Document co-authoring workflow
Guides the user through writing a document in three stages: context gathering with numbered questions, section-by-section drafting with brainstormed options, and a test on a subagent that sees only the text. Use when drafting a spec, proposal or decision doc.
doc-coauthoring- Author
- Anthropic
- Source
- anthropics/skills/skills/doc-coauthoring @ e4bb5d9
- License
- none stated
About this skill
What it does
The skill turns writing a spec, decision doc, proposal or RFC into three guided stages. The agent offers it first; decline and it writes freeform.
Context comes first: five questions on type, audience, desired impact, template and constraints, then you dump what you have (connectors or MCP servers such as Slack or Google Drive can pull it in), then 5–10 numbered clarifying questions. It ends when the agent can ask about edge cases, not basics.
Then the document is built section by section, the most uncertain first, the summary last. Each gets clarifying questions, 5–20 numbered points to keep, cut or merge, a gap check, a draft and targeted edits. The agent asks for feedback in chat, not direct edits, to learn your style; after three rounds with no substantial changes it asks what can be cut. The draft lives in an artifact or a Markdown file in the working directory.
Last comes the reader test: the agent predicts 5–10 reader questions and gives a subagent only the document and one question at a time, then checks for ambiguity and contradictions. Without subagents (the claude.ai web app) you run it in a fresh chat. The skill is a single SKILL.md.
When to use it, and when not
Use it for a document others will read without you in the room: a design doc, PRD, decision doc or proposal. Skip it for a short note or settled content; the stages mean many rounds of questions.
How to run it
We do not copy this skill because the repository gives it no licence, so install it from Anthropic's repository with the source button. For Claude Code, its README has you register the repository as a plugin marketplace: /plugin marketplace add anthropics/skills, then /plugin install example-skills@anthropic-agent-skills, which brings the other example skills too. Then:
- Claude Code:
/example-skills:doc-coauthoring(a plugin's skills carry its name as a prefix), or ask for the skill by name. - Codex:
$doc-coauthoring. - Cursor: type
/in the Agent chat and pickdoc-coauthoring.
Example: /example-skills:doc-coauthoring Help me write a design doc on moving our job queue from Redis to Postgres.
How it differs from similar skills
Brainstorming before you build asks its questions one at a time rather than in numbered batches, and its design doc leads to code; this skill ends with a document tested on a reader. Conversation to spec writes up a discussion already held, with no interview. Architecture decision record gives a fixed template for one kind of document; this skill builds the structure with you. To get a .docx, hand the result to Word documents (.docx). Writing Guidelines review checks finished English prose against Vercel's style handbook and lists findings by line; it does not help decide what the document says.
Install
This skill is not copied to the catalog: the author's repository has no licence text. Install it from there.
Connect through AnyModel API
This skill runs on whatever model your agent uses. Point Claude Code, Codex or Cursor at AnyModel to run it on Claude, GPT, Gemini and more with one key — pay per token, no subscription.
AnyModel