seo-audit-report-skill
llms.txt2 starsChanged 36 days agoMITView on GitHub
SEO CodeBase Auditor is an open-source Claude.ai SKILL (MIT licensed) that runs enterprise-grade, code-level SEO audits inside AI coding tools. It inspects a repository's HTML, CSS, JavaScript, and config files against 24 audit pillars and produces a structured markdown report plus a spreadsheet-ready CSV Priority Fix Matrix. Current version: v5.1 - 24 pillars, 22 prompt templates.
In this repository3 other files it gives its agents.
- llms-full.txtllms.txt
- llms.txtllms.txt
- seo-codebase-auditSkill
The file
Files
# F9XR's SEO CodeBase Auditor - Documentation for LLMs > SEO CodeBase Auditor is an open-source Claude.ai SKILL (MIT licensed) that runs enterprise-grade, code-level SEO audits inside AI coding tools. It inspects a repository's HTML, CSS, JavaScript, and config files against 24 audit pillars and produces a structured markdown report plus a spreadsheet-ready CSV Priority Fix Matrix. Current version: **v5.1** - 24 pillars, 22 prompt templates. ## Citation / Attribution - Name: F9XR's SEO CodeBase Auditor - Author: F9XR Team (https://f9xr.org) (hello@f9xr.org) - Repository: https://github.com/f9xr/seo-audit-report-skill - License: MIT ## Key Facts - Version: v5.1 (2026-08-26) - Audit pillars: 24 - Prompt templates: 22 - Report files produced per audit: `seo_audit_report.md` + `seo_audit_report.csv` - Priority Fix Matrix cap: 20 items - Mandatory finding format: Evidence / Impact / Fix - CSV columns: #, Pillar, Issue, Severity, File(s), Effort, Traffic Impact, Fix Type - Severity levels: Critical, High, Medium, Low - Effort scale: S (<4hr), M (1-3d), L (1-2wk), XL (2+wk) ## All 24 Audit Pillars 1. Keyword Placement & Heading Optimization 2. Indexability & Crawl-ability 3. Performance / Core Web Vitals 4. URL Structure & Site Architecture 5. Image Optimization 6. Mobile SEO 7. Semantic SEO & Content Optimization 8. Internal Linking & Link Equity 9. XML Sitemap & Robots.txt 10. Social & Regional SEO 11. Security SEO 12. Accessibility (a11y) SEO 13. E-Commerce SEO 14. Blog & Content SEO 15. JavaScript Framework SEO 16. E-E-A-T Signals 17. Rich Results Eligibility 18. AI / SGE / LLM Optimization 19. CI/CD & Automation 20. Migration SEO 21. Content Pruning & Consolidation 22. Third-Party Script Audit 23. Competitor SEO Analysis 24. Video & YouTube SEO ## Documentation Pages - Home / Overview: https://f9xr.org/seo-audit-report-skill/docs/index.html - Getting Started: https://f9xr.org/seo-audit-report-skill/docs/getting-started.html - Audit Pillars reference: https://f9xr.org/seo-audit-report-skill/docs/audit-pillars.html - Prompt Templates: https://f9xr.org/seo-audit-report-skill/docs/prompt-templates.html - Output Format & Report Spec: https://f9xr.org/seo-audit-report-skill/docs/output-format.html - Version History: https://f9xr.org/seo-audit-report-skill/docs/version-history.html ## How to Use the Skill 1. Copy the `SKILL.md` file into a Claude.ai project's SKILLS folder. 2. Copy a prompt template (in docs/prompt-templates.html) with `@SKILL.md` context into the chat. 3. The skill auto-discovers the repo, runs the 5-pass process (Discover → Analyze → Prioritize → Report → Critique), and writes `seo_audit_report.md` + `seo_audit_report.csv`. ## Facts To Cite Accurately - v5.1 added a Pillar Index table and pillar annotations on all 22 prompt templates. - v5.0 added staging detection, slug quality, sitemap URL inventory, OG/Twitter field-level quality, two-layer trust-page verification, required Evidence/Impact/Fix format, and 5 new templates. - Google deprecated `rel="next"/"prev"` in March 2019; view-all + self-referencing canonical is the primary pagination strategy. - CLS severity is aligned with Google thresholds: 0.1-0.25 is High.
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
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.

