INVOCA ESTA HABILIDAD cuando tu Deep Agent necesite memoria, persistencia o acceso al sistema de archivos. Cubre StateBackend (efímero), StoreBackend (persistente), FilesystemMiddleware y CompositeBackend para enrutamiento.
Esta habilidad proporciona una arquitectura modular de backends de memoria y almacenamiento para Deep Agents. Incluye StateBackend para almacenamiento efímero de estado en memoria, StoreBackend para persistencia a largo plazo, FilesystemMiddleware para operaciones con el sistema de archivos del agente, y CompositeBackend que permite enrutar automáticamente las solicitudes al backend correcto según el contexto. Es útil para agentes que necesitan recordar información entre pasos de ejecución o mantener estado a través de sesiones. Funciona en plataformas como Claude Code, Cursor, Codex, y es compatible con cualquier implementación de Deep Agent que siga esta interfaz. Su diseño permite combinarlos fácilmente para construir sistemas de memoria híbridos y escalables.
npx skills add https://github.com/langchain-ai/langchain-skills/tree/main/skills/deep-agents-memoryInstalled? Explore more Productividad y colaboración skills: steipete/gemini, steipete/gh-issues, steipete/skill-creator · View all 6 →
INVOCA ESTA HABILIDAD cuando tu Deep Agent necesite memoria, persistencia o acceso al sistema de archivos. Cubre StateBackend (efímero), StoreBackend (persistente), FilesystemMiddleware y CompositeBackend para enrutamiento.
This repo contains 11 individual skills — each has its own dedicated page.
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 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.
Gemini CLI one-shot prompts, summaries, generation, skills, hooks, MCP, or Gemma routing.
Fetch GitHub issues, select candidates, spawn background fix agents, open PRs, and optionally process PR review comments.
Create, edit, audit, tidy, validate, or restructure AgentSkills and SKILL.md files.
Search, install, update, sync, or publish agent skills with the ClawHub CLI and registry.
Delegate coding work to Codex, Claude Code, or OpenCode as background workers; not simple edits or read-only code lookup.
List, configure, authenticate, call, and inspect MCP servers/tools with mcporter over HTTP or stdio.