Agent skills

AI & Agents skills

Read straight from the source repositories, not from submitted listings. Every skill shows what it does, what is inside, where it came from — and whether attention around its source is actually growing.

Toolclaude-code 29,140codex 4,755cursor 3,111copilot 976windsurf 55cline 34
CategoryWorkflow & Productivity 4,979AI & Agents 3,037Data & Analytics 2,345Code Review & Quality 1,376Backend & API 1,244Security 1,194Design & Presentation 1,154Documentation 965Content & Marketing 916Testing & QA 777DevOps & Cloud 576Databases 550Frontend 469Business & Finance 328Media & Video 257Other 9,833
4,965 found
385432 · page 9 / 104
explaining-machine-learning-modelsBuild this skill enables AI assistant to provide interpretability and explainability for machine learning models. it is triggered…jeremylongshorewritesguixingren-skill硅星人/硅星人Pro(品玩/PingWest旗下AI科技媒体)的AI科技内容创作思维——硅谷一线视角+中美双线叙事+快讯串联结构+AI社区产品化运营。…momozi1996hypothesis-genUse when the user wants to generate and literature-vet a pool of novel, testable research hypotheses for a question or domain. A…gaasherlegal-analysis-forge-oliver-schmidt-prietzEU Digital Regulation Legal Analysis Forge — generates a tailored expert prompt for structured legal analysis of an EU…lawve-ailiangziwei-skill量子位(QbitAI,国内AI行业Top 1科技媒体)的AI科技自媒体创作思维——团队出品·数据驱动·速报+深析+智库三位一体。 触发词:「量子位视角」「像量子位那样写」「AI行业新闻快讯」「AI十大趋势」「AIGC全景图谱」「MEET智能未来」。…momozi1996lijigang-skill李继刚(Prompt布道师/Prompt之神)的AI提示词创作思维——Lisp压缩美学+哲学底色+结构化写作+极简主义。 触发词:「李继刚视角」「像李继刚那样写」「Prompt之神」「汉语新解」「压缩美学」「ljg-skills」「Lisp提示词」。…momozi1996managing-simulink-projectsManages MATLAB projects for Simulink workflows: path management, file registration, labels, source control configuration, and…matlabml-training-recipesBattle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery…OpenRaisernemo-relay-plugin-adaptive-tuningUse this skill when baseline NeMo Relay instrumentation exists and the user wants to configure or evaluate adaptive plugin…NVIDIAopenrouter-model-availabilityMonitor OpenRouter model availability and implement health checks. Use when building systems that depend on specific models being…jeremylongshorewritesopentagSet up, run, and troubleshoot OpenTag with the published CLI across Slack, GitHub, GitLab, Linear, Lark / Feishu, Codex, Claude…amplifthqoptimizing-promptsExecute this skill optimizes prompts for large language models (llms) to reduce token usage, lower costs, and improve…jeremylongshorewrites案件承接与委托刑事辩护案件承接与委托Skill。协助律师完成刑事案件的初次接待、案件评估、风险告知、委托手续办理及案件信息采集,生成标准化委托文书并建立案件档案。当用户发送客户编号并提及"刑事案件承接"、"刑事委托"、"刑事接案"等指令时触发使用。pa1nrui1产品法务中国境内产品法务与产品合规 Skill。用于产品上线、功能合规、默认开启、客户 Logo/客户案例展示、PRD/页面流程/用户协议/隐私政策/帮助中心审查、产品材料合规审查、高合规行业产品深度评估、营销文案产品场景初筛等任务。适用于用户询问“这个功能能不能做”…pa1nrui1诉讼案件管理民事、刑事及劳动争议诉讼共用的案件运营管理 Skill。用于案件更新、传票/开庭通知/举证通知/应诉通知/裁判文书处理、期限台账、飞书日历提醒、事实时间线和程序时间线维护、飞书思维导图同步、案件简报、诉讼案件总览、案件组合状态、案件关闭与结案归档检查。案件隔离…pa1nrui1劳动争议仲裁程序管理劳动争议仲裁程序全流程管理Skill,覆盖仲裁前置强制检测、仲裁时效计算、一裁终局自动判断、仲裁申请书/答辩书生成(W/E双角色)、仲裁请求清单、仲裁→诉讼衔接路由(L9五分支)、仲裁策略报告和用人单位仲裁前风险敞口评估。当用户发送客户编号并提及"仲裁申请"、…pa1nrui1plakatstil-prompt-compiler把文字主题、商品照片、包装照片、物品照片或人物服务主题编译成 Plakatstil / Sachplakat 风格提示词。用户提到…FANzR-archqiuzhi2046-skill秋芝2046(前产品经理,AI Native创作者)的AI科普内容创作思维——爆肝实操导向、痛点前置产品思维、全平台内容矩阵、B站深度+抖音短平快+飞书系统化。…momozi1996reducing-entropyManual-only skill for minimizing total codebase size. Only activate when explicitly requested by user. Measures success by final…softaworkssaibochanshin-skill赛博禅心(大聪明,技术深度型AI博主)的AI科技自媒体创作思维——技术散文·反热潮·深度拆解·冷静旁观。 触发词:「赛博禅心视角」「像赛博禅心那样写」「AI技术深度解读」「AI论文解读」「AI行业大事记」「踏马的Agent」。…momozi1996saiwenqiaoyi-skill赛文乔伊(周游,Joy)的AI科技短视频创作思维——产品老炮视角、前沿科技速递、AI降临派技术乐观主义。 触发词:「赛文乔伊视角」「像赛文乔伊那样写」「科技乔伊瞧」「AI产品短视频」「AI降临派」。…momozi1996skill-developerComprehensive guide for creating and managing skills in Claude Code with auto-activation system, following Anthropic's official…sickn33specifying-plant-modelsSpecify plant models for closed-loop simulation: system specs, architecture, build plans, validation plans. Use when creating…matlabtegongyuzhou-skill特工宇宙/仲泰(Agent Universe,国内首个聚焦AI智能体AI Agent的垂直科技自媒体)的内容创作思维——Agent垂直深耕+实操导向+产品体验验证+社区分发闭环+AI Agent翻译器。