doc-coauthoring
Structured workflow for co-authoring docs, proposals, specs, and decision docs with reader testing.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for doc-coauthoring, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
Anthropic's official skill guiding a three-stage collaborative writing workflow: Context Gathering, Refinement & Structure, and Reader Testing (validating the doc with a fresh no-context Claude). Pure guidance content with no bundled scripts; it shapes how the agent interviews the user and iterates on document sections.
Key features and capabilities
- Three-stage co-authoring workflow
- Context-transfer clarifying questions
- Fresh-Claude reader testing to catch blind spots
Use cases
- Co-author a PRD or design doc
- Pressure-test a proposal before sharing