Open Skills Logo
Open Skills

doc-coauthoring

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.

Author

@anthropics

Category

Content Creation

Install

Hot:13

Download and extract to your skills directory

Copy command and send to OpenClaw for auto-install:

Download and install this skill https://openskills.cc/api/download?slug=anthropics-skills-doc-coauthoring&locale=en&source=copy

Doc Co-Authoring - Collaborative Document Writing Workflow

Overview


A three-stage structured document collaboration workflow that helps users efficiently gather context, iteratively refine content, and validate document effectiveness through reader testing.

Applicable Scenarios


  • Technical Documentation: Writing technical specification documents, architecture design documents, API documentation, and other technical content, ensuring clear structure, complete information, and ease of understanding for readers.

  • Decision and Proposal Documents: Preparing decision documents (Decision Doc), RFCs, proposals, or PRDs; using a structured process to ensure rigorous logic and thorough consideration.

  • Team Collaborative Writing: When multiple people collaborate on documents, using a unified workflow reduces communication costs and improves content quality and consistency.

    • Core Features


  • Context Collection Stage: Use guided questions to help authors systematically collect and organize all relevant background information, including target audience, project background, technical constraints, team dynamics, etc., to avoid missing key context.

  • Iterative Refinement Stage: Build the document section by section; each section goes through five steps—questioning, brainstorming, filtering, drafting, and polishing—to ensure content accuracy and alignment with the author's intent.

  • Reader Testing Stage: Use a new AI instance to test document readability, predict questions readers might ask, identify blind spots and ambiguous expressions, and optimize content before official release.

    • Frequently Asked Questions

    What types of documents is the Doc Co-Authoring workflow suitable for?


    This workflow is especially suitable for structured content that requires systematic thinking and clear communication, including technical specification documents, decision documents, design documents, RFCs, PRDs, proposals, project summaries, and so on. For simple emails or quick notes it may be overly cumbersome, but it is worthwhile for any content that requires careful reading and understanding by others.

    How long does it take to write a document using this workflow?


    Time investment depends on document complexity and the author's level of preparation. For first-time users, the context collection stage may take 15–30 minutes, the iterative refinement stage 20–40 minutes per section, and the reader testing stage 15–30 minutes. It can be faster with experience. Although it requires more upfront time, it can greatly reduce rework later and the cost of others' understanding and communication.

    How is the reader testing stage carried out?


    If you use an interface that supports sub-agents (such as Claude Code), the system will automatically use a new AI instance to test the document; if you use the web version, open a new conversation, paste only the document content without providing any background, and then ask the AI to predict questions readers might have. If the AI can answer correctly and does not show misunderstandings or point out ambiguous parts, the document passes the test. If problems are found, return to the iterative stage to revise the relevant sections.