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
1,3931,440 · page 30 / 104
dspy-rubyThis skill should be used when working with DSPy.rb, a Ruby framework for building type-safe, composable LLM applications. Use…majiayu000dspy-simba-optimizerThis skill should be used when the user asks to "optimize with SIMBA", "use Bayesian optimization", "optimize agents with custom…majiayu000writesdspyCompile prompts into self-improving pipelines with signatures, modules, optimizers, and programmatic prompt engineeringmajiayu000duetTwo-party posture — user as director, agent as executor; every fork, tradeoff, or choice surfaced via batched AskUserQuestion…majiayu000early-stopping-callbackManage early stopping callback operations. Auto-activating skill for ML Training. Triggers on: early stopping callback, early…majiayu000writesEdge Deployment SkillML model optimization and deployment on robot edge devices (Jetson, embedded)a5c-aiwritesEdge Deployment SkillML model optimization and deployment on robot edge devices (Jetson, embedded)majiayu000writesEdge Model CompressionEdge Model Compression enables deployment of large, accurate machine learning models on resource-constrained edge devices through…majiayu000Effect AIThis skill should be used when the user asks about "Effect AI", "@effect/ai", "LLM integration", "AI tool use", "AI execution…majiayu000effect-systemsExpert skill for designing and implementing algebraic effect systems including effect annotation, inference, handlers…a5c-aiwriteselectron-memory-profilerProfile Electron app memory usage, detect leaks, analyze renderer process memory, and optimize memory consumptiona5c-aiwriteseleven-agent-managerManage ElevenLabs Conversational AI agent configuration including prompts, voice settings, MCP servers, and conversation…majiayu000eliciting-user-workflowsUse when eliciting user workflows is required during ux work, especially when the result must be traceable, independently…casioreview20-glitchelizaos-expert-2026Expert ElizaOS plugin and agent development (January 2026). Use when (1) Building ElizaOS plugins, (2) Creating AI agent…majiayu000embedded-cryptoEmbedded cryptographic operations and secure element integration. Expert skill for hardware crypto accelerators, secure key…a5c-aiwritesembedding-strategy-skillPROTECTED: Manage chunking strategies and embedding dimensions. Changes require user approval + full impact analysis.'majiayu000enetENet reliable UDP skill for channels and packet fragmentation.a5c-aiwritesenforcing-accessibilityUse when enforcing accessibility is required during ux work, especially when the result must be traceable, independently…casioreview20-glitchenforcing-domain-languageUse when enforcing domain language is required during implementation work, especially when the result must be traceable…casioreview20-glitchenforcing-saas-quotasUse when enforcing saas quotas is required during saas product work, especially when the result must be traceable, independently…casioreview20-glitchengineering-features-for-machine-learningCreate, encode, transform, and select features before model fitting. Use when the user needs feature engineering decisions or…majiayu000writesengineering-manufacturable-productsUse when engineering manufacturable products is required during physical-products product work, especially when the result must…casioreview20-glitchenhancerTransform simple prompts into comprehensive, context-aware prompts. Use for prompt enhancement, requirements analysis, and…majiayu000writesenterprise-discoverDeep codebase learning agent. Run FIRST on any new project, any new worktree, or whenever hardcoded paths break. Produces…majiayu000entity-memory-extractionEntity and fact extraction for user profiling and personalizationa5c-aiwritesepic-sdkEpic Online Services skill for launcher integration.a5c-aiwriteseptr2-price-analysisThis skill helps you query and analyze electricity market prices from Turkey's EPIAS Transparency Platform using the eptr2 Python…majiayu000error-analysisThis skill should be used when analyzing errors, stack traces, and logs to identify root causes and implement fixes.majiayu000eureka-context-engineering-v6.1Complete Eureka V6.1 Context Engineering suite with observability, structured output, and hybrid memorymajiayu000event-loopExpert skill for high-performance event-driven I/O programming and optimizationa5c-aiwriteseverything-openai-codexDevelopment conventions and patterns for Everything OpenAI Codex. JavaScript project with conventional commits.mturacevla-vlaEdgeVLA - Open-source edge vision-language-action model for robotics. Standardizes Open-X Embodiment datasets for consistent VLA…majiayu000evo-advanced-elicitationPush the LLM to reconsider refine and improve its recent output. Use when the user asks for advanced elicitation.majiayu000evolvePopulation-based evolutionary search for code optimization. Maintains k candidates, evaluates against a fitness function, selects…majiayu000evolving-skill-packsUse when evolving skill packs is required during meta work, especially when the result must be traceable, independently…casioreview20-glitchexa-researchComprehensive research skill using Exa AI tools for web search and code context retrieval. Use when conducting research on…majiayu000example-skillBrief description of what this skill does and when the model should activate it. Use when [describe the user's intent or…jeremylongshorewritesprompt-execExecute the forged prompt exactly as written, with no reinterpretation. Requires explicit user consent and a ready prompt…majiayu000explain-decisionsAlways explain your reasoning before making changes Use when configuring AI agent workflows and patterns. Agent Behavior category…majiayu000explainable-aiMake AI model decisions interpretable and transparent. Use for: implementing SHAP for feature importance analysis, using LIME for…majiayu000explaining-machine-learning-modelsBuild this skill enables AI assistant to provide interpretability and explainability for machine learning models. it is triggered…majiayu000writesexploreMeta-skill for internal codebase exploration at varying depths (quick/deep/architecture)majiayu000writesexplore-dnn-modelManual invocation only; use only when the user explicitly requests `explore-dnn-model` by name. Explore how to run a given DNN…majiayu000exploreRead-only codebase exploration: discovery, structural reading, and emission of architecture/pattern/tooling/dependency summaries.…majiayu000explore-skillYou are an expert codebase exploration specialist with deep understanding of code patterns, architectural structures, and…majiayu000exploring-edge-usersUse when exploring edge users is required during creativity work, especially when the result must be traceable, independently…casioreview20-glitchexploring-zero-resource-designsUse when exploring zero resource designs is required during creativity work, especially when the result must be traceable…casioreview20-glitchexpo-examplesExpo's official example projects — the expo/examples repo of ~70 `with-*` integrations (Stripe, Clerk, Supabase, OpenAI, maps…sickn33
← Prev30 / 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