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 29,139codex 4,760cursor 3,079copilot 977windsurf 55cline 34
CategoryWorkflow & Productivity 4,986AI & Agents 3,034Data & Analytics 2,346Code Review & Quality 1,378Backend & API 1,244Security 1,196Design & Presentation 1,129Documentation 966Content & Marketing 918Testing & QA 778DevOps & Cloud 576Databases 550Frontend 469Business & Finance 328Media & Video 258Other 9,844
5,741 found
289336 · page 7 / 120
matlab-model-rfRF Toolbox and RF Blockset in MATLAB -- S-parameter I/O, network conversions (S/Z/Y/ABCD/T/H/G, mixed-mode)…matlabcode-testing-extensionsProvides file paths to language-specific extension files for the code-testing pipeline. Call this skill to discover available…dotnettao-train-centerposeCenterPose for keypoint / pose estimation. Detects object centers and regresses keypoint locations for 6-DoF object pose…NVIDIAwritestao-train-segformerSegFormer for semantic segmentation. Lightweight transformer-based architecture with hierarchical feature extraction, efficient…NVIDIAwritestao-train-sparse4dSparse4D for multi-camera temporal 3D object detection and tracking. Uses sparse queries with deformable attention across camera…NVIDIAwritesforgecadForgeCAD model authoring, editing, debugging, and execution guidance for .forge.js, SVG-import, assembly, and CLI workflows. Use…ForgeCADkaggle-learnerThis skill should be used when the user asks to "learn from Kaggle", "study Kaggle solutions", "analyze Kaggle competitions", or…brycewang-stanfordctf-pwnProvides binary exploitation techniques for CTF challenges. Use when you already have a vulnerable native target or service and…ljagiellowritestao-train-fast-foundation-stereoReal-time stereo depth estimation using FastFoundationStereo (FFS), the distilled bp2 commercial variant of FoundationStereo.…NVIDIAwritesshort-drama-assets从短剧剧本拆解并统筹角色/造型、场景/视图、道具/状态和跨场连续性。用户说‘拆角色/场景/道具’、‘做资产表/角色表/场景表/道具表’、‘判断复用还是新变体’、‘更新造型/道具状态’,或拿现成剧本直接做视觉资产准备时使用;本 skill…worldwonderersuper-codeStanding house style to enforce dense, correct, and idiomatic code on all coding tasks. Minimizes code bloat and agent operation…sickn33tao-train-bevfusionBEVFusion for multi-sensor 3D object detection. Fuses LiDAR point clouds and camera images in bird's-eye-view (BEV) space, used…NVIDIAwritestao-train-nvpanoptix3dNVPanoptix3D for panoptic 3D scene reconstruction from posed RGB images. Produces 3D panoptic segmentation (semantic, instance…NVIDIAwritesusing-aoCatalog of the AO (Agent Orchestrator) `ao` CLI: spawning workers, managing sessions and projects, sending messages, controlling…Untrivial-aibuiltin-toolBuild LobeHub builtin tool packages. Use when adding agent-callable tools, manifests, executors, runtimes, inspectors, renders…lobehublearning-coach中文高级私人学习教练。用户说“开始学习 X”“继续/下一课”“学完了”“记录进度/打卡”“我学到哪了/还要多久”,正在通过真实项目、源码、作品、题目或任务学习编程、Agent、写作、语言、考试、研究或职业技能,或对具体概念和材料连续追问时使用。触发后主动读取学…chrichuang218oma-marketMarket research skill for pain-point extraction, trend detection, competitor positioning, and discovery across community sources…first-flukesignal-geometryCreate Signal Geometry abstract illustrations and posters from concepts or briefs. Use when the user asks for sparse geometric…CaliCastlebetter-harnessUse when /better-harness reviews the outer coding-agent Harness for lifecycle controls, repeated work, project feedback, agent…QoderAIchalk-logicCreate Chalk Logic concept-led chalkboard illustrations from briefs. Use for sparse wordless chalkboard explanations, non-diagram…CaliCastlegastownMulti-agent orchestrator for Claude Code. Use when user mentions gastown, gas town, gt commands, bd commands, convoys, polecats…jeremylongshorellmquant-optionsRouter skill for LLMQuant options workflows. Use when the user needs IV rank, option scoring, strategy construction, Greeks, P&L…LLMQuantmatlab-solve-pdeEnd-to-end finite element analysis in MATLAB PDE Toolbox — geometry creation, model setup, solve, and post-processing in one…matlab二审阶段辩护刑事辩护二审阶段工作Skill,覆盖上诉审委托接案、一审材料衔接、阅卷审查、会见策略、争取开庭、书面辩护意见、二审庭审、不开庭审理沟通、裁判分析及发回重审衔接。