---
name: doc
description: Create or update project documentation in the local style. Write documentation that matches the…
category: documentation
runtime: no special runtime
---

# doc output preview

## PART A: Task fit
- Use case: Create or update project documentation in the local style. Write documentation that matches the project. Before final output, verify: runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Process / Self-validation / Rules” and do not present inference as author intent.

## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Create or update project documentation in the local style. Write documentation that matches the project. Before final output, verify: runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more.”.
- **02** When the source has headings, the agent prioritizes “Process / Self-validation / Rules” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files, read environment variables; mostly runs locally; usually needs no extra API key.

## Running Rules
- read files, write/modify files, read environment variables; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options.