Audit generated HTML, Markdown, crawler controls, model-readable docs, structured data, API specs, and URL-class drift from one local source graph.
Scanned 9/3/2026
Install to Claude Code
Skills Directorynpx -y skills add jmagly/aiwg --skill generated-docs-audit --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Generated Docs Audit?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/jmagly-generated-docs-audit)More formats (shields.io, HTML) on the badges page.
---
namespace: aiwg
platforms: [all]
name: generated-docs-audit
description: Audit generated HTML, Markdown, crawler controls, model-readable docs, structured data, API specs, and URL-class drift from one local source graph.
triggers:
- audit generated docs discoverability
- check llms txt sitemap drift
- generated docs crawl index matrix
commandHint:
argumentHint: "--root <generated-site> [--graph <source-graph>] [--json] [--out <report>]"
allowedTools: Read, Bash
category: documentation-quality
---
# Generated Docs Audit
Run the CI-friendly local auditor:
```bash
npm run docs:discoverability:audit -- --root <generated-site> --json
```
Use a reviewed `aiwg.docs-discoverability/v1` source graph. Treat failed crawl, index, or AI-discoverability controls as release blockers; review warnings for orphan, thin, stale, near-duplicate, and doorway-shaped output.
Do not present a local pass as hosted or multi-site governance. See `docs/guides/generated-docs-discoverability-audit.md` for the graph schema, severity rules, and public/enterprise boundary.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
