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
1,4411,488 · page 31 / 104
export-pipelineProduction export from Blender to FBX, GLTF, OBJ, USD, and Alembic with scale, pivot, rotation, normals, materials, animation…arjun988extract-hyperparametersIdentify and document model hyperparameters from papers. Use when setting up training configurations.majiayu000extract-insightsThis skill should be used when user wants to learn from their collected references, synthesize patterns across sources, or turn…majiayu000extractExtract decisions and learnings from Claude session transcripts. Triggers: "extract learnings", "process pending", SessionStart…majiayu000extract-promptAnalyze a conversation and extract a reusable prompt that captures the successful pattern. Generalizes specific instructions into…majiayu000extract-promptTurn successful interactions into reusable promptsmajiayu000extracting-user-painUse when extracting user pain is required during research work, especially when the result must be traceable, independently…casioreview20-glitchfacial-animationFacial animation skill for blend shapes and lip sync.a5c-aiwritesfailure-recoveryRecovery protocols for stuck agents, context exhaustion, build failures, and confusion. Use when agent is looping, responses…majiayu000writesfaion-llm-integrationLLM APIs: OpenAI, Claude, Gemini, local LLMs, prompt engineering, function calling.majiayu000writesfaion-make-agents-skillCreates, edits, updates, or modifies Claude Code custom agents (subagents). Use when user asks to create agent, edit agent…majiayu000writesfaion-ml-engineerML Engineer role: LLM APIs (OpenAI, Claude, Gemini), embeddings, RAG pipelines, fine-tuning, LangChain, LlamaIndex, vector…majiayu000writesfaion-ml-opsML operations: fine-tuning (LoRA, QLoRA), model evaluation, cost optimization, observability.majiayu000writesfaion-rag-engineerRAG engineering: embeddings, chunking, vector databases, hybrid search, reranking.majiayu000writesfairlearn-bias-detectorFairness assessment skill using Fairlearn for bias detection, mitigation, and compliance reporting.a5c-aiwritesfairlearn-bias-detectorFairness assessment skill using Fairlearn for bias detection, mitigation, and compliance reporting.majiayu000writesfaissFacebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU…Orchestra-Researchfast-analysisAnalyze exported game files to assess gameplay, model decisions, and likely bugs without raw logs. Use for quick game triage.majiayu000fastmcpFastMCP is a Python framework for building Model Context Protocol (MCP) servers that expose tools, resources, and prompts to…majiayu000fatigue-analysisSpecialized skill for fatigue life assessment and durability prediction under cyclic loading conditionsmajiayu000writesfeast-feature-storeFeature store management skill for online/offline feature serving, feature registration, and training-serving consistency.a5c-aiwritesfeast-feature-storeFeature store management skill for online/offline feature serving, feature registration, and training-serving consistency.majiayu000writesFeature EngineeringCreate and transform features using encoding, scaling, polynomial features, and domain-specific transformations for improved…majiayu000feature-engineering-helperConfigure with feature engineering helper operations. Auto-activating skill for ML Training. Triggers on: feature engineering…majiayu000writesfeature-importance-analyzerFeature Importance Analyzer - Auto-activating skill for ML Training. Triggers on: feature importance analyzer, feature importance…majiayu000writesfeature-store-connectorExecute feature store connector operations. Auto-activating skill for ML Deployment. Triggers on: feature store connector…majiayu000writesfeedback-observingRead agent interaction logs across packs and detect operational patterns. Emits state-transition FeedbackEvents for…majiayu000writesfercracix33-poli2-clean-architecture-claude-skills-agent-creatorPurpose: Guide creation of Claude Code agents following Anthropic official best practices.'majiayu000fermi-surfaceThis skill group covers the calculation and visualization of Fermi surfaces -- the constant-energy surface in reciprocal space…majiayu000fetch-arxiv-papersFetch recent AI/ML research papers from arXiv RSS feeds and store them in memory. Uses RSS tool for fetching and memory MCP for…majiayu000fetch-rss-feedsFetch articles from RSS/Atom feeds and store them in memory for analysis. Uses the rss tool for fetching and memory MCP for…majiayu000few-shot-example-genFew-shot example generation and optimization for improved LLM performancea5c-aiwritesfew-shot-examplesCurated few-shot examples for construction AI tasks: classification, extraction, analysis. Domain-specific examples for improved…majiayu000find-skillFind and install skills from the Orthogonal skill library. Use when you need capabilities you don't have, want to discover…gooseworks-aifinding-duplicate-functionsUse when auditing a codebase for semantic duplication - functions that do the same thing but have different names or…majiayu000FinOps AI ExpertCost optimization for AI workloads - model selection, GPU sizing, commitment strategies, and multi-cloud cost managementmajiayu000fixing-bugs-with-tddUse when fixing bugs with tdd is required during implementation work, especially when the result must be traceable, independently…casioreview20-glitchflow-network-builderModel optimization problems as network flow problemsa5c-aiwritesfluid-simulationWater physics skill for fluid dynamics and buoyancy systems.a5c-aiwritesFlutter/Dart DevelopmentSpecialized skill for Flutter app development and Dart programminga5c-aiflux-imageGenerate images with FLUX models (Black Forest Labs) via inference.sh CLI. Models: FLUX Dev LoRA, FLUX.2 Klein LoRA with custom…majiayu000fmodFMOD Studio integration skill for events, parameters, and mixing.a5c-aiwritesfoggy-modeUse when the user asks for foggy-mode or brain-fog-mode, or has low working memory, brain fog, fatigue, sleep debt, illness…softcaneforce-updateGenerates a minimum version enforcement system with hard-block and soft-prompt update flows, App Store redirect, and remote…rshankraswritesprompt-forgeShape, refine, and stabilize human intent into a canonical prompt artifact without executing anything. Iteratively clarifies…majiayu000forgecad-grade-modelGrade a ForgeCAD or CAD-as-code model against a requirement, brief, prompt, reference, or acceptance criteria with evidence and a…ForgeCADforgecad-image-promptWrite builder-honest AI image prompts from a concrete ForgeCAD model, build brief, HLD, or LLD without hiding how the artifact is…ForgeCADforgecad-reconstruct-cad-fileReconstruct a readable parametric ForgeCAD model from an existing CAD or mesh file such as STL, OBJ, 3MF, STEP, or STP.ForgeCAD
← Prev31 / 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