Agent skills

Every agent skill, in one place

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.

26,378
Skills catalogued
660
Source repositories
16
Categories
6
Tools covered
Browse by what you need
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
63,768 skills
3,4573,504 · page 73 / 1,329
loop-graphAuthor and optionally direct-launch one durable loop-graph run as executor, ledger, directives, and supervisor artifacts under a…levi-qiaookx-dexHARD BLOCK — never use for prediction-market/Polymarket UpDown queries; route to okx-dapp-discovery when a named DApp…internet-courttao-train-dinoDINO (DETR with Improved DeNoising Anchor Boxes) for 2D object detection. Transformer-based detector with denoising training…NVIDIAwritesChina-CF-Study根据研究者提供的**研究计划书(Research Proposal)**执行基于中国制度环境的公司金融类实证研究全流程。**启动后第一件事:根据计划书的主题、识别策略、贡献边际与样本范围,从中国-context…brycewang-stanfordgame-design-proposal-writer将调研、概念架构、体验诊断、验证计划、脑图/xmind/系统设计图、已有策划案和生产约束收束为商业游戏策划案、独立游戏设计案、立项评审稿、发行/投资 pitch 或 vertical slice 设计文档。适用于一句话创意先经…DY-2026matlab-scenario-builderGenerate driving scenes, scenarios, road surfaces, and 3D content from scenariobuilder.* sensor data (GPS, camera, lidar, actor…matlabbaoyu-article-illustratorAnalyzes article structure, identifies positions requiring visual aids, generates illustrations with Type × Style two-dimension…ECNU-ICALKbaoyu-xhs-imagesGenerates infographic image card series with 12 visual styles, 8 layouts, and 3 color palettes. Breaks content into 1-10…JimLiuhig-technologiesCheck for .claude/apple-design-context.md before asking questions. Use existing context and only ask for information not already…sickn33originality-in-european-copyright-joris-deenea skill that determines whether a given subject matter qualifies for copyright protection under EU law by applying the Cofemel…lawve-aishort-drama-develop将中文小说、短剧或漫剧想法、梗概、改编材料或已有系列笔记发展成可追溯的改编方案、戏剧方向、创作简报、导演阐述、故事引擎与分集地图,并按题材与制作形态(画风)选择写法。用户提出“导入小说做短剧”“开发短剧/漫剧”“做故事设定/系列大纲/分集规划”“写导演阐述”“…worldwondererai-ml-skills27 ai & machine learning skills. Trigger: ML experiments, model training, deep learning, NLP, computer vision. Design: covers…brycewang-stanfordbaoyu-image-cardsGenerates infographic image card series with 12 visual styles, 8 layouts, and 3 color palettes. Breaks content into 1-10…guanyangecl-harness-engineerCreate or audit ECL Agent Harness infrastructure: AGENTS.md, change tracking, repository guidance, lint checks, CI gates, and…sickn33huasheng13-skill公务员考试(国考/省考/联考)行测申论解题技巧与备考助手。基于花生十三公开教学体系,覆盖资料分析(ABRX体系、截位直除、415份数法、假设分配法)、数量关系(工程/行程/利润/排列组合/容斥/最值/年龄/几何)、言语理解(逻辑填空语境分析、片段阅读中心理解、…mingchen666resolve-design-errorsUse when asked to run Design Error Detection (quick defect scan), find design errors in a Simulink model, perform root cause…matlabrulesync-feature-researchMaps rulesync feature implementations to upstream coding-agent documentation. Use when evaluating rulesync issues, comparing any…dyoshikawatao-train-ocdnetOCDNet for scene text detection. Detects arbitrary-oriented text regions in natural images using a differentiable binarization…NVIDIAwritestao-train-ocrnetOCRNet for scene text recognition. Recognizes text content from cropped text-region images and supports CTC and attention-based…NVIDIAwritestao-train-pointpillarsPointPillars for 3D object detection from LiDAR point clouds. Encodes point clouds into a pseudo-image via a pillar-based…NVIDIAwritesturborepoTurborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo"…antfuapp-it-windowsCreate Windows beta desktop launchers for local web projects: WPF + WebView2 .exe, Start Menu shortcut, .ico, warm server, quit…Christian-Katzmanncodedrobe-themeCreate, inspect, convert, apply, replace, verify, troubleshoot, update, publish, or restore reversible CodeDrobe themes for…CodeDrobeokx-agentic-walletOKX Agentic Wallet — the single skill