Llms.txt Audit Claude Skill
This skill audits a website's /llms.txt file for AI and LLM discoverability and produces an actionable report. It fetches and parses the file against the llmstxt.org specification to find a missing file, a file served as HTML instead of markdown, a missing required H1 title or blockquote summary, broken or redirecting links, links missing descriptions, malformed list items, wrong-host or relative URLs, duplicates, and whether a companion /llms-full.txt exists.
What The Skill Checks
- File-level problems: a missing
/llms.txt, a file served as HTML instead of markdown, the wrong content type, an empty file with no sections, and a missing required H1 title or blockquote summary. - Link quality across every entry: broken (non-200) or redirecting links, links missing descriptions, malformed list items that aren't proper markdown links, links to the wrong host, and links that are noindexed or blocked by robots.txt.
- Hygiene and completeness signals: relative instead of absolute URLs, duplicate links, and whether a companion
/llms-full.txtfile exists alongside the main file.
How The Skill Is Packaged
The skill follows the standard Claude Agent Skill structure: a SKILL.md file with YAML frontmatter and workflow instructions, a references/ folder with the full audit check definitions and report template, and a scripts/ folder with Python scripts that fetch and parse the file and audit it against the spec. Every report can be exported to a shareable Word .docx or a flat .csv of findings via the bundled md_to_docx.py and findings_to_csv.py scripts. Install it with npx claude-seo-skills install llms-txt-audit, or copy the skill folder into your Claude skills directory; Claude invokes it automatically when a request matches its description.
Skill Files
Every file in the skill is embedded below directly from the Claude-SEO-Skills repository, so you can review exactly what the skill instructs Claude to do before installing it.
SKILL.md
The skill definition: frontmatter, inputs to collect, the five-step workflow against the llmstxt.org spec, and the resources the skill relies on.
Audit Checks Reference (references/audit-checks.md)
Full definitions, severities, and rationale for all fourteen checks, from a missing file and HTML serving to relative URLs and a missing companion file.
Report Template (references/report-template.md)
The output structure the skill follows, including file status, issues grouped by type, and prioritized remediation actions.
Llms.txt Collector Script (scripts/collect_llms.py)
Fetches and parses /llms.txt, extracting the H1 title, blockquote summary, H2 sections, and list items while recording HTTP status and content type, and probes each linked URL.
Llms.txt Auditor Script (scripts/audit_llms.py)
Runs the audit checks against the collected inventory to validate it against the llmstxt.org specification and outputs the structured report data.