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 29,140 codex 4,755 cursor 3,111 copilot 976 windsurf 55 cline 34

CategoryWorkflow & Productivity 4,979 AI & Agents 3,037 Data & Analytics 2,345 Code Review & Quality 1,376 Backend & API 1,244 Security 1,194 Design & Presentation 1,154 Documentation 965 Content & Marketing 916 Testing & QA 777 DevOps & Cloud 576 Databases 550 Frontend 469 Business & Finance 328 Media & Video 257 Other 9,833

4,965 found

2,593–2,640 · page 55 / 104

unsloth-inferenceUnsloth models can be deployed using native optimized inference or through production serving engines like vLLM and SGLang.…majiayu000

unsloth-long-contextUnsloth enables training on extreme context lengths (up to 89K+ on a single 80GB GPU) by utilizing manually derived Triton…majiayu000

unsloth-loraConfiguring and optimizing 16-bit Low-Rank Adaptation (LoRA) and Rank-Stabilized LoRA (rsLoRA) for efficient LLM fine-tuning…majiayu000

unsloth-orpoUnsloth-orpo facilitates one-step preference alignment using Odds Ratio Preference Optimization (ORPO). Unlike DPO, which…majiayu000

unsloth-quantizationUnsloth utilizes advanced quantization techniques to reduce the memory footprint of LLM fine-tuning. This includes "Dynamic…majiayu000

unsloth-sttUnsloth supports fine-tuning for Speech-to-Text (STT) models like OpenAI Whisper. By applying its optimized LoRA pipeline to…majiayu000

update-llm-modelsAutonomously research and update the default lightweight LLM models in `src/core/llm.ts` using web search to ensure the most…majiayu000

updating-knowledgeSystematic research methodology for building comprehensive, current knowledge on any topic. Requires web_search tool. Use when…majiayu000

urdf-sdf-modelExpert skill for robot model creation and validation in URDF and SDF formats. Generate URDF files with proper link-joint…a5c-aiwrites

usage-pattern-analyzerClaude Code 도구 사용 패턴 및 생산성 트렌드 분석. 반복 작업 감지, 시간대별 생산성, 도구 사용 빈도 시각화. "패턴 분석", "사용 통계", "productivity" 등의 요청 시 자동 적용.majiayu000

user-input-protocolStructured checkpoint format for requesting human input. When an agent needs a decision, it must stop, present context, show…majiayu000

using-claude-code-cliInvoke Claude Code CLI from Python orchestrators and shell scripts. Use when asked to "spawn claude as subprocess", "automate…majiayu000writes

using-denial-laddersUse when using denial ladders is required during creativity work, especially when the result must be traceable, independently…casioreview20-glitch

using-forge-osUse when using forge os is required during kernel work, especially when the result must be traceable, independently reviewable…casioreview20-glitch

using-llm-specialistLLM specialist router to prompt engineering, fine-tuning, RAG, evaluation, and safety skills.majiayu000

using-ml-productionRouter skill directing to deployment, optimization, MLOps, and monitoring guides.majiayu000

using-pytorch-engineeringRoutes to appropriate PyTorch specialist skill based on symptoms and problem typemajiayu000

using-superpowersUse when starting any conversation. Establishes how to find and use skills, requiring skill invocation before any response.a5c-ai

utility-aiUtility AI skill for scoring functions and decision making.a5c-aiwrites

validating-observabilityUse when validating observability is required during operations work, especially when the result must be traceable, independently…casioreview20-glitch

validating-physical-product-safetyUse when validating physical product safety is required during physical-products product work, especially when the result must be…casioreview20-glitch

validating-source-credibilityUse when validating source credibility is required during research work, especially when the result must be traceable…casioreview20-glitch

vasp_aseProfessional skill for setting up, executing, and debugging VASP DFT calculations using the Atomic Simulation Environment (ASE).majiayu000

vaultr-index-knowledgeBuilds and refreshes domain-based index files for the Vaultr knowledge base. Use this skill whenever the user wants to build…skoowoo

vector-index-tuningOptimize vector index performance for latency, recall, and memory. Use when tuning HNSW parameters, selecting quantization…majiayu000

vector-index-tuningOptimize vector index performance for latency, recall, and memory. Use when tuning HNSW parameters, selecting quantization…sickn33

vector-index-tuningOptimize vector index performance for latency, recall, and memory. Use when tuning HNSW parameters, selecting quantization…majiayu000

vector-index-tuningOptimize vector index performance for latency, recall, and memory. Use when tuning HNSW parameters, selecting quantization…wshobson

vector-memoryHNSW vector search for pattern similarity retrieval and knowledge graph maintenance with PageRank scoring, community detection…a5c-aiwrites

vector-memoryHNSW vector search for pattern similarity retrieval and knowledge graph maintenance with PageRank scoring, community detection…majiayu000writes

vector-memoryPersistent vector memory for Claude Code via LanceDB. Use when: remembering across sessions, storing lessons, recalling past…majiayu000

vector-searchImplement vector search for knowledge retrieval. Use when adding RAG, semantic search, knowledge base features, or context…majiayu000writes

vehicle-physicsVehicle simulation skill for wheel colliders, suspension, and aerodynamics.a5c-aiwrites

vercel-ai-gatewayVercel AI Gateway provider fallback and host order configuration. Use when working with aiGateway, hostOrder, getGatewayOptions…majiayu000

verify-promptCompare original and distilled prompts to verify the distillation is faithful and lossless. Checks completeness, accuracy, and…majiayu000

verify-promptValidate distilled prompts preserve essential instructionsmajiayu000

verifying-interface-completenessUse when verifying interface completeness is required during ux work, especially when the result must be traceable, independently…casioreview20-glitch

vertex-ai-deployerVertex Ai Deployer - Auto-activating skill for ML Deployment. Triggers on: vertex ai deployer, vertex ai deployer Part of the ML…majiayu000writes

vexorVector-powered CLI for semantic file search with a Claude/Codex skillmajiayu000

vhdl-languageDeep expertise in VHDL language constructs, IEEE 1076 standard compliance, and synthesis coding guidelines. Expert skill for…a5c-aiwrites

vibe-agentsGenerate AGENTS.md and AI configuration files for your project. Use when the user wants to create agent instructions, set up AI…majiayu000writes

← Prev55 / 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

Collections, ranked →

Which skill collections are moving this week, from our own snapshots.

Open Source Radar →

The repositories behind these skills, watched daily.

The makers →

Who publishes the skills you install.

Startup rankings →

The companies building in the same ecosystem.