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
2,4972,544 · page 53 / 104
tensorflow-model-trainerTensorflow Model Trainer - Auto-activating skill for ML Training. Triggers on: tensorflow model trainer, tensorflow model trainer…majiayu000writestensorflow-serving-setupTensorflow Serving Setup - Auto-activating skill for ML Deployment. Triggers on: tensorflow serving setup, tensorflow serving…majiayu000writestensorflow-trainerTensorFlow/Keras model training skill with callbacks, distributed strategies, and TensorBoard integration.a5c-aiwritestensorflow-trainerTensorFlow/Keras model training skill with callbacks, distributed strategies, and TensorBoard integration.majiayu000writestensorrt-optimizationNVIDIA TensorRT model optimization and deployment. Convert models to TensorRT engines, configure optimization profiles and…a5c-aiwritestensorrt-optimizationNVIDIA TensorRT model optimization and deployment. Convert models to TensorRT engines, configure optimization profiles and…majiayu000writesopen-eth-terminal-agentAn agent that can help users with creating and running open-eth-terminal scripts to support interacting with the application. It…majiayu000terminal-agentsHigh-Performance CLI AI Agents (Claude Code, Gemini CLI, Open Code).majiayu000terrainTerrain skill for heightmaps, splatmaps, and vegetation.a5c-aiwritestessaTESSA (TCR and Expression Joint Clustering) is a Bayesian model that integrates T-cell receptor (TCR) sequence profiling with…majiayu000testing-ai-hallucinationsUse when testing ai hallucinations is required during ai-products product work, especially when the result must be traceable…casioreview20-glitchtesting-ai-prompt-injectionUse when testing ai prompt injection is required during ai-products product work, especially when the result must be traceable…casioreview20-glitchtesting-automation-schedulesUse when testing automation schedules is required during automation product work, especially when the result must be traceable…casioreview20-glitchtesting-automation-webhooksUse when testing automation webhooks is required during automation product work, especially when the result must be traceable…casioreview20-glitchtesting-browser-store-readinessUse when testing browser store readiness is required during browser-extensions product work, especially when the result must be…casioreview20-glitchtesting-desktop-cross-platformUse when testing desktop cross platform is required during desktop product work, especially when the result must be traceable…casioreview20-glitchtesting-desktop-file-associationsUse when testing desktop file associations is required during desktop product work, especially when the result must be traceable…casioreview20-glitchtesting-desktop-installationUse when testing desktop installation is required during desktop product work, especially when the result must be traceable…casioreview20-glitchtesting-developer-compatibilityUse when testing developer compatibility is required during developer-tools product work, especially when the result must be…casioreview20-glitchtesting-ecommerce-refundsUse when testing ecommerce refunds is required during ecommerce product work, especially when the result must be traceable…casioreview20-glitchtesting-ecommerce-taxUse when testing ecommerce tax is required during ecommerce product work, especially when the result must be traceable…casioreview20-glitchtesting-enterprise-isolationUse when testing enterprise isolation is required during enterprise product work, especially when the result must be traceable…casioreview20-glitchtesting-extension-cross-browserUse when testing extension cross browser is required during browser-extensions product work, especially when the result must be…casioreview20-glitchtesting-extension-cspUse when testing extension csp is required during browser-extensions product work, especially when the result must be traceable…casioreview20-glitchtesting-game-balanceUse when testing game balance is required during games product work, especially when the result must be traceable, independently…casioreview20-glitchtesting-game-determinismUse when testing game determinism is required during games product work, especially when the result must be traceable…casioreview20-glitchtesting-game-performanceUse when testing game performance is required during games product work, especially when the result must be traceable…casioreview20-glitchtesting-interactive-3d-performanceUse when testing interactive 3d performance is required during interactive-3d product work, especially when the result must be…casioreview20-glitchtesting-mobile-deep-linksUse when testing mobile deep links is required during mobile product work, especially when the result must be traceable…casioreview20-glitchtesting-mobile-devicesUse when testing mobile devices is required during mobile product work, especially when the result must be traceable…casioreview20-glitchtesting-physical-ai-deployment-boundariesUse when testing physical ai deployment boundaries is required during physical-ai product work, especially when the result must…casioreview20-glitchtesting-product-usabilityUse when testing product usability is required during ux work, especially when the result must be traceable, independently…casioreview20-glitchtesting-production-rollbackUse when testing production rollback is required during operations work, especially when the result must be traceable…casioreview20-glitchtesting-saas-entitlementsUse when testing saas entitlements is required during saas product work, especially when the result must be traceable…casioreview20-glitchtesting-skill-behaviorUse when testing skill behavior is required during meta work, especially when the result must be traceable, independently…casioreview20-glitchtext-classificationLLM-based text classification: codebook, validation, agreement statistics.brycewang-stanfordtext-classificationLLM-based text classification. Codebook, validation, agreement statistics.majiayu000texture-pipelineTexture skill for compression, atlasing, and streaming.a5c-aiwritesthe-oracleThis skill should be used when the user asks to "use the oracle" or "ask the oracle" for deep research, analysis, or…majiayu000the-oracleThis skill should be used when the user asks to "use the oracle" or "ask the oracle" for deep research, analysis, or…majiayu000think-harder4-phase structured analysis wrapper for vibe pre-routing (compatible with claude-code-settings think-harder semantics).majiayu000thinking-model-combinationCombine multiple mental models for richer analysis. Use for complex problems requiring multiple lenses, high-stakes decisions, or…majiayu000thinking-model-routerRoute to the right mental model based on your domain and problem type. The single entry point for all thinking skills.majiayu000thinking-model-selectionChoose the right mental model for the problem at hand. Use when facing new problems, when current approaches fail, or when you…majiayu000threejs-gltf-loadingLoad glTF/GLB models in three.js with GLTFLoader and play their skinned animations with AnimationMixer, including…gamedev-skillsthreejs-materials-lightingLight and shade a three.js scene: choose materials (MeshStandardMaterial PBR vs unlit MeshBasicMaterial), add…gamedev-skillstiling-treeExhaustive problem space exploration using the MIT Synthetic Neurobiology "tiling tree" method. Partitions a problem into MECE…majiayu000tket-compilerCambridge Quantum (Quantinuum) t|ket> compiler skill for platform-independent circuit optimizationmajiayu000writes
← Prev53 / 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