[agents](https://carteblanche.com/index.md?kind=agent) / [code](https://carteblanche.com/index.md?category=code)

# documentation-engineer

what it does

Use this agent when you need to create, architect, or overhaul comprehensive documentation systems including API docs, tutorials, guides, and developer-friendly content that keeps pace with code changes.

tools it asks for

Reads files · Edits files · Uses the web

by VoltAgent · version 1 · license MIT

We imported this agent from its author’s repository. Is this yours? [Claim this listing](https://carteblanche.com/claim/documentation-engineer)

Verified · Before and after: 2 models · 1 try per case · [View source](https://github.com/VoltAgent/awesome-claude-code-subagents/blob/ed74d115b7fb7026a22a4f816a8e3250f425e3b4/categories/06-developer-experience/documentation-engineer.md) · [Install from your agent](https://carteblanche.com/connect.md) · [Download .zip](https://carteblanche.com/skills/documentation-engineer/download)

## Compare the answers

Answers from Claude Sonnet 5.5 and GPT-6.1 Sol · try 1 of 1

Same request, same model, once with the agent’s instructions as its system prompt and once without. Neither could use a tool. Read both and judge for yourself.

[Compare the answers](https://carteblanche.com/skills/documentation-engineer/compare)

## The models

2 models

Claude Sonnet 5.5

made by Anthropic

claude-sonnet-5-5 · revision not reported by the provider

1 try per case · tested 7 Nov 2026

GPT-6.1 Sol

made by OpenAI

gpt-6.1-sol · revision not reported by the provider

1 try per case · tested 7 Nov 2026

## The tasks

written by Carte Blanche

**example-1**

“Our team maintains a small Python library called pyqueue-lite (a Redis-backed job queue). Docs are just a single README right now. Can you propose a documentation architecture for it? I'm thinking quickstart, concepts, how-to guides, API reference generated from docstrings, and a changelog. Please give me a suggested folder structure, a sidebar outline, and a draft of the quickstart page. Public API: Queue(name, redis\_url), Queue.enqueue(func, \*args, retry=3), Worker(queue).run(), and Job.status().”

**example-2**

“Our REST API docs have drifted from the code. Endpoints get added in PRs and nobody updates the docs. We use FastAPI with an auto-generated OpenAPI spec, and docs live in a Docusaurus site. Can you design a workflow that keeps the docs in sync with code changes? I'd like CI checks that fail when the spec changes without doc updates, a PR template checklist, and a plan for adding code samples in curl, Python and JavaScript for each endpoint. Please include example GitHub Actions steps.”

## Install

Download the .zip and unzip it. Put `documentation-engineer.md` here:

Claude Code · `~/.claude/agents/` · Every project. For one project only, use .claude/agents/ inside it. It gives the agent the tools it asks for, and no others.

Cursor · `~/.cursor/agents/` · Cursor also reads the Claude Code folder above. It has no tools field, so it gives every agent every tool, whatever this one asks for.

Codex · Codex’s custom agents are TOML files, not Markdown, so this agent doesn’t install there.

Keep its license file beside it, as `documentation-engineer.LICENSE`: a name that doesn’t end in .md, since every .md file there is read as an agent.

Then start a new session and ask for it by name. Folders checked 6 November 2026.

Or [install from your agent](https://carteblanche.com/connect.md): ask it to install `documentation-engineer` from Carte Blanche.

## Badge for your README

Carte Blanche: Verified

Paste this into the agent’s README. It links to this page, and shows how the listing stands whenever it’s loaded.

```
[![Carte Blanche](https://carteblanche.com/badge/documentation-engineer.svg)](https://carteblanche.com/skills/documentation-engineer)
```

## About this test

- **tested**: 7 Nov 2026
- **version tested**: v1
- **cases**: 2
- **tries per case**: 1 try per case
- **run without the agent**: yes
- **cases written by**: Carte Blanche
- **size**: 6422 characters

What this shows, and what it doesn’t

How 2 models answered these 2 requests, with and without the agent. It says nothing about other models, and it doesn’t limit what your own agent can do.

The answers were written without tools: the agent’s instructions were the system prompt, and it read no file and ran nothing.

[How we test](https://carteblanche.com/how-it-works.md)