> ## 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.

# Skill Review Protocol • AI Agent SDK

> SkillReviewProtocol: Policy for the autonomous skill self-improvement loop.

# SkillReviewProtocol

> Defined in the [**protocols**](../modules/protocols) module.

<Badge color="blue">AI Agent</Badge>

Policy for the autonomous skill self-improvement loop.

After a task finishes, an opt-in guarded review pass asks the agent
whether the session revealed a reusable technique worth capturing as a
skill. `should_review` decides *whether* to run the pass and
`review_prompt` produces the directive given to the agent. Both take a
lightweight trajectory dict so wrappers/plugins can swap the policy
without depending on core internals.

## Methods

<CardGroup cols={2}>
  <Card title="should_review()" icon="function" href="../functions/SkillReviewProtocol-should_review">
    Return True if the finished session warrants a skill review.
  </Card>

  <Card title="review_prompt()" icon="function" href="../functions/SkillReviewProtocol-review_prompt">
    Return the directive prompt for the guarded review turn.
  </Card>
</CardGroup>

## Source

<Card title="View on GitHub" icon="github" href="https://github.com/MervinPraison/PraisonAI/blob/main/src/praisonai-agents/praisonaiagents/skills/protocols.py#L201">
  `praisonaiagents/skills/protocols.py` at line 201
</Card>

***

## Related Documentation

<CardGroup cols={2}>
  <Card title="Skills Concept" icon="wand-magic-sparkles" href="/docs/docs/concepts/skills" />

  <Card title="Skills Feature" icon="star" href="/docs/docs/features/skills" />
</CardGroup>