Meta Data Audit Claude Skill
This skill audits a website's title tags and meta descriptions and produces an actionable SEO report. It crawls pages to find missing, duplicate, too-long, too-short, or multiple titles and descriptions, generic boilerplate titles, and keyword-stuffed metadata, then recommends ready-to-paste replacements.
Quick Take
Point the skill at a site URL, sitemap, or local HTML folder. It builds a title and description inventory, runs severity-ranked audit checks with length-band analysis, and returns a prioritized report with replacement metadata written to fit.
What The Skill Checks
- Missing or empty title tags and meta descriptions, plus titles and descriptions duplicated across indexable pages, each reported with the exact page and current value.
- Length problems on both sides: titles outside the 30 to 60 character band and descriptions outside 70 to 160 characters, where snippets get truncated or waste space, plus pages carrying multiple title or description tags from CMS and plugin conflicts.
- Generic boilerplate titles ("Home", "Untitled", brand-only), descriptions that just repeat the title, keyword stuffing, and informational signals like title/H1 mismatch. A brand suffix option strips your brand pattern before duplicate detection.
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 extract metadata from pages and audit the resulting inventory. Copy the skill folder into your Claude skills directory and 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 (including an optional brand suffix), the five-step audit workflow, and the resources the skill relies on.
Audit Checks Reference (references/audit-checks.md)
Full definitions, thresholds, and rationale for every audit check, from missing and duplicate metadata to length bands and keyword stuffing.
Report Template (references/report-template.md)
The output structure the skill follows when writing the final audit report, including the length distribution table.
Metadata Extractor Script (scripts/extract_metadata.py)
Crawls a live site, URL list, or local HTML folder within the configured page limits and collects every title tag and meta description into a JSON inventory, along with the first H1, canonical, robots, and Open Graph tags.
Metadata Auditor Script (scripts/audit_metadata.py)
Runs the audit checks against the metadata inventory, with options for brand suffix stripping and noindex handling, and outputs the structured audit report data with length-band distributions.