Assemble production agent harnesses with DeepAgents
Use DeepAgents to build long-running task agents with a batteries-included harness for planning, tools, and workflow structure.
npx skills add agentskillexchange/skills --skill assemble-production-agent-harnesses-with-deepagents
DeepAgents provides a batteries-included harness for building deep task agents. This skill is for developers who need to start from an agent harness, wire model and tool capabilities, define task behavior, and test the resulting agent on realistic workflows. Invoke it when a user needs a durable custom agent structure rather than a one-off prompt or a generic LangChain project reference. The scope boundary is the production agent harness and its planning/tool workflow, not the whole LangChain ecosystem.
What this skill actually does
Inputs and prerequisites: DeepAgents, model provider credentials, workflow tools.
Setup notes: Follow the DeepAgents repository instructions, configure model access and tools, then implement and test the target long-running agent workflow.
Source and verification boundary: use https://github.com/langchain-ai/deepagents as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.
Framework fit: publish this as a Custom Agents workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.