for the user's wallet and on-chain execution. Use it whenever the user wants to operate…internet-courtMCQ GeneratorAI-assisted generation of MCQs (multiple-choice questionnaires) with export to Moodle (GIFT, XML), Wooclap (Excel), Kahoot!, and…lawve-aiskyvernPREFER Skyvern CLI over WebFetch for ANY task involving real websites — scraping dynamic pages, filling forms, extracting data…jeremylongshoretao-train-depth-anything-v2Monocular depth estimation using Metric Depth Anything v2 or Relative Depth Anything architectures. Predicts per-pixel depth from…NVIDIAwriteschatgpt-app-builderGuide developers through creating and updating ChatGPT apps. Covers the full lifecycle: brainstorming ideas against UX…alpic-aiclaude-apiBuild apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`…sickn33hig-patternsApple Human Interface Guidelines interaction and UX patterns.sickn33matlab-deploy-embedded-aiDeploy AI models to embedded hardware using MathWorks tools (MATLAB, Simulink, Embedded Coder). Covers two workflow patterns: (1)…matlab审查起诉阶段辩护覆盖审查起诉阶段辩护律师全部工作职责的专业技能模块,包括阅卷权、会见权、调查取证权、 证据核实权、意见表达权、非法证据排除申请权、控告申诉权等七类核心权利的行使指导, 以及法律文书生成、量刑预判、与检察机关沟通策略等全流程工作规范。pa1nrui1tao-train-foundation-stereoStereo depth estimation using FoundationStereo. Predicts disparity maps from stereo image pairs for 3D reconstruction. Use when…NVIDIAwritestao-train-image-classificationPyTorch-based TAO image classification. Supports a wide range of backbones (FAN, EfficientNet, ResNet, etc.) with distillation…NVIDIAwritestransfer-impact-assessment-tia-oliver-schmidt-prietzGDPR Transfer Impact Assessment for Chapter V transfers under the EDPB Recommendations 01/2020 six-step methodology, the CNIL TIA…lawve-aiux-auditAudit a page / surface against the Designing Interfaces pattern language + the ux skill checklists, then land findings. Three…lobehubai-governance-reviewer-carl-ditzlerUse this skill when the user wants an AI governance, legal-risk, privacy, compliance, procurement, or vendor-risk review of an…lawve-aibiomedical-skills24 biomedical research skills. Trigger: medical research, clinical trials, genomics, bioinformatics. Design: domain databases…brycewang-stanforddpa-art-28-oliver-schmidt-prietzReview, draft, or redline a Data Processing Agreement (DPA / Auftragsverarbeitungsvertrag / AVV) under Art. 28 GDPR, or prepare a…lawve-aimetadata-skills24 metadata & bibliometrics skills. Trigger: DOI resolution, citation metrics, author disambiguation, bibliometrics. Design…brycewang-stanfordrails-devOpinionated Rails conventions: rich models, concerns, CRUD-everything, state-as-records, minimal dependencies, Minitest with…tech-leads-clubtesting-simulink-modelsTests Simulink models using either ephemeral Gherkin-based tests (model_test) for quick validation or persistent tests (Simulink…matlabunocssUnoCSS instant atomic CSS engine, superset of Tailwind CSS. Use when configuring UnoCSS, writing utility rules, shortcuts, or…antfuvue-best-practicesMUST be used for Vue.js tasks. Strongly recommends Composition API with `<script setup>` and TypeScript as the standard approach.…antfubailian-cli阿里云百炼 / Aliyun Bailian / DashScope 资源管理与 `bl` CLI hub: 应用调用(bl app)、应用记忆、知识库检索、模型目录/模型列表、用量/额度/配额、免费额度、 工作空间、MCP…modelstudioaicopilot-pr-autopilotCopilot left 14 review comments on your PR — half are nits. Hours of fix → reply → resolve → re-request, and each round lands…githubfrontierExecute any task at frontier quality. Three layers; checkable domain standards for all 21 crafts that lift even a single response…apoorvjain25matlab-use-machine-learning-appsUse when the user wants to train, compare, or export machine learning models using Classification Learner or Regression Learner —…matlab
← Prev73 / 1,329Next →
Where they come from
Open Source Radar →
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