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

# technical-writer

what it does

Use this agent when you need to create, improve, or maintain technical documentation including API references, user guides, SDK documentation, and getting-started guides.

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/technical-writer)

Verified · Before and after: 2 models · 1 try per case · [View source](https://github.com/VoltAgent/awesome-claude-code-subagents/blob/ed74d115b7fb7026a22a4f816a8e3250f425e3b4/categories/08-business-product/technical-writer.md) · [Install from your agent](https://carteblanche.com/connect.md) · [Download .zip](https://carteblanche.com/skills/technical-writer/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/technical-writer/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**

“I need an API reference entry for our POST /v1/invoices endpoint. It takes customer\_id (string, required), currency (string, ISO 4217, required), line\_items (array of objects with description, quantity, unit\_price\_cents), and due\_date (ISO 8601 date, optional). It returns 201 with the invoice object including id, status ('draft'), and total\_cents. Errors: 400 for validation, 401 for a bad token, 404 for an unknown customer. Please include a curl example and a sample JSON response.”

**example-2**

“Here's the README intro for our Python SDK, 'fastqueue'. It says: 'Install it and use it. Call connect() then push(). Works with Python 3.8+.' That's way too thin for new users. Can you turn it into a proper getting-started guide covering installation with pip, authenticating with an API token from an environment variable, pushing and consuming a first message, and a short troubleshooting section for common connection errors?”

## Install

Download the .zip and unzip it. Put `technical-writer.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 `technical-writer.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 `technical-writer` 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/technical-writer.svg)](https://carteblanche.com/skills/technical-writer)
```

## 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**: 6232 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)
