Use Anthropic's doc-coauthoring skill to run a disciplined writing workflow instead of freeform drafting. The agent gathers missing context, iterates section by section, and pressure-tests the final document with reader-style review before teammates see it.
Scanned 6/8/2026
Install via CLI
openskills install agentskillexchange/skills---
name: "Co-author structured docs with staged context gathering and reader testing"
slug: "co-author-structured-docs-with-staged-context-gathering-and-reader-testing"
description: "Use Anthropic's doc-coauthoring skill to run a disciplined writing workflow instead of freeform drafting. The agent gathers missing context, iterates section by section, and pressure-tests the final document with reader-style review before teammates see it."
verification: "security_reviewed"
source: "https://github.com/anthropics/skills/tree/main/skills/doc-coauthoring"
author: "Anthropic"
publisher_type: "Organization"
category: "Templates & Workflows"
framework: "Claude Agents"
---
# Co-author structured docs with staged context gathering and reader testing
Use Anthropic's doc-coauthoring skill to run a disciplined writing workflow instead of freeform drafting. The agent gathers missing context, iterates section by section, and pressure-tests the final document with reader-style review before teammates see it.
## Installation
Requirements and caveats from upstream:
- The frontmatter requires only two fields:
Basic usage or getting-started notes:
- Select document-skills or example-skills
- /plugin install example-skills@anthropic-agent-skills
- These example skills are all already available to paid plans in Claude.ai.
- Source: https://github.com/anthropics/skills/tree/main/skills/doc-coauthoring
- Extracted from upstream docs: https://raw.githubusercontent.com/anthropics/skills/HEAD/README.md
## Documentation
- https://github.com/anthropics/skills/tree/main/skills/doc-coauthoring
## Source
- [Agent Skill Exchange](https://agentskillexchange.com/skills/co-author-structured-docs-with-staged-context-gathering-and-reader-testing/)
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.