docs — Documentation Generation

SkillDocs & knowledge

Dispatch docs subagent to audit, generate, and validate documentation against the codebase.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the docs — Documentation Generation skill

What this skill tells your AI

The instructions your AI receives, as published by automagik-dev/genie in skills/docs/SKILL.md and read by ahel’s review.

Runtime syntax: invoke the plugin copy through the active runtime's owner-qualified skill selector; use a bare selector only when intentionally selecting a user-tier copy (a separately installed personal copy; Genie no longer seeds this tier). Cross-skill prose below uses bare names as portable semantic routes; the orchestrator resolves the selector for the active runtime.

Audit existing documentation, fill gaps, and validate every claim against actual code. Standalone or as part of work.

When to Use

  • Undocumented modules, APIs, or workflows; docs referencing removed features
  • A wish deliverable includes documentation
  • Code just changed in ways existing docs describe (e.g. after work completes)

Surfaces

TypeLocationPurpose
READMEREADME.md, */README.mdOverview, setup, usage
AGENTS.mdAGENTS.md, */AGENTS.mdAgent conventions, constraints, commands, verification
CLAUDE.mdCLAUDE.md, */CLAUDE.mdConventions, commands, gotchas for agents
API docsdocs/api/, inline JSDoc/TSDocContracts, request/response schemas
Architecturedocs/architecture.md, ARCHITECTURE.mdSystem design, data flow
InlineJSDoc, TSDoc, docstringsFunction/class/module docs

AGENTS.md is the governing agent instruction surface. CLAUDE.md remains evidence of repository intent when present; keep both current when the project has both files.

Flow

  1. Audit — map what exists across the surfaces above.
  2. Diff against code — find missing, stale, or wrong claims; governing AGENTS.md accuracy first.
  3. Generate — fill gaps in the project's existing documentation style.
  4. Validate — every referenced path exists, every API matches, every described behavior is real.
  5. Report — created/updated files with per-claim validation results.

Dispatch

Runs as a subagent (native runtime): the dispatching agent issues an native delegation surface call with a curated brief — scope (which docs, which change triggered the audit), the code areas to validate against, and the expected report shape.

Example brief: "Audit README.md, CLAUDE.md, and skills/work/SKILL.md after PR #746 — verify dispatch examples match current code, fix stale references, report per-file verdicts with evidence."

Rules

  • Grounded progress: report only what was audited or generated in this session, each claim backed by a check actually run — "3 files verified current, 1 updated, 0 dead references", never just "docs written".
  • No fiction: never document features that don't exist yet; no dead paths or APIs.
  • Write to the reader's interface boundary: explain what they need to decide, do, observe, and verify. Prefer observable promises, outcomes, failure behavior, and next steps over internal machinery. Include implementation details only when the reader needs them to use the feature safely, troubleshoot it, or extend it; otherwise keep that mechanism in internal or architecture documentation.
  • Match existing project conventions for style and structure.

Signals

GitHub stars
335
Forks
50
Last commit
Sep 2026
Hacker News mentions
20
Advanced
Catalog kind
skill
Gateway key
docs-automagik-dev
Source
github.com/automagik-dev/genie