agentleFS
Sign inStart free
claude-worldclaude-world/cf-browser/skills/site-auditor/SKILL.md

site-auditor

Skill9 starsChanged 8 months agoMITView on GitHub

Audit website SEO, links, and accessibility using Cloudflare Browser Run

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. gwonvibe/gwonvibe-agent-skills★ 4same name
    2. paolomoz/skills★ 4same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository5 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Treat external links as unverified until each destination is separately fetched or checked

    line 49

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Site Auditor

Comprehensive website audit for SEO, broken links, and accessibility.

Prerequisites

CF Browser MCP server must be configured (see the CF Browser quick start).

Workflow

Step 1: Crawl Site

browser_crawl(url, limit=50)
→ browser_crawl_status(job_id, wait=True)
→ Get list of all discovered pages

Step 2: Quick Analysis from Crawl Data

The crawl records include URL, record status, and page metadata such as final URL, title, and HTTP status. Parse only fields actually present before making extra calls:

  • metadata.title → check for missing/duplicate titles
  • metadata.status → identify 4xx/5xx error pages
  • metadata.url versus record URL → identify a final-URL change; do not claim a full redirect chain without separate evidence

Step 3: Deep Scrape (only pages with issues)

For pages where crawl metadata is insufficient, use browser_scrape to extract:

  • h1, h2, h3 headings (hierarchy check)
  • img tags (check alt attributes)
  • link[rel="canonical"] canonical URL
  • meta[name="robots"] directives
  • meta[name="description"] (if not in crawl metadata)

Batch scrape in groups of 5 to respect rate limits.

Step 4: Check Links

Using browser_links on 3-5 key pages (homepage, major sections):

  • Categorize: internal, external, resource
  • Cross-reference with crawl results to find orphan pages
  • Identify links pointing to 4xx/5xx pages already evidenced by crawl records
  • Treat external links as unverified until each destination is separately fetched or checked

Step 5: Generate Report

Output a markdown report with sections:

SEO Issues

  • Missing or duplicate <title> tags
  • Missing or duplicate meta descriptions
  • Missing h1 or multiple h1 tags
  • Missing canonical URLs
  • Missing OpenGraph tags

Link Health

  • Broken internal links (404s)
  • Broken external links (only when separately verified)
  • Redirect chains (only when hop-by-hop evidence is available)
  • Orphan pages

Accessibility

  • Images without alt text
  • Missing form labels
  • Missing lang attribute

Structure

  • Sitemap coverage
  • Page depth analysis
  • URL structure issues

Each issue includes:

  • Severity: Critical / Warning / Info
  • Page: URL where issue was found
  • Fix: Specific action to take

Output

Markdown report saved to audit-report-{domain}-{date}.md in the current directory.

Examples

"Audit my website for SEO issues"
→ Crawl + analyze + generate full report

"Check for broken links on docs.example.com"
→ Crawl + link check only

"Review OpenGraph tags across the site"
→ Crawl + extract OG tags + report missing ones

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free