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
1,6811,728 · page 36 / 104
langgraph-implementationImplements stateful agent graphs using LangGraph. Use when building graphs, adding nodes/edges, defining state schemas…majiayu000langgraphExpert guidance for building stateful, multi-actor AI agents with LangGraph - graphs, nodes, edges, state management, and agent…majiayu000writeslanggraph-overview理解 LangGraph:用于构建有状态、长期运行 Agent 的低级编排框架,具有持久执行、流式传输和人机交互能力majiayu000langgraphLangGraph skill for building stateful agent graphs, subgraphs, checkpoints, conditional flows, parallel execution, streaming, and…majiayu000langgraph-state在 LangGraph 中管理状态:模式、reducer、通道和消息传递,用于协调 Agent 执行majiayu000langgraph-supervisorLangGraph supervisor-worker pattern. Use when building central coordinator agents that route to specialized workers, implementing…majiayu000langsmith-evaluatorINVOKE THIS SKILL when building evaluation pipelines for LangSmith. Covers three core components: (1) Creating Evaluators -…majiayu000langsmith-testing-skillCRITICAL for RAG: Every RAG query MUST be traced in LangSmith for observability. Silent failures (bad retrieval, hallucinations)…majiayu000langsmith-tracingLangSmith tracing and debugging setup for LLM applications. Configure observability, capture traces, and enable debugging for…a5c-aiwriteslatent-briefingThis skill should be used when the user asks to \"share memory between agents\", \"KV cache compaction for multi-agent\"…guanyanglatex-econ-modelWrite and typeset economic models in LaTeX with proper notationbrycewang-stanfordlearn-from-repo用于深度理解研究型代码仓库的方法论 skill。当用户想要学习一个新的 ML/AI repo、理解其实现与论文的对应关系、或为后续修改做准备时使用。结合对话式学习风格,逐组件拆解模型实现。majiayu000learnProvides autonomous project pattern learning by analyzing the codebase to discover development conventions, architectural…majiayu000writeslearn-movieAnalyze movies to extract cinematographic techniques and store them in memory.majiayu000learnRuns the learning cycle on all LearningAgent sessions with pending transcripts. Identifies issues, investigates root causes, and…majiayu000learn-voiceTrain RVC voice models from artist names. Full pipeline: YouTube search, download, stem separation, preprocessing, training, and…majiayu000writeslearning-from-agent-failuresUse when learning from agent failures is required during meta work, especially when the result must be traceable, independently…casioreview20-glitchlearning-sdk-integrationIntegration patterns and best practices for adding persistent memory to LLM agents using the Letta Learning SDKmajiayu000lettaLetta framework for building stateful AI agents with long-term memory. Use for AI agent development, memory management, tool…majiayu000libagentlibagent - Agent orchestration library for conversational AI. AgentMind class coordinates LLM completions, memory management…majiayu000libvectorlibvector - Vector similarity search. VectorIndex stores embeddings with metadata and performs cosine similarity search.…majiayu000lindy-ci-integrationConfigure CI/CD pipelines for testing Lindy AI agent integrations. Use when setting up automated testing, configuring GitHub…jeremylongshorewriteslindy-incident-runbookIncident response procedures for Lindy AI agent failures and outages. Use when responding to incidents, troubleshooting agent…jeremylongshorewriteslisa-learnThis skill should be used when analyzing a downstream project's git diff after Lisa was applied to identify improvements that…majiayu000lisaLisa - intelligent assistant for memory and tasks. Triggers on 'lisa', 'hey lisa', or addressing lisa directly.majiayu000lisaLisa - intelligent assistant for memory and tasks. Triggers on 'lisa', 'hey lisa', or addressing lisa directly.majiayu000lit-synthesisDeep reading and synthesis of literature corpus. Theoretical mapping, thematic clustering, and debate identification using Zotero…majiayu000litellmWhen calling LLM APIs from Python code. When connecting to llamafile or local LLM servers. When switching between…majiayu000literature-filterFilter, validate and organize literature search results. LOAD THIS SKILL WHEN: User has search results and needs to "過濾", "篩選"…majiayu000llamaMeta Llama open-source LLM family. Use for local AI.majiayu000llamaindex-agentLlamaIndex agent and query engine setup for RAG-powered agentsa5c-aiwritesllamaindex-agentLlamaIndex agent and query engine setup for RAG-powered agentsmajiayu000writesLLMImplement large language model (LLM) chat completions using the z-ai-web-dev-sdk. Use this skill when the user needs to build…majiayu000llm-app-patternsProduction-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps…majiayu000llm-app-patternsProduction-ready patterns for building LLM applications, inspired by [Dify](https://github.com/langgenius/dify) and industry best…majiayu000llm-application-dev-langchain-agentYou are an expert LangChain agent developer specializing in production-grade AI systems using LangChain 0.1+ and LangGraph.majiayu000llm-application-dev-langchain-agentYou are an expert LangChain agent developer specializing in production-grade AI systems using LangChain 0.1+ and LangGraph.majiayu000llm-application-devBuilding applications with Large Language Models - prompt engineering,majiayu000llm-application-devBuilding applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. Use for AI-powered…majiayu000llm-application-dev-prompt-optimizeYou are an expert prompt engineer specializing in crafting effective prompts for LLMs through advanced techniques including…majiayu000llm-application-dev-prompt-optimizeYou are an expert prompt engineer specializing in crafting effective prompts for LLMs through advanced techniques including…majiayu000llm-application-dev-prompt-optimizeYou are an expert prompt engineer specializing in crafting effective prompts for LLMs through advanced techniques including…sickn33llm-application-patternsUse when building LLM applications: prompt engineering, structured output, agents, RAG integration, memory management, or…majiayu000llm-application-patternsThis skill should be used when building production LLM applications in any language. It applies when implementing predictable AI…majiayu000llm-architectUse when user needs LLM system architecture, model deployment, optimization strategies, and production serving infrastructure.…majiayu000llm-as-computerExecute programs on a compiled transformer stack machine where every instruction fetch and memory read is a parabolic attention…majiayu000llm-calibration-logprobsAnalyze LLM token logprobs and calibration. Use for per-decision confidence, ECE, Brier scores, reliability diagrams, and…majiayu000llm-calibration-logprobsLLM token logprobs and calibration. Per-decision confidence, ECE, Brier, reliability diagrams, low-confidence triage.majiayu000
← Prev36 / 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