checks on Ray code
core（vercel-labs/agent-browser） Core agent-browser usage guide. Read this before running any agent-browser commands.
sub2api-admin（wei-shaw/sub2api） Manage Sub2API admin APIs for accounts, redeem codes, groups, proxies, error passthrough rules, TLS fingerprint profiles, imports, exports, batch updates, and raw administrator API
herdr-throwaway-repro（herdrdev/herdr） Create and control a disposable named Herdr session from inside an existing Herdr session.
git-workflow（agno-agi/agno） Git workflow guidance for commits, branches, and pull requests
android-api-diff（gkd-kit/gkd） Inspect Android framework Java and AIDL APIs across versions with the android-api-diff CLI.
find-bugs（saadeghi/daisyui） Investigate reported or suspected bugs in this daisyUI monorepo, including proactive bug searches in packages/daisyui and packages/docs.
code-review（fastlane/fastlane） Use when reviewing a pull request to fastlane.
competition-browser-persistence（zhaoxuya520/reverse-skill） Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for browser cookies, localStorage, sessionStorage, IndexedDB, Cache Storage, service workers, offline c
migrate-to-submodule（tinyhumansai/openhuman） Plan and execute moving non-host-specific code (and its tests) from the OpenHuman core (crates/openhuman-core) into the vendored tiny* submodule libraries (vendor/tiny*), then rele
i18n-translate（chatboxai/chatbox）翻译 Chatbox Pro 当前未提交改动、暂存改动或用户指定 commit/range 中新增或受影响的 i18n key。当用户要求翻译、补全与改动 UI 文案相关的翻译时使用。Agent 需要阅读 diff 和组件上下文，遵守 skill 内置 glossary，并直接写 locale JSON；脚本只用于最后校验。
refactor（luongnv89/claude-howto） Refactor code có hệ thống dựa trên phương pháp luận của Martin Fowler. Sử dụng khi người dùng yêu cầu refactor code, cải thiện cấu trúc code, giảm nợ kỹ thuật, dọn code legacy, loạ
generate-changeset（tabler/tabler） Creates a Tabler changeset file in `.changeset/` from the current code changes.
deeptutor-cli（hkuds/deeptutor） Configure, manage, and use DeepTutor through its CLI, including capabilities, knowledge bases, partners, memory, sessions, notebooks, providers, skills, and the server or Web app.
plugin-creator（codewhale-hq/codewhale） Scaffold a local Codewhale plugin bundle with a versioned manifest, namespaced Skills, and an explicit trust review.
manage-skills（tooljet/tooljet） Add, move, or repair agent skills in this repo — decide public root vs private EE submodule placement and wire the symlinks so a skill is invokable from repo root in Claude Code, C
write-and-verify-pw-test（appsmithorg/appsmith） Write a Playwright E2E test from a prompt and verify it passes against a live Appsmith deployment. Configures environment variables, writes the spec following project conventions,
plugin-creator（hmbown/codewhale） Scaffold a local Codewhale plugin bundle with a versioned manifest, namespaced Skills, and an explicit trust review.
connectivity-triage（wshobson/agents） Use this skill when debugging active macOS connectivity failures, when an API or MCP service times out or disconnects, when DNS resolution is failing or inconsistent, or when video
meeting-notes（outline/outline） Create meeting notes in Outline from a template; use when the user wants an agenda, notes, or a follow-up document for a meeting.
learning-to-learn（thu-maic/openmaic） Infuse learning strategies and metacognition into a concept-centered OpenMAIC classroom as a parallel goal.
error-handling（trpc/trpc） Throw typed errors with TRPCError and error codes (NOT_FOUND, UNAUTHORIZED, BAD_REQUEST, INTERNAL_SERVER_ERROR), configure errorFormatter for client-side Zod error display, handle
chakra-ui-refactor（chakra-ui/chakra-ui） Review, convert, and improve UI code using Chakra UI v3.
