Legal Page Discovery
Find every legal and compliance page on a live website, not just the ones in the nav
Triangulates a website's sitemap, robots.txt, footer/nav links across multiple pages, and common compliance path guesses to find every privacy policy, HIPAA/Part 2 notice, terms page, and consent form actually posted, including pages the site's own navigation doesn't link to. Retrieves each page's verbatim text, classifies its content and controlling entity, and flags nav-label or entity mismatches.
From document to output
Point the skill at a base domain and, if known, the legal name of the regulated entity operating it
Sitemap.xml, robots.txt, footer/nav links from two different page templates, and a list of common compliance path guesses are all checked, every run
Every candidate URL is fetched with curl and HTML-stripped to plain text, never a summarizing fetch, which can silently drop the clause that matters
Content type, controlling entity, and nav-label/content/entity mismatches are recorded, grounded in the page's own language
A markdown table plus JSON manifest lists every discovered page for downstream routing (e.g. by skill-router). It does not recommend which assessment to run
What you get back
Every finding is structured JSON: status, evidence, risk level, and remediation in one package. No interpretation required before acting on it.
{
"url": "https://example-recovery.com/legal/npp",
"nav_labels": [
"\"HIPAA\" in the global footer"
],
"found_via": [
"sitemap",
"homepage_footer",
"deep_page_footer"
],
"classification": "Notice of HIPAA Privacy Practices / Part 2 SUD notice",
"controlling_entity": "Example Recovery Medical Group, P.A.",
"entity_match": "match",
"mismatch_flags": [
"Labeled 'HIPAA' in the footer rather than 'Privacy' or 'Notice of Privacy Practices'"
]
} Three ways to run this skill
The first two are yours to run. The third is the platform, which runs as the instrument behind the practice rather than as a product sold here.
One-click install for Claude and Cowork users. The skill runs as a native tool in your Claude environment. No configuration, no MCP setup. Apache 2.0.
Get on ClawHub →Install as an MCP server in Claude Code, or download the SKILL.md and use it as a system prompt with any LLM. Runs the full methodology against documents you provide. Apache 2.0. No account required.
The platform runs this skill against a full document corpus in a workspace-isolated store: every finding is sourced to a specific document section, cross-referenced across the policy library, and carries a disposition and a reasoning trace. Not currently open for signups. It runs as the instrument behind the practice, and access is arranged inside an engagement.
How the practice runs it12 more skills in the methodology.
HIPAA Gap Analysis, BAA Review, Framework Mapping, Control Assessment, Risk Assessment, AI Claims Assessment, Part 2 Notice Assessment, Compliance Q&A, Compliance Posture Intake, Document Finder, Skill Router, and AI Tooling Inventory. All open source under Apache 2.0.
Need this done rather than explained? Dan Gonzalez runs Dang's Solutions, the practice that delivers it.