doc-coauthoring

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

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/chhpt/skills --skill doc-coauthoring-chhpt
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: doc-coauthoring
Source: https://github.com/chhpt/skills/tree/main/skills/doc-coauthoring
Command: npx skills add https://github.com/chhpt/skills --skill doc-coauthoring-chhpt

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Writing documentation, proposals, and specs alone often produces documents that make sense to the author but confuse readers. This Skill structures the co-authoring process so context is fully transferred, each section is deliberately refined, and blind spots are caught before others read the document. ## Core Features & Use Cases - Context Gathering: Collects background, audience, constraints, and organizational context through structured questions and info dumps, optionally pulling from connected tools like Slack or Google Drive. - Section-by-Section Refinement: Brainstorms 5-20 options per section, curates them with the user, drafts content, and iterates with surgical edits. - Reader Testing: Tests the finished document with a fresh AI instance (sub-agent or new conversation) to surface ambiguity, false assumptions, and contradictions. - Use Case: A product manager drafting a decision doc uses this workflow to dump context, build each section iteratively, then verify a fresh reader can correctly answer likely questions before sharing it with the team. ## Quick Start Ask the assistant to guide you through the doc co-authoring workflow to draft a technical design doc for your upcoming project.

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 with AI assistance?

Use a structured co-authoring workflow: first dump all project context while the AI asks clarifying questions, then build the doc section by section through brainstorming and curation, and finally test the draft with a fresh AI conversation to catch confusing passages.

How to test if my documentation is clear to readers?

Paste the document into a fresh AI conversation with no prior context and ask it reader-style questions. If the fresh instance misinterprets sections or flags assumed knowledge, revise those gaps before sharing the doc with real readers.

What types of documents does this workflow support?

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

Can I use this workflow with Slack or Google Drive documents?

Yes, if integrations or MCP connectors are enabled, the workflow can pull context directly from team channels and shared documents. Without connectors, you can paste the relevant content manually into the conversation.

When should I skip the structured workflow and write freeform?

Freeform writing fits short or low-stakes documents where reader ambiguity carries little risk. The structured workflow is most valuable for substantial documents like specs and decision docs that many stakeholders will read and act on.