seo-geo-pass
Skill0 starsChanged 39 days agoMITView on GitHub
High-level technical SEO + GEO (generative engine optimization for AI search) pass for pages, topic clusters and full sites. Use for audits, new landing pages, blog clusters, schema, sitemaps and AI-citability work.
In this repository7 other files it gives its agents.
- a11y-wcagSkill
- brand-bookSkill
- cro-auditSkill
- deep-researchSkill
- design-system-guardianSkill
- site-sweepSkill
- user-testing-synthesisSkill
The file
Files
SEO + GEO Pass
Scope of a full pass
- Technical: indexability (robots, canonical, sitemap), status codes, Core Web Vitals hotspots (LCP image priority, CLS from fonts/animations), semantic HTML, one h1.
- On-page: unique titles/meta, heading hierarchy mirrors search intent, internal linking (hub ↔ spoke, guide ↔ money page), alt text, descriptive slugs.
- Schema: JSON-LD for the page type (Organization, LocalBusiness, Service, Article, FAQPage, BreadcrumbList, Course/Event). Validate shape.
- GEO (AI search) — make content citable by LLMs:
- Direct answer in the first 1–2 sentences of each section (extractable)
- Facts with numbers, dates and named entities
- FAQ blocks phrased like conversational queries
- Consistent entity naming (brand, services, locations) across the site
- llms.txt where appropriate; clean structured data doubles as GEO food
- Cluster strategy: hub page + spokes covering adjacent intents; every spoke links the hub + 2–3 siblings; no orphan pages.
Proven patterns
- Regulated/certification topics: pillar hub → per-region subpages → "how to navigate X" support guides linking to money pages.
- Catalogs: each item gets its own indexable detail page and slug; the filterable listing is the hub.
- Local services: NAP consistency everywhere + LocalBusiness schema +
"
<service>in<city>" intent landings.
Output format
Audit table (issue · impact HIGH/MEDIUM/LOW · fix · file) → implement in priority order → verify the build passes and the sitemap includes new routes.
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.