当用户提及"二审"、"上诉"、"抗诉"、"争取开庭"、"发回重审"、"二审辩护"等关键词时触发使用。pa1nrui1skill-writerCreate and improve agent skills following the Agent Skills specification. Use when asked to create, write, or update skills.sickn33tao-train-mask-auto-labelMAL (Mask Auto-Label) for weakly-supervised segmentation. Produces segmentation masks from minimal annotations (point or box…NVIDIAwritescivil-service-essay-grader公务员考试申论精细批改与多轮改写助手。用户要求“批改申论”“给申论小题打分”“看看漏了哪些采分点”“批改公文/汇报提纲/发言稿”“批改大作文”“逐段修改”“我改完了再批一次”“对比两版答案”,或提交申论材料、题干、作答要求和答案时,应使用本…mingchen666civil-service-question-practice公务员考试专项刷题与错题重练助手。当用户说“刷题”“来10道资料分析”“逐题做判断推理”“按某省真题练习”“从我上传的PDF/题库里抽题”“先别给答案”“限时练一组”“错题重做”“再来几道同类题”“针对薄弱点出题”时,应使用本…mingchen666learn-anything面向“学习任何知识”的通用导师型 skill。用于用户想学习新主题、制定学习计划、整理学习笔记、做课后复盘、生成项目任务书、做掌握度检查,或希望基于自己资料与外部权威资料进行中文导师式陪学时。默认采用“导师 + 项目教练”模式,以项目驱动和 Mastery…mingchen666learn-anything-skill面向“学习任何知识”的通用导师型 skill。用于用户想学习新主题、制定学习计划、整理学习笔记、做课后复盘、生成项目任务书、做掌握度检查,或希望基于自己资料与外部权威资料进行中文导师式陪学时。默认采用“导师 + 项目教练”模式,以项目驱动和 Mastery…read2017performancePerformance profiling and SwiftUI debugging skills — Instruments guidance, hangs, memory issues, slow launches, energy drain…rshankraswritestao-run-automlRun AutoML / hyperparameter optimization (HPO) for NVIDIA TAO networks using AutoMLRunner. Handles algorithm selection (bayesian…NVIDIAwritescli-masteryInteractive training for the GitHub Copilot CLI. Guided lessons, quizzes, scenario challenges, and a full reference covering…githubcommand-developmentThis skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define…anthropicsCommand DevelopmentThis skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define…brycewang-stanfordcursor-performance-tuningOptimize Cursor IDE performance: reduce memory usage, speed up indexing, tune AI features, and manage extensions for large…jeremylongshorewriteskleros-curateInteract with Kleros Curate registries — the decentralized token-curated list protocol for token lists, address tags, and…internet-courtmock-examThis skill should be used when the user asks to "模拟考试", "出模拟卷", "做一套模拟题", "帮我批改", "批改试卷", "给我出题考试", "期末模拟", "模拟测试", "考考我"…mingchen666writesnetwork-protocol-vizGenerate single-file HTML animations that teach network protocols and packet flow. Use this skill when the user asks about…mingchen666侦查阶段辩护刑事辩护侦查阶段工作Skill,涵盖会见全流程、案件法律分析与量刑预判、批捕时间节点管理、法律文书生成、执业风险防范等完整辩护工作规范pa1nrui1简易速裁程序刑事辩护简易程序、速裁程序及普通程序简化审理分支Skill,重点处理认罪认罚案件中的程序适用审查、量刑协商、庭审简化、权利保障和时间节点管理。作为一审阶段辩护的分支,当用户提及"简易程序"、"速裁程序"、"认罪认罚"、"快速审理"、"当庭宣判"等关键词时触发使…pa1nrui1version-bumperExecute automatically handles semantic version updates across plugin.json and marketplace catalog when user mentions version…jeremylongshorewritescertifying-release-evidenceUse when a source archive, package, container, skill registry, or product release needs reproducible proof bound to the exact…casioreview20-glitchcomposing-technique-workflowsUse when one outcome requires multiple specialized techniques with branch, join, parallel, retry, or rollback relationships…casioreview20-glitchconsolidating-project-memoryUse when decisions, blockers, conventions, and stable summaries must survive across tasks without treating conversation…casioreview20-glitchenforcing-context-budgetsUse when planned context, tool schemas, model output reserve, or retrieved artifacts may exceed tenant, route, model, or…casioreview20-glitcherror-analysisThis skill should be used when the user asks to "分析错题", "错因分析", "整理错题本", "我这道题做错了", "帮我分析错因", "归类薄弱知识点", "错误模式", "巩固练习"…mingchen666writesexplaining-route-decisionsUse when a human or agent needs a concise, auditable explanation of why techniques and providers were selected, excluded…casioreview20-glitch
← Prev7 / 120Next →
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