← Use cases · Building agents
AI agents for building skill-based subagents
Short answer: Deep Agents (tested 7.2/10 in our smoke test) builds on LangGraph and lets you pin skills by name, with each subagent getting its own skills middleware.
Tools for this job
| # | Tool | Why for this job | AgentPick Score | Link |
|---|---|---|---|---|
| #1 |  LangGraph | The graph runtime underneath, for custom control | 90/100 | Official source ↗ |
| #2 |  LangChain Deep Agents | Tested 7.2/10: pinned_skills per subagent | 87/100 · Hands-on tested 7.2/10 | Official source ↗ |
Ordered by AgentPick Score. Links may become affiliate links; they never change order. Disclosure.
How to do it
- Write each skill as a small, testable unit.
- Pin only the skills a subagent needs.
- Give each subagent one clear job.
- Smoke-test offline before adding a live model.
Starter prompt
Create a Deep Agents setup with a planner and two subagents, [A] and [B]. Pin skills [x] to A and [y] to B only. Add a smoke test that runs without an API key.
Get one use case like this every week. Tools, prompt and our verdict in AgentPick Weekly. Free. Get the weekly digest
Related use cases
Running several coding tasks in parallel →
Coding
Refactoring a codebase without leaving VS Code →
Coding
Trying a coding agent without paying first →
Coding
Building a typed Python agent with structured output →
Building agents
AgentPick Weekly
The week's new agent tools with a verdict on each, every week. Free. We'll email you a link to confirm, and you can unsubscribe any time. See our Privacy Policy.