Skip to main content
Generalfusengine

seo-local

Use when optimizing local SEO. Covers Google Business Profile, NAP consistency, citations, reviews acquisition, Local Pack ranking, location pages, LocalBusiness schema.

Stars
13
Source
fusengine/agents
Updated
2026-05-17
Slug
fusengine--agents--seo-local
View on GitHubRaw SKILL.md

// install — copy + paste into any project

mkdir -p .claude/skills && curl -fsSL https://raw.githubusercontent.com/fusengine/agents/HEAD/plugins/seo/skills/seo-local/SKILL.md -o .claude/skills/seo-local.md

Drops the SKILL.md into .claude/skills/seo-local.md. Works with Claude Code, Cursor, and any agent that loads SKILL.md files from .claude/skills/.

Local SEO

Workflow

  1. Audit Google Business Profile (categories, hours, photos, posts, services)
  2. Check NAP consistency across web (citations: Yelp, Bing, Apple Maps, industry directories)
  3. Analyze reviews (volume, recency, response rate, sentiment)
  4. Map ranking in Local Pack for target keywords + geo
  5. Optimize location pages (one per service area, LocalBusiness schema)

NAP Consistency

Must be character-for-character identical on the site, GBP, and every directory:

[Business Name]
[Street Number] [Street], [Suite]
[City], [Region] [Postal Code]
[+CC Phone]
  • Abbreviations must match too: Route ≠ Rte, Suite ≠ Ste. One variation fractures the entity.

GBP as an Entity Signal (2026)

  • GBP is no longer just a local directory — AI engines cross-reference it as an entity anchor. ~42% of local AI citations originate from listings.
  • A complete profile = ~2.7x more likely to rank in the Local Pack. Fill categories, hours, photos, posts, services.
  • Service areas = named cities / postal codes only (max ~20). Country- or state-wide service areas are no longer allowed (Google change, June 2025).

Quality Gates

  • Warning at 30+ location pages
  • Hard stop at 50+ location pages (manual audit required)
  • Each location page must have unique content (not template fill-in)

LocalBusiness Schema (GEO-priority)

AI engines (ChatGPT, Perplexity, Gemini) parse LocalBusiness JSON-LD to answer "best [service] near me". Precise geo + areaServed = better entity resolution in local AI Overviews.

{
  "@context": "https://schema.org",
  "@type": "[SpecificType]",
  "name": "[Business Name]",
  "address": { "@type": "PostalAddress", "streetAddress": "[Street]",
    "addressLocality": "[City]", "addressRegion": "[Region]",
    "postalCode": "[Postal Code]", "addressCountry": "[CC]" },
  "geo": { "@type": "GeoCoordinates", "latitude": "[lat]", "longitude": "[lng]" },
  "areaServed": { "@type": "GeoCircle",
    "geoMidpoint": { "@type": "GeoCoordinates", "latitude": "[lat]", "longitude": "[lng]" },
    "geoRadius": "[meters]" },
  "sameAs": ["[GBP URL]", "[directory URL]", "[social URL]"],
  "openingHoursSpecification": [{ "@type": "OpeningHoursSpecification",
    "dayOfWeek": ["Monday"], "opens": "[HH:MM]", "closes": "[HH:MM]" }],
  "aggregateRating": { "@type": "AggregateRating",
    "ratingValue": "[x.x]", "reviewCount": "[n]" }
}
  • @type: use the specific subtype (Plumber, Dentist, Restaurant…), not generic LocalBusiness — better category matching.
  • geo (GeoCoordinates): disambiguates the entity; coordinates must match the GBP pin and Apple Maps.
  • areaServed as GeoCircle (geoMidpoint + geoRadius): drives "near me" matching for LLMs.
  • sameAs array (GBP + directories + socials): confirms existence across authoritative sources.
  • LLMs do cite local businesses when schema + GBP + reviews are solid.

References

  • seo-schema — LocalBusiness JSON-LD (templates/json-ld/localbusiness.json)
  • seo-entity — declare the business entity via sameAs (Wikidata, GBP)
  • skills/seo/10-local-seo/ (gbp, nap-citations, reviews, local-pack, landing-pages, local-backlinks)