Deep Agents Memory
Skill AvisoINVOKE THIS SKILL when your Deep Agent needs memory, persistence, or filesystem access. Covers StateBackend (ephemeral), StoreBackend (persistent), FilesystemMiddleware, and CompositeBackend for routing.
This skill provides configurable backend strategies for Deep Agents, including ephemeral state, persistent storage across sessions, and hybrid routing. It also details how to use `FilesystemMiddleware` for direct file operations and offers examples for various storage scenarios.
License
- critical:License usabilityThe extension does not have a LICENSE file or a SPDX identifier in any manifest, nor does the README specify a license, making its usability for redistribution unclear.
Versioning
- critical:Release ManagementThere is no version information (e.g., in SKILL.md frontmatter, package.json, or changelog) and no GitHub releases, making it impossible to track or pin versions.
Instalação
Primeiro, adicione o marketplace
/plugin marketplace add langchain-ai/langchain-skills/plugin install langchain-skills@langchain-skillsExtensões similares
LangGraph Persistence
92INVOKE 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.
AI Agent Builder
95Build AI agents with tools, memory, and multi-step reasoning - ChatGPT, Claude, Gemini integration patterns
dbs-save：诊断存档
95把当前诊断的关键状态存到本地，下次回来可以接着用。 触发方式：/dbs-save、/存档、「保存这次诊断」「记下来」「这个结论留着」 Save the current diagnosis state to disk for cross-session recall. Trigger: /dbs-save, "save this diagnosis", "remember this"
Framework Selection
95INVOKE 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.
Deep Agents Orchestration
95INVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, TodoList for planning, and HITL interrupts.
Deep Agents Core
93INVOKE THIS SKILL when building ANY Deep Agents application. Covers create_deep_agent(), harness architecture, SKILL.md format, and configuration options.