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
2,6412,688 · page 56 / 104
vibe-agentsGenerate AGENTS.md and AI configuration files for your project. Use when the user wants to create agent instructions, set up AI…majiayu000writesvision-multimodalVision and multimodal capabilities for Claude including image analysis, PDF processing, and document understanding. Activate for…majiayu000writesvision-utilitiesGuide for using vision utilities in speedy_utils, including fast GPU image loading, memory-mapped datasets, and notebook…majiayu000vlm-ocr-pipelineVLM-based OCR pipeline: model selection, prompts, architecture, evaluation.brycewang-stanfordvoice-agentsElevenLabs voice agent creation for client discovery and feedback calls. Use this skill when creating AI voice agents, setting up…majiayu000voice-ai-engine-developmentBuild real-time conversational AI voice engines using async worker pipelines, streaming transcription, LLM agents, and TTS…majiayu000voice-aiProduction voice AI agents with sub-500ms latency. Groq LLM, Deepgram STT, Cartesia TTS, Twilio integration. No OpenAI. Use when…majiayu000voice-chatVoice chat skill for echo cancellation and codec optimization.a5c-aiwritesvoice-chatVoice-controlled Claude Code - speak commands, hear responses in Olivia voicemajiayu000voice-input-processorA pre-processor skill for input that arrives via voice-to-text or as unstructured, free-flowing thought. Use when receiving long…majiayu000voice-refineTransform verbose voice input into optimized Claude promptsmajiayu000VoltAgent DevelopmentCreate and configure VoltAgent AI agents with tools, memory, hooks, and sub-agents. Use when building AI agents, adding agent…majiayu000vqc-trainerVariational quantum classifier training skill with gradient optimizationmajiayu000writesvta-memoryReward and motivation system for AI agents. Dopamine-like wanting, not just doing. Part of the AI Brain series.majiayu000vta-memoryReward and motivation system for AI agents. Dopamine-like wanting, not just doing. Part of the AI Brain series.majiayu000vulkan-computeVulkan compute shader development and pipeline configuration. Generate GLSL/HLSL compute shaders, compile to SPIR-V, configure…a5c-aiwriteswandb-experiment-loggerExecute wandb experiment logger operations. Auto-activating skill for ML Training. Triggers on: wandb experiment logger, wandb…majiayu000writeswandb-experiment-trackerWeights & Biases integration skill for experiment tracking, hyperparameter sweeps, and artifact versioning.a5c-aiwriteswandb-plotShared skill entrypoint for Claude Code. See the canonical skill file at: wandb-plot/SKILL.mdmajiayu000wannier-functionsThis skill group covers the construction of maximally localized Wannier functions (MLWFs) from DFT Bloch states. Wannier…majiayu000wasm-agentCreate and manage sandboxed WASM agents for isolated code executionmajiayu000writeswavecap-whisperTune WaveCap Whisper model settings. Use when the user wants to change model size, adjust decoding parameters, configure prompts…majiayu000web-researchUse this skill for requests related to web research; it provides a structured approach to conducting comprehensive web researchmajiayu000web-researchUse this skill for requests related to web research; it provides a structured approach to conducting comprehensive web research.majiayu000web-searchAdvanced web search capability using the gemini command for gathering current, relevant information. Prefer this skill over…majiayu000writesweb-to-markdownUse ONLY when the user explicitly says: 'use the skill web-to-markdown ...' (or 'use a skill web-to-markdown ...'). Converts…softaworkswebresearcherAlso called "wr". Optional research agent for broad multi-source research without polluting context. Use when user requests it or…majiayu000webshop-option-selectorThis skill selects product options or variants (such as size, color, or quantity) on a product detail page based on user…zjunlpwebshop-price-checkerThis skill scans product listings or detail pages to verify if an item's price meets a specified budget constraint. It is…zjunlpwebshop-product-detail-navigatorNavigates to and interacts with a specific product's detail page. This skill is triggered after a candidate product ID is…zjunlpwebshop-product-evaluatorEvaluates product listings against user requirements such as price limits and feature matches to identify viable options. Use…zjunlpwebshop-query-parserThis skill extracts key constraints and product requirements from a user's shopping query. It should be triggered when the agent…zjunlpwebshop-search-constructorThis skill formulates an effective search query from structured product criteria. It is used when initiating a product search on…zjunlpwebshop-search-formulatorThis skill generates effective search keywords based on parsed product criteria. It is triggered after query parsing, when the…zjunlpwebshop-variant-chooserThis skill selects a product variant (e.g., size, quantity) from available options on a product detail page. It is triggered when…zjunlpwhen-optimizing-agent-learning-use-reasoningbank-intelligenceImplement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvementmajiayu000when-optimizing-agent-learning-use-reasoningbank-intelligence/============================================================================/majiayu000when-optimizing-prompts-use-prompt-architectComprehensive framework for analyzing, creating, and refining prompts for AI systems using evidence-based techniquesmajiayu000when-optimizing-prompts-use-prompt-architect/============================================================================/majiayu000when-optimizing-prompts-use-prompt-optimization-analyzer/============================================================================/majiayu000whole-regrouperPhân tích, gom nhóm, và ĐỒNG BỘ THÔNG MINH giữa Tổng Quan listing và actual group headers. v5.1.0: Intelligent Analysis with…majiayu000writeswhylabs-monitorWhyLabs integration skill for ML observability, profile logging, and anomaly detection.a5c-aiwriteswhylabs-monitorWhyLabs integration skill for ML observability, profile logging, and anomaly detection.majiayu000writeswjs-evaling-voicedrop-promptsUse when 王建硕 wants to evaluate whether a change to VoiceDrop's 挖矿 system prompt is actually better than the live version — runs…jianshuowork-decompositionDecompose goals into MEOWs (Molecular Expressions of Work) - trackable atomic units following Gas Town's bead-based work model.a5c-aiwritesworkerExecute beads autonomously within a track. Handles bead-to-bead context persistence via Agent Mail, uses preferred tools from…majiayu000workerExecute beads autonomously within a track. Handles bead-to-bead context persistence via Agent Mail, uses preferred tools from…majiayu000Workers AIThis skill should be used when the user asks about "Workers AI", "AI models", "text generation", "embeddings", "semantic search"…majiayu000
← Prev56 / 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