Agent skills

Skills for codex

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
9,699 found
1,0571,104 · page 23 / 203
laminaRoute ordinary product implementation and explicit Lamina lifecycle requests. Use passively after initialization for changes to…aryaniyapsnemotron-customizePlan, configure, and chain repo-native Nemotron customization steps into single-step or multi-step pipelines: curation…NVIDIAoma-observabilityIntent-based observability + traceability router across layers, boundaries, and signals. Routes to vendor-specific skills via…first-flukedbos-golangGuide for building reliable, fault-tolerant Go applications with DBOS durable workflows. Use when adding DBOS to existing Go…sickn33matlab-vehicle-network-communicationUse when setting up vehicle network communication in MATLAB using Vehicle Network Toolbox. Covers CAN/CAN FD (fully implemented)…matlabokx-aiERC-8004 Agent identity: 注册/更新/上架/下架/搜索agent, register/update/activate/deactivate/search — User/ASP/Evaluator(买家/卖家/仲裁者)…internet-courtremotion-best-practicesBest practices for Remotion - Video creation in Reactsickn33remotion-video-creationBest practices for Remotion - Video creation in React. 29 domain-specific rules covering 3D, animations, audio, captions, charts…mturacswiftui-ui-patternsApply proven SwiftUI UI patterns for navigation, sheets, async state, and reusable screens.sickn33genesisUse this skill BEFORE drafting any agentic primitive module (skill, persona scoping file, scope-attached rule file, orchestrator…danielmeppielokx-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…NVIDIAwritesmatlab-scenario-builderGenerate driving scenes, scenarios, road surfaces, and 3D content from scenariobuilder.* sensor data (GPS, camera, lidar, actor…matlabbaoyu-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…sickn33short-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”“…worldwondererecl-harness-engineerCreate or audit ECL Agent Harness infrastructure: AGENTS.md, change tracking, repository guidance, lint checks, CI gates, and…sickn33resolve-design-errorsUse when asked to run Design Error Detection (quick defect scan), find design errors in a Simulink model, perform root cause…matlabtao-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…NVIDIAwritesapp-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-courttao-train-depth-anything-v2Monocular depth estimation using Metric Depth Anything v2 or Relative Depth Anything architectures. Predicts per-pixel depth from…NVIDIAwritesclaude-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)…matlabtao-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…NVIDIAwritestesting-simulink-modelsTests Simulink models using either ephemeral Gherkin-based tests (model_test) for quick validation or persistent tests (Simulink…matlabmatlab-use-machine-learning-appsUse when the user wants to train, compare, or export machine learning models using Classification Learner or Regression Learner —…matlabmfs-ingestRegister, update, or re-sync data sources for MFS so they become searchable — postgres / mysql / mongo / snowflake / bigquery…zilliztechtao-train-deformable-detrDeformable DETR for 2D object detection. Uses deformable attention for efficient multi-scale feature processing, lighter than…NVIDIAwritestao-train-grounding-dinoGrounding DINO for open-set object detection. Combines DINO-style detection with a BERT text encoder for language-guided…NVIDIAwritestao-train-mask-grounding-dinoMask Grounding DINO for grounded instance segmentation. Extends Grounding DINO with a mask-prediction head for open-set…NVIDIAwritestao-train-mask2formerMask2Former for universal image segmentation (panoptic, instance, and semantic). Transformer-based with masked attention for…NVIDIAwritestao-train-oneformerOneFormer for universal image segmentation. Unifies panoptic, instance, and semantic segmentation with a single architecture…NVIDIAwritestao-train-rtdetrRT-DETR (Real-Time DEtection TRansformer) for 2D object detection. Designed for real-time inference with competitive accuracy and…NVIDIAwritesmatlab-build-simbiology-modelBuild, modify, and diagram SimBiology models — API reference, helper functions, and layout patterns. Use when constructing or…matlabmatlab-model-rfRF Toolbox and RF Blockset in MATLAB -- S-parameter I/O, network conversions (S/Z/Y/ABCD/T/H/G, mixed-mode)…matlabbaocutDrive BaoCut from the CLI: transcribe local media or media URLs, polish transcripts through Agent workers, translate/correct…JimLiucrossframe-orgUse when CrossFrame Suite routes explicit Chinese analysis of teams, projects, organizations, responsibility chains, feedback…sickn33deepstream-devNVIDIA DeepStream SDK development with Python pyservicemaker API. Use when building video analytics pipelines, GStreamer-based…NVIDIAmfs-findSearch, grep, browse, and read across registered MFS data sources via the `mfs` CLI — codebases, docs, PDFs, web crawls…zilliztechroadrunner-convert-lanelet2-to-rrhdConvert Lanelet2 maps (.osm) to RoadRunner HD Map (.rrhd) format using MATLAB. Use when converting Lanelet2 maps into RoadRunner…matlabtao-train-centerposeCenterPose for keypoint / pose estimation. Detects object centers and regresses keypoint locations for 6-DoF object pose…NVIDIAwritestao-train-metric-learning-recognitionMetric-learning recognition (ml-recog) for fine-grained visual recognition. Learns embeddings for retrieval-based matching (e.g.…NVIDIAwrites
← Prev23 / 203Next →
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