> ## Documentation Index
> Fetch the complete documentation index at: https://praison.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Build Learn Prompt • AI Agent SDK

> build_learn_prompt: Build a grounded skill-authoring directive from a user request.

# build\_learn\_prompt

<div className="flex items-center gap-2">
  <Badge color="teal">Function</Badge>
</div>

> This function is defined in the [**learn**](../modules/learn) module.

Build a grounded skill-authoring directive from a user request.

This is the **skill authoring** path: distil a reusable `SKILL.md` from
real sources. It is complementary to — and distinct from — the memory
`learn=` recall path (conversation→memory extraction) and the automatic
`self_improve` loop.

## Signature

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
def build_learn_prompt(request: str) -> str
```

## Parameters

<ParamField query="request" type="str" required={true}>
  A natural-language description of the sources to learn from and the skill to produce, e.g. `"Read ./my-repo and the docs in ./docs/*.pdf and make a 'deploy-flow' skill"`.
</ParamField>

### Returns

<ResponseField name="Returns" type="str">
  A prompt string that instructs an agent to gather the named sources with
  its existing tools and author one grounded `SKILL.md` via
  `skill_manage`.
</ResponseField>

## Source

<Card title="View on GitHub" icon="github" href="https://github.com/MervinPraison/PraisonAI/blob/main/src/praisonai-agents/praisonaiagents/skills/learn.py#L54">
  `praisonaiagents/skills/learn.py` at line 54
</Card>

***

## Related Documentation

<CardGroup cols={2}>
  <Card title="Agent Learn" icon="graduation-cap" href="/docs/docs/concepts/agent-learn" />

  <Card title="Learn Configuration" icon="gear" href="/docs/docs/configuration/learn-config" />
</CardGroup>
