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.

DocumentationPack: Anthropic skillslinkdoc-coauthoring
Author
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 pick doc-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.

Open the source

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.

More from the pack Anthropic skills

MCP server builder

Guides the agent through building an MCP server for an external API in TypeScript or Python: tool design, schemas, pagination, errors, testing and an evaluation run with Claude. Use when wrapping an API or service as MCP tools.

Skill creator with evals

Drafts or revises an agent skill, tests it with subagents against a baseline, shows results and benchmarks on a review page and tunes the description for triggering. Use when a new or edited skill has to be measured, not just written.

Distinctive frontend design

Gives new UI a visual direction drawn from its subject: a short plan of colours, type and layout, checked against the brief and against common AI-generated looks before any code. Use when a page or product screen should not look templated.

Web app testing with Playwright scripts

Tests a local web app with Python Playwright scripts: a helper starts and stops the servers, the agent inspects the rendered page, then clicks, fills, takes screenshots and reads console logs. Use when checking a frontend change or reproducing a UI bug.

PDF files: read, fill, create

Extracts text and tables, merges, splits, encrypts and OCRs PDFs with pypdf, pdfplumber, reportlab and qpdf, and fills forms through bundled scripts that check fields and boxes. Use when a task reads, fills or produces a PDF file.

Word documents (.docx)

Creates Word files with docx-js, edits existing ones as unpacked XML, adds tracked changes and comments through bundled scripts, then validates and renders the result. Use when the deliverable or input is a .docx or .dotx file.

Excel spreadsheets (.xlsx)

Builds and edits Excel workbooks with openpyxl, keeps real formulas, recalculates them in LibreOffice with a JSON error report and follows financial-model conventions. Use when the deliverable is a spreadsheet file such as .xlsx, .xlsm or .csv.

PowerPoint decks (.pptx)

Creates themed decks with pptxgenjs, edits templates as unpacked XML with scripts for slide text, thumbnails, duplication and validation, and checks every slide as an image. Use when a task creates, edits or reads a .pptx or .potx file.

Claude API reference for agents

Anthropic's reference for code that calls Claude: SDKs in seven languages and cURL, current models and prices, tool use, caching, Managed Agents, plus migration, cost and eval procedures. Use when writing or changing code that uses the Claude API.

Algorithmic art with p5.js

Creates generative art in p5.js: a short manifesto for the piece, then a seeded algorithm in one HTML page with sliders, seed navigation and PNG download. Use when asked for flow fields, particle systems or other art made with code.