$ ~/registry/skill/anthropics-doc-coauthoring

SKILL

doc-coauthoring

Name: doc-coauthoring
Author: Anthropic

Guide users to co-author docs, proposals, and specs through iterative refinement.

Source

GitHub

Updated

2026-07-15

// securityCaution

Prompt only, no code
Open source

Summary

The material indicates a prompt-only documentation co-authoring workflow with no declared secrets, remote endpoints, or local execution capability. Given its open-source source and prompt-only nature, overall risk is low, though any actual link/file access would depend on the host platform's integrations and permission controls.

CredentialsLow risk

The material explicitly states that no keys or environment variables are required, and it does not ask users for API tokens, account passwords, or other sensitive credentials, so credential exposure risk is low.

Network egressLow risk

No remote endpoints are declared. The README only notes that if a user provides a shared document link, an appropriate integration may be used to fetch it; this is a host-platform optional capability rather than a built-in exfiltration path of the skill itself. Based on the material, no custom data egress target is specified.

Code executionLow risk

This skill is a prompt-only workflow description and does not describe starting local processes, running scripts, invoking a shell, or requesting system-level execution privileges.

Data accessCaution

The material mentions reading content when a user provides a file or shared document link, and suggests checking existing documents and image descriptions; this means it may access user document content when host integrations are available. This access is aligned with the stated purpose, but users should still minimize the scope of documents shared.

Supply chainLow risk

The source is the open-source GitHub repository anthropics/skills, which is auditable and a strong risk-reducing factor. Although the license is unspecified, stars are low, and maintenance status is unknown, there are no concrete red flags such as closed source code, suspicious install scripts, or unknown dependencies.

Recommendations

Only provide the minimum necessary document excerpts, files, or shared links to this skill.
If the host platform supports external integrations, verify their access scope and permission model first.
Avoid including unnecessary passwords, tokens, or highly sensitive internal information in large context dumps.

Audited by: gpt-5.4 · 2026-06-17

// install

Copy the install command and let the AI configure it · recommended for beginners

Please install the "doc-coauthoring" skill from askskill:
1. Download https://raw.githubusercontent.com/anthropics/skills/main/skills/doc-coauthoring/SKILL.md
2. Save it as ~/.claude/skills/doc-coauthoring/SKILL.md
3. Reload skills and tell me it's ready

// download

Download SKILL.mdInstall manifest ↗

// docs

Doc Co-Authoring Workflow

This skill provides a structured workflow for guiding users through collaborative document creation. Act as an active guide, walking users through three stages: Context Gathering, Refinement & Structure, and Reader Testing.

When to Offer This Workflow

Trigger conditions:

User mentions writing documentation: "write a doc", "draft a proposal", "create a spec", "write up"
User mentions specific doc types: "PRD", "design doc", "decision doc", "RFC"
User seems to be starting a substantial writing task

Initial offer: Offer the user a structured workflow for co-authoring the document. Explain the three stages:

Context Gathering: User provides all relevant context while Claude asks clarifying questions
Refinement & Structure: Iteratively build each section through brainstorming and editing
Reader Testing: Test the doc with a fresh Claude (no context) to catch blind spots before others read it

Explain that this approach helps ensure the doc works well when others read it (including when they paste it into Claude). Ask if they want to try this workflow or prefer to work freeform.

If user declines, work freeform. If user accepts, proceed to Stage 1.

Stage 1: Context Gathering

Goal: Close the gap between what the user knows and what Claude knows, enabling smart guidance later.

Initial Questions

Start by asking the user for meta-context about the document:

What type of document is this? (e.g., technical spec, decision doc, proposal)
Who's the primary audience?
What's the desired impact when someone reads this?
Is there a template or specific format to follow?
Any other constraints or context to know?

Inform them they can answer in shorthand or dump information however works best for them.

If user provides a template or mentions a doc type:

Ask if they have a template document to share
If they provide a link to a shared document, use the appropriate integration to fetch it
If they provide a file, read it

If user mentions editing an existing shared document:

Use the appropriate integration to read the current state
Check for images without alt-text
If images exist without alt-text, explain that when others use Claude to understand the doc, Claude won't be able to see them. Ask if they want alt-text generated. If so, request they paste each image into chat for descriptive alt-text generation.

Info Dumping

Once initial questions are answered, encourage the user to dump all the context they have. Request information such as:

Background on the project/problem
Related team discussions or shared documents
Why alternative solutions aren't being used
Organizational context (team dynamics, past incidents, politics)
Timeline pressures or constraints
Technical architecture or dependencies
Stakeholder concerns

Advise them not to worry about organizing it - just get it all out. Offer multiple ways to provide context:

Info dump stream-of-consciousness
Point to team channels or threads to read
Link to shared documents

If integrations are available (e.g., Slack, Teams, Google Drive, SharePoint, or other MCP servers), mention that these can be used to pull in context directly.

If no integrations are detected and in Claude.ai or Claude app: Suggest they can enable connectors in their Claude settings to allow pulling context from messaging apps and document storage directly.

Inform them clarifying questions will be asked once they've done their initial dump.

During context gathering:

If user mentions team channels or shared documents:
- If integrations available: Inform them the content will be read now, then use the appropriate integration
- If integrations not available: Explain lack of access. Suggest they enable connectors in Claude settings, or paste the relevant content directly.
If user mentions entities/projects that are unknown:

…

View full docs ↗