…momozi1996training-machine-learning-modelsBuild train machine learning models with automated workflows. Analyzes datasets, selects model types (classification…jeremylongshorewritesusing-aegisUse when starting a turn or checking Aegis skill routing.GanyuanRanusing-superpowersUse when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response…guanyangusing-superpowersUse when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response…Infrasity-Labsusing-superpowers在开始任何对话时使用——确立如何查找和使用技能,要求在任何响应(包括澄清性问题)之前调用 Skill 工具jnMetaCodevertex-ai-media-masterExecute automatic activation for all google vertex ai multimodal operations operations. Use when appropriate context detected.…jeremylongshorewritesxinzhiyuan-skill新智元(AI_era,国内AI领域权威媒体)的AI科技自媒体创作思维——中文叙事+惊叹号密集+记者视角+深度长文+快速快讯。 触发词:「新智元视角」「像新智元那样写」「AI行业深度报道」「AI人物榜」「AIGCRank」「超智能时代」。…momozi1996chinese-de-aigc面向中文学术论文的降 AIGC 检测率 Skill。针对知网、万方、维普、Turnitin 中文版的检测机制,识别并消除中文大语言模型的 17 类结构化写作痕迹。采用"定位 → 诊断 → 改写 → 自评 →…brycewang-stanfordapp-routerThis skill should be used when the user asks to "create a Next.js route", "add a page", "set up layouts", "implement loading…davepoonapple-on-device-aiBuild private, on-device AI features on iPhone, iPad, and Mac with Foundation Models, Core ML, MLX Swift, or llama.cpp. Use when…dpearson2699bailian-protocol阿里云百炼 `bl` 家族共享执行协议(consent 确认、版本预检、鉴权/安装、错误上报、本地文件与输出约定)。 不是面向用户意图的业务入口;当任一 bailian-* 业务 skill(bailian-cli / bailian-gen /…modelstudioaibaoyu-wechat-summarySummarizes WeChat group chat highlights into a structured digest using the local wx-cli binary…JimLiubauhaus-visual-prompt把包豪斯(Bauhaus)视觉语言拆成媒介模块,识别用户意图后编译成一条确定性、可直接用于图像模型的提示词。用户提到包豪斯风格封面、文章配图、栏目/活动海报、Bauhaus…FANzR-archc-bounds-safetyGuide for the C -fbounds-safety language extension. Covers the language model, pointer annotations, adopting bounds-safety in…superagents-labclaude-automation-recommenderAnalyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for…anthropicscursor-model-selectionConfigure and select AI models in Cursor for Chat, Composer, and Agent mode. Triggers on "cursor model", "cursor gpt", "cursor…jeremylongshorewritesdoca-structured-tools-contractUse this skill whenever another DOCA skill says "prefer the structured tool per doca-structured-tools-contract", or when the user…NVIDIAesmUse when working directly with the `esm` Python SDK, ESM3 or ESMC model IDs, Forge/Biohub inference clients, or ESMFold2 folding…K-Dense-AIfable-foremanTeam-lead orchestrator: whichever frontier-class Claude model leads your session plans, routes, and verifies while cheaper Claude…olsenbrandsfine-tuning-expertUse when fine-tuning LLMs, training custom models, or adapting foundation models for specific tasks. Invoke for configuring…Jeffallanweather-forecast-report将天气要素(风速、能见度、降雨量等)单站预报系统的项目文档、模型、报告、评估结果整理成符合省级自然科学基金项目编写规范的专题研究报告。适用于:(1) 基于Claude Code + OpenSpec开发的气象预报系统结题报告编写,(2)…staruhubxuefeng-method雪峰式AI-Native产品开发方法论。适用于:(1) 用户行为开放、不可穷举的AI-native产品(AI日历、AI助手、AI推荐、对话式产品等),(2) 强模型依赖型场景,AI驱动核心决策而非仅辅助,(3) 多专精Agent架构设计与分工,(4)…staruhubgenerate-requirement-draftsGenerates draft requirements from Simulink models. Use when drafting or updating requirement artifacts from a model. Prefers…matlabgolang-dependency-injectionComprehensive guide for dependency injection (DI) in Golang. Covers why DI matters (testability, loose coupling, separation of…samberwrites
← Prev9 / 104Next →
How the catalog works
What is an agent skill?

A folder with a SKILL.md inside — instructions, and often scripts and assets, that an AI agent loads when the task matches. Claude Code, Codex, Cursor and Copilot all read the same format, so one skill usually works across them.

Where does this catalog come from?

We read 660 source repositories straight from their file trees rather than from submitted listings — what you see is what is actually published. 98 repositories were rejected because they advertise skills but contain none: link lists, not folders.

Why is there no install counter?

Because install counts live in the registry that serves `npx skills add`, and that is not ours — publishing a number we cannot verify would be worse than showing none. Instead we show where a skill comes from and whether attention around its source is actually growing, measured from our own weekly snapshots.

Do you deduplicate?

Yes, and it matters more than expected. Aggregator repositories republish the same skill in several places — one source carried 6,317 SKILL.md files for 2,001 actual skills. We collapse by folder name and keep the canonical copy, so the catalog counts things, not copies.

Keep going