creator profile · 22 approved skills · page 2 of 3
total skills
22
showing 10 on this page
page installs
0
0 this week
The deepagents CLI loads skills from five sources, listed here from lowest to highest precedence:
Long-form blog post writing with research delegation, structured content templates, and AI-generated cover images. \n \n Delegates research to subagents before writing, storing fi…
Create, manage, and upload evaluation datasets to LangSmith for testing and validation. \n \n Supports four dataset types: final_response (full conversations), single_step (indivi…
Build evaluation pipelines for LangSmith with LLM-as-Judge and custom code evaluators. \n \n Three core components: creating evaluators (LLM-as-Judge or custom code), defining run…
Add tracing to LangChain/LangGraph apps and query trace data via CLI for debugging and dataset generation. \n \n Automatic tracing for LangChain/LangGraph apps with environment va…
Build production LangChain agents with create_agent(), tools, and middleware patterns. \n \n Use create_agent() with model, tools list, and system prompt; configure state persiste…
Orchestrate subagents, plan multi-step tasks, and require human approval for sensitive operations. \n \n Delegate work to specialized subagents via the task tool; custom subagents…
Framework selection guide for LangChain, LangGraph, and Deep Agents layered architecture. \n \n Layered frameworks where LangChain provides foundation primitives, LangGraph adds o…
Pluggable memory and file backends for Deep Agents with ephemeral, persistent, and hybrid routing options. \n \n Four backend types: StateBackend (thread-scoped, ephemeral), Store…
Human-in-the-loop approval, custom middleware, and structured output patterns for LangChain agents. \n \n HumanInTheLoopMiddleware pauses execution before dangerous tool calls, al…