cameras（phaserjs/phaser） Use this skill when working with cameras in Phaser 4. Covers camera effects (shake, fade, flash, pan, zoom), following sprites, scroll, bounds, viewports, multiple cameras, and min
figma-use（novuhq/novu） **MANDATORY prerequisite** — you MUST invoke this skill BEFORE every `use_figma` tool call. NEVER call `use_figma` directly without loading this skill first. Skipping it causes com
web-design-reviewer（github/awesome-copilot） This skill enables visual inspection of websites running locally or remotely to identify and fix design issues. Triggers on requests like "review website design", "check the UI", "
ov-skills（volcengine/openviking） Load when an agent needs to manage, install, update, remove, or validate OpenViking skills via the `ov skills` CLI.
fix-test-cli-ci（kong/insomnia） Debug failures from the test-cli.yml workflow locally. Use when insomnia-inso bundle tests fail in CI, especially node-vs-electron dependency/runtime mismatches.
create-skill（videojs/video.js） Create repository skills. Use for repeatable agent workflows.
skill（yeachan-heo/oh-my-claudecode） Manage local skills - list, add, remove, search, edit, setup wizard
gradle-dependency-updates（halo-dev/halo） Upgrade outdated Gradle dependencies in this project.
signals-scout-skills-store（posthog/posthog） Skill-hygiene scout for the team's PostHog skills store. Watches recently-changed and most- used skills for authoring violations — vague descriptions, bloated bodies, dead file lin
ask-matt（the-vibe-company/quivr） Ask which skill or flow fits your situation. A router over the skills in this repo.
skill-creator（anthropics/financial-services） Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specializ
session-report（anthropics/claude-plugins-official） Generate an explorable HTML report of Claude Code session usage (tokens, cache, subagents, skills, expensive prompts) from ~/.claude/projects transcripts.
mobile-e2e（rssnext/folo） Run apps/mobile Maestro end-to-end tests in this repo. Use when an agent needs to validate mobile auth flows on iOS Simulator or Android Emulator. Current maintained coverage is re
langextract-usage（google/langextract） How to use LangExtract to extract structured information from text. Use when writing code that calls lx.extract(), building extraction pipelines, defining examples, or troubleshoot
antd（ant-design/ant-design-pro） Use when the user's task involves Ant Design (antd) — writing antd components, debugging antd issues, querying antd APIs/props/tokens/demos, migrating between antd versions, or ana
tiptap（ueberdosis/tiptap） Integrate, build and debug Tiptap editors in applications. Use for Tiptap setup, installing or creating extensions, collaboration, comments, AI features, and document conversion. E
agentic-workflows（dotnet/aspnetcore） Route gh-aw workflow design/create/debug/upgrade requests to the right prompts.
adding-llm-mcp-tools（triliumnext/trilium） Use when adding, changing, or reviewing an LLM/MCP tool in Trilium (the `defineTools` definitions under packages/trilium-core/src/services/llm/tools/ — note/attribute/attachment/hi
hugging-face-jobs（patchy631/ai-engineering-hub） This skill should be used when users want to run any workload on Hugging Face Jobs infrastructure.
copilotkit（copilotkit/copilotkit） Use for any CopilotKit question — adding it to an app, chat UI, frontend or server tools, generative UI, shared state, human-in-the-loop, agent frameworks (LangGraph, CrewAI, Mastr
v-mcp（vlang/v） Using the V MCP server, `v mcp serve`, to read and change V code through the compiler itself - the AST, declarations, references, diagnostics, stdlib docs, an AST-aware rename, a g
frontend-design（dokploy/dokploy） Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates crea
codename-one（eugenp/tutorials） Build and modify Codename One cross-platform mobile apps (Java 17, Maven, ParparVM/Android/iOS/JavaScript).
