doc-coauthoring

Guides collaborative document drafting through context gathering, iterative refinement, and reader testing.

Updated Jan 10, 2026
One-click install
npx skills add https://github.com/Rabbit-Ivan/Ivan-skills --skill doc-coauthoring-rabbit-ivan
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: doc-coauthoring
Source: https://github.com/Rabbit-Ivan/Ivan-skills/tree/main/skills/doc-coauthoring
Command: npx skills add https://github.com/Rabbit-Ivan/Ivan-skills --skill doc-coauthoring-rabbit-ivan

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Writing documentation, proposals, and specs alone often produces documents full of blind spots, missing context, and unclear sections that confuse readers. This Skill structures the co-authoring process so the final document actually works for its intended audience. ## Core Features & Use Cases - Three-Stage Workflow: Walks users through Context Gathering, Refinement & Structure, and Reader Testing to build documents section by section. - Iterative Section Drafting: Brainstorms 5-20 options per section, curates with the user, then drafts and refines through targeted edits. - Reader Testing: Validates the finished document with a fresh, context-free reviewer (sub-agent or manual test) to catch ambiguity, false assumptions, and contradictions. - Use Case: A product manager needs to write a decision doc for a migration plan. The Skill gathers project context, drafts each section through brainstorming and curation, then tests whether a fresh reader can correctly answer likely questions about the doc. ## Quick Start Ask the assistant to guide you through writing a design doc or proposal using the doc co-authoring workflow, starting with context gathering.

Frequently Asked Questions about doc-coauthoring

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I write a design doc or proposal with an AI assistant?▼

Use a structured co-authoring workflow: first dump all project context while the assistant asks clarifying questions, then build the document section by section through brainstorming and curation, and finally test the draft with a fresh reviewer to catch blind spots.

How to test whether a document is clear to readers?▼

Predict 5-10 questions real readers would ask, then have a fresh AI instance with no prior context answer them using only the document. Incorrect answers or flagged ambiguities reveal gaps to fix before publishing.

What document types does this workflow support?▼

It supports technical specs, decision docs, RFCs, PRDs, proposals, and similar structured content. The workflow adapts its section suggestions based on the document type and any template the user provides.

Can I skip stages of the co-authoring workflow?▼

Yes. The workflow explicitly gives users agency to skip stages or work freeform at any point. If a user declines the structured approach, the assistant proceeds with freeform writing instead.

Does reader testing work without sub-agents?▼

Yes. Without sub-agent access, the user manually opens a fresh conversation, pastes the document, and asks the predicted reader questions plus checks for ambiguity, assumed knowledge, and contradictions.