langchain-ai/deep-agents-core
INVOKE THIS SKILL when building ANY Deep Agents application. Covers create_deep_agent(), harness architecture, SKILL.md format, and configuration options.
INVOKE THIS SKILL when building ANY Deep Agents application. Covers create_deep_agent(), harness architecture, SKILL.md format, and configuration options.
npx skills add https://github.com/langchain-ai/langchain-skills/tree/main/skills/deep-agents-coreINVOKE THIS SKILL when building ANY Deep Agents application. Covers create_deep_agent(), harness architecture, SKILL.md format, and configuration options.
This repo contains 11 individual skills — each has its own dedicated page.
INVOKE THIS SKILL when your Deep Agent needs memory, persistence, or filesystem access. Covers StateBackend (ephemeral), StoreBackend (persistent), FilesystemMiddleware, and CompositeBackend for routing.
INVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, TodoList for planning, and HITL interrupts.
INVOKE THIS SKILL at the START of any LangChain/LangGraph/Deep Agents project, before writing any agent code. Determines which framework layer is right for the task: LangChain, LangGraph, Deep Agents, or a combination. Must be consulted before other agent skills.
INVOKE THIS SKILL when setting up a new project or when asked about package versions, installation, or dependency management for LangChain, LangGraph, LangSmith, or Deep Agents. Covers required packages, minimum versions, environment requirements, versioning best practices, and common community tool packages for both Python and TypeScript.
Create LangChain agents with create_agent, define tools, and use middleware for human-in-the-loop and error handling.
INVOKE THIS SKILL when you need human-in-the-loop approval, custom middleware, or structured output. Covers HumanInTheLoopMiddleware for human approval of dangerous tool calls, creating custom middleware with hooks, Command resume patterns, and structured output with Pydantic/Zod.
INVOKE THIS SKILL when building ANY retrieval-augmented generation (RAG) system. Covers document loaders, RecursiveCharacterTextSplitter, embeddings (OpenAI), and vector stores (Chroma, FAISS, Pinecone).
INVOKE THIS SKILL when writing ANY LangGraph code. Covers StateGraph, state schemas, nodes, edges, Command, Send, invoke, streaming, and error handling.
INVOKE THIS SKILL when implementing human-in-the-loop patterns, pausing for approval, or handling errors in LangGraph. Covers interrupt(), Command(resume=...), approval/validation workflows, and the 4-tier error handling strategy.
INVOKE THIS SKILL when your LangGraph needs to persist state, remember conversations, travel through history, or configure subgraph checkpointer scoping. Covers checkpointers, thread_id, time travel, Store, and subgraph persistence modes.
Dispatches many independent items in parallel: create a table, fan out to subagents, aggregate results. One row = one unit of work.
Fully local multi-agent swarm intelligence simulation engine using Neo4j + Ollama for public opinion, market sentiment, and social dynamics prediction.
An open-source agentic AI system for real-time and scheduled research on user-defined topics with custom skills. Uses local models, web search, and Python to generate multi-format reports, chat with results, and deliver them to Discord.
A comprehensive, vendor-agnostic framework for consistent AI-assisted development workflows - standardized instructions and commands that work seamlessly across Claude, Gemini, Copilot, and local AI models. See also: https://github.com/JacobPEvans/claude-code-plugins
召唤一个影子，问问他们真心在想什么，预演即将发生的对话。Build a digital shadow of anyone real. Ask what they were actually thinking (/seance). Rehearse hard conversations before they happen (/rehearse). A Claude Code Agent Skill.
A curated collection of autonomous AI agent skills powered by Skillfish. Specialized tools for productivity, document management, and custom LLM workflows.
Store and serve AI memory for identity, preferences, decisions, and projects via REST API or MCP for better context across assistants