debug-cuda-crash（sgl-project/sglang） Call this skill when you need to debug CUDA crashes in SGLang using kernel API logging
clone-website（jcodesmore/ai-website-cloner-template） Rebuild existing web pages as working local code, matching their real content, assets, responsive layout, and interactions. Use for website cloning, replication, or reverse enginee
guide（pnpm/pnpm） How to use with-agent-skills
writing-tsdocs（medusajs/medusa） Adds and updates TypeDoc (TSDoc) comments to TypeScript source files in the Medusa codebase.
update-deps（microsoft/graphrag） Update this GraphRAG uv-workspace monorepo's dependencies and repair the resulting breakages so every check and test passes again.
cn-check（continuedev/continue） Install and run the Continue CLI (`cn`) to execute AI agent checks on local code changes. Use when asked to "run checks", "lint with AI", "review my changes with cn", or set up Con
github-research（block/buzz） Search GitHub issues, PRs, and code using the gh CLI.
utm-review（utmapp/utm） Review pending UTM changes before they are submitted.
linear-bug-triage（langfuse/langfuse） Use this skill after a bug or regression candidate has measured evidence to document them within linear.
reasonix-guide（esengine/deepseek-reasonix） Troubleshoot and configure Reasonix capabilities: Skills (project/custom/global/builtin priority, discovery dirs), Commands (override order, /dir:file naming), Hooks (11 events, au
browser-cdp（agentscope-ai/qwenpaw） Use this skill when the user explicitly wants to connect to a running Chrome browser, scan local CDP ports, specify a `cdp_port`, or share a single browser across multiple agents/t
vibe-trading（hkuds/vibe-trading） Professional finance research toolkit — backtesting (10 engines + benchmark comparison panel), factor analysis, Alpha Zoo (462 pre-built alphas across qlib158/alpha101/gtja191/acad
calendar（can1357/oh-my-pi） Third calendar skill.
book-to-skill（virgiliojr94/book-to-skill） Converts books and documents (PDF, EPUB, DOCX, HTML, Markdown, plain text, RTF, MOBI/AZW with Calibre) into structured agent skills, extracting frameworks, mental models, principle
rustfs-release-version-bump（rustfs/rustfs） Prepare an exact RustFS Cargo version or align installation references after publication. Use for requested version bumps or the release workflow.
registry-submission（jdx/mise） Rules for adding a new tool or shorthand to mise's `registry/` — the popularity bar, the required user warning and popularity check, the PR's Popularity section, and which backends
custom-blocks（huggingface/diffusers） Use when the user has written (or wants to write) a `ModularPipelineBlocks` subclass in a local Python file and needs to package it into a Hub-uploadable directory.
plugin-analytics-instrumentation（backstage/backstage） Instrument a Backstage frontend plugin with analytics events using the Backstage Analytics API.
detecting-cryptomining-in-cloud（mukul975/anthropic-cybersecurity-skills） This skill teaches security teams how to detect and respond to unauthorized cryptocurrency mining operations in cloud environments.
greeting-demo（openbmb/chatdev） Greet the user in a distinctive, easy-to-verify format for skill activation demos.
gpt-image-2-style-library（freestylefly/awesome-gpt-image-2） Choose GPT-Image2 / gpt-image-2 visual styles and industrial prompt templates from the awesome-gpt-image-2 style library.
weknora-shared（tencent/weknora） Use when driving a WeKnora RAG server through the `weknora` CLI as an agent — authenticating, managing knowledge bases / documents / sessions / agents, running search or chat, or i
codspeed-optimize（swc-project/swc） Autonomously optimize code for performance using CodSpeed benchmarks, flamegraph analysis, and iterative improvement.
timesfm-forecasting（google-research/timesfm） Zero-shot time series forecasting with Google's TimesFM foundation model.
