Skip to main content

/docs — Documentation Generation

Audit existing documentation, identify gaps, generate what’s missing, and validate every claim against actual code.

When to Use

  • Codebase has undocumented modules, APIs, or workflows
  • Existing documentation is stale or references removed features
  • A wish deliverable includes documentation
  • After significant code changes that invalidate existing docs

Documentation Surfaces

TypeLocationPurpose
READMEREADME.md, */README.mdProject/module overview, setup, usage
CLAUDE.mdCLAUDE.md, */CLAUDE.mdProject conventions for AI agents
API docsdocs/api/, inline JSDoc/TSDocEndpoint contracts, schemas
Architecturedocs/architecture.mdSystem design, data flow
Inline docsJSDoc, TSDoc, docstringsFunction/class-level documentation
CLAUDE.md is a first-class documentation surface — it should always reflect the current state of the project.

Flow

  1. Audit existing docs — scan all documentation surfaces, map what exists.
  2. Identify gaps — compare documentation against actual code, find what’s missing or outdated.
  3. Generate — write documentation to fill the gaps, matching project conventions.
  4. Validate against code — verify every claim: file paths exist, APIs match, behaviors are accurate.
  5. Report — return list of created/updated files with validation results.

Dispatch

# Spawn a docs subagent
genie spawn docs

Rules

  • Validate every claim against actual code — no fiction
  • No dead references — every path, function, and API mentioned must exist
  • Match existing project conventions for documentation style
  • Never document features that don’t exist yet
  • Include validation evidence in the report