Deep Agents Orchestration
Skill VérifiéINVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, TodoList for planning, and HITL interrupts.
This skill provides middleware for Deep Agents, enabling task delegation to specialized subagents, structured task planning via a TodoList, and human-in-the-loop approval for sensitive operations. It leverages LangChain and LangGraph components for its functionality.
Documentation
- info:Configuration & parameter referenceWhile configuration options like `subagents`, `tools`, `interrupt_on`, and `checkpointer` are mentioned and shown in examples, explicit defaults for all parameters and a clear precedence order for configuration are not detailed.
License
- info:License usabilityThe README mentions the project is in early development and points to a separate repository for skills, but no explicit LICENSE file or SPDX identifier is directly present in this skill's directory. The overall project's license is not clearly stated here.
Versioning
- info:Release ManagementThe skill is part of a larger project ('langchain-skills') and the README mentions versioning, but no specific version number is declared for this skill itself within its SKILL.md or associated manifests, and installation instructions point to the main branch.
Code Execution
- info:ValidationWhile the code examples demonstrate structured inputs for tools and configurations (e.g., `zod` for TypeScript), explicit mention of a schema library for all input validation and sanitization across all tools is not detailed in the SKILL.md.
Installation
Ajoutez d'abord la marketplace
/plugin marketplace add langchain-ai/langchain-skills/plugin install langchain-skills@langchain-skillsExtensions similaires
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 Core
93INVOKE THIS SKILL when building ANY Deep Agents application. Covers create_deep_agent(), harness architecture, SKILL.md format, and configuration options.
LangGraph Human-in-the-Loop
90INVOKE 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.
Web Research Skill
85Searches multiple web sources, synthesizes findings, and produces cited research reports using delegated subagents. Use when the user asks to research a topic online, search the web, look something up, find current information, compare options, or produce a research report.
Gitea Coordinator
98Orchestrate multiple worker agents to implement groomed tasks in Gitea repositories. Use when multiple ready tasks need implementation, when you want autonomous multi-task execution, or when coordinating batch development work with Gitea. Keywords: coordinator, orchestrator, multi-task, parallel, workers, batch, autonomous, gitea, tea.
Agile Coordinator
98Orchestrate multiple worker agents to implement groomed tasks. Use when multiple ready tasks need implementation, when you want autonomous multi-task execution, or when coordinating batch development work. Keywords: coordinator, orchestrator, multi-task, parallel, workers, batch, autonomous.