gpt-5-4-prompting（openai/codex-plugin-cc） Internal guidance for composing Codex and GPT-5.4 prompts for coding, review, diagnosis, and research tasks inside the Codex Claude Code plugin
huashu-nuwa（alchaincyf/nuwa-skill）女娲造人：输入人名/主题/甚至只是模糊需求，自动深度调研→思维框架提炼→生成可运行的人物Skill。两种入口：(1)明确人名→直接蒸馏 (2)模糊需求→诊断推荐→再蒸馏。触发词：「造skill」「蒸馏XX」「女娲」「造人」「XX的思维方式」「做个XX视角」「更新XX的skill」。模糊需求也触发：「我想提升决策质量」「有没有一种思维方式能帮我...」「
improve（motiondivision/motion） Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never i
agent-tools（carbon-language/carbon-lang） Guidelines and restrictions on shell commands and file manipulation tools for AI assistants.
pr-labeling（vercel-labs/skills） Classify a skills CLI pull request from its description and patch, while respecting existing labels.
bump-version（iofficeai/aionui） Use when bumping the AionUi version: query AionCore release, verify artifacts, update package.json, generate CHANGELOG, branch, commit, push, create PR, auto-merge, tag release.
skill（yeachan-heo/oh-my-codex） Manage local skills - list, add, remove, search, edit, setup wizard
nacos-skill-registry（alibaba/nacos） Discover, install, update, merge, and publish AI skills with Nacos for personal or team skill registries.
supersede-pr（remix-run/remix） Safely replace one GitHub pull request with another. Use when a user says a PR supersedes/replaces an older PR, asks to auto-close a superseded PR, or needs guaranteed closure beha
process-inbox（telegramdesktop/tdesktop） Process the local ignored ai-tdesktop inbox into durable, independently testable Telegram Desktop task records while task execution worktrees remain active.
feature-matrix-parity（zeroclaw-labs/zeroclaw） Update the OpenClaw and Hermes comparison columns of the ZeroClaw feature-and-support matrix.
burp-suite-web-application-testing（davila7/claude-code-templates） This skill should be used when the user asks to "intercept HTTP traffic", "modify web requests", "use Burp Suite for testing", "perform web vulnerability scanning", "test with
backport-pr-assistant（cockroachdb/cockroach） Help backport PRs to release branches using the backport CLI tool. Use when backporting changes that have merge conflicts requiring manual resolution.
browser（onyx-dot-app/onyx） Core browser usage guide. Read this before running any browser commands.
vercel-react-best-practices（vercel-labs/agent-skills） React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optima
scaffold-feature（signoz/signoz） Scaffold the co-located feature structure in frontend/src. Use when creating a new page, feature, view (tab), or component folder, when a feature needs a shell with tabs, or when m
a-share-runtime-data-access（hsliuping/tradingagents-cn） Use when the task requires reading A-share stock data, financial data, valuation context, or querying local stock collections through core.skill_runtime runtime interfaces.
build-graph（tirth8205/code-review-graph） Build or update the code review knowledge graph. Run this first to initialize, or let hooks keep it updated automatically.
cognee（topoteretes/cognee） Use this skill whenever the user asks about Cognee, AI memory, persistent agent memory, self-improving agents, agents learning from feedback, knowledge graphs, graph-based RAG, lon
officecli-financial-model（iofficeai/officecli） Use this skill when the user wants to build a financial model — 3-statement model, DCF valuation, LBO, SaaS unit economics, sensitivity / scenario analysis, debt schedule, or fundr
benchmark-report（dragonflydb/dragonfly） Generate a technical benchmark report in markdown from raw memtier/redis-benchmark output.
rxjs-next-migration（reactivex/rxjs） Migrate an RxJS 7 application, library, or test suite to RxJS Next through an agent-led workflow that establishes a green behavioral baseline, makes Observable lifecycle choices ex
setup（feder-cr/aihawk_mcp_server） What the AIHawk browser server needs on this machine - the patched Firefox it drives, which the server downloads on its own the first time it runs.
setup（feder-cr/aihawk） One-time setup for the AIHawk browser server - downloads the patched Firefox it drives. Use when a browser tool reports that the engine is missing, or right after installing the pl
gws-calendar-agenda（googleworkspace/cli） Google Calendar: Show upcoming events across all calendars.
symfony-security-review（symfony/symfony） Review a change (a PR, the current branch diff, or a set of files) or audit a component or the whole tree for missing or incorrect security hardening.
turborepo（vercel/turborepo） Configure and troubleshoot Turborepo repositories. Use when working with turbo.json, task pipelines, caching, Remote Cache, the turbo CLI, filtering, environment variables, package
supermemory（supermemoryai/supermemory） Supermemory is a state-of-the-art memory and context infrastructure for AI agents. Use this skill when building applications that need persistent memory, user personalization, long
colima（abiosoft/colima） Guide to using Colima — container runtimes (Docker, containerd, Kubernetes, Incus) on macOS and Linux via lightweight Lima VMs.
add-clidash（nanocoai/nanoclaw） Add clidash — a zero-dependency, read-only web dashboard that derives its tabs and tables at runtime from any CLI that lists resources as JSON.
compliant-position（garrytan/gbrain） Skill that runs gbrain search before external lookup
9router（decolua/9router） Entry point for 9Router — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch. Use when the user mentions 9Router, NINEROUTE
update-ard-port（googlechrome/lighthouse） Sync Lighthouse's Agentic Resource Discovery (ARD) port with upstream ards-project/ard-spec.
bilibili-evolved-dev-server（the1812/bilibili-evolved） Bilibili-Evolved local dev server workflow.
skill-maintenance（composiohq/composio） Create, update, validate, or reorganize repo-local Agent Skills under .agents/skills, including SKILL.md frontmatter, first-level references, compatibility symlinks, and validation
skill-creator（langchain-ai/deepagents） Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations.
implementation-kickoff（openai/openai-agents-python） Carry implementation through an isolated worktree and local handoff. Use only when this skill is explicitly invoked.
opencli-autofix（jackwener/opencli） Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapte
gpt-researcher（assafelovic/gpt-researcher） GPT Researcher is an autonomous deep research agent that conducts web and local research, producing detailed reports with citations.
picoclaw-agent（sipeed/picoclaw） Configure, extend, debug, or contribute to PicoClaw itself. Use when the task is about PicoClaw CLI commands, config.json, gateway, auth, models, skills, MCP servers, cron, routing
hallmark（nutlope/hallmark） Anti-AI-slop design skill for greenfield pages, audits, redesigns, and design extraction from URLs or screenshots. Use when the user asks to build a new app or landing page, wants
ctx-insight（mksglu/context-mode） Open the context-mode Insight dashboard in your default browser. Insight is the hosted analytics layer for AI-assisted engineering teams — per-engineer productive rate, retry waste
cleanup（simstudioai/sim） Run all code quality skills — effects, memo, callbacks, state, React Query, emcn design review, url-state, comments, and test-audit — analyzing in parallel, then applying fixes seq
zoom-cobrowse-sdk（anthropics/knowledge-work-plugins） Reference skill for Zoom Cobrowse SDK. Use after routing to a collaborative-support workflow when implementing browser co-browsing, annotation tools, privacy masking, remote assist
fastgpt-docker-deploy（labring/fastgpt） FastGPT Docker Compose self-hosting deployment workflow.
codeguard（the-art-of-hacking/h4cker） A CodeGuard security skill that helps AI coding agents write secure code and prevent common vulnerabilities. Use this skill when writing, reviewing, or modifying code to ensure sec
odl-pdf（opendataloader-project/opendataloader-pdf） Procedure for extracting structured data from PDFs with opendataloader-pdf (ODL) correctly: read the installed tool's own help to discover its current options, build the minimal co
karakeep（karakeep-app/karakeep） Official skill for how to use karakeep (the bookmark manager) and interact with it programmatically.
write-agentmemory-skill（rohitg00/agentmemory） The house format and rules for writing or updating an agentmemory skill. Use when adding a new skill, restructuring an existing one, or reviewing a skill contribution for consisten

AI 技能总库

技能总库列表