seo-local

Example output: [examples/seo-local-sweetgreen-com-20260514/LOCAL-SEO-REPORT.md](../../examples/seo-local-sweetgreen-com-20260514/LOCAL-SEO-REPORT.md)

Local SEO

Score a local business's website against the signals that drive local-pack and "near me" visibility — GBP integration on the page, NAP consistency, on-page local intent, citation footprint on Tier-1 directories, review-platform presence, and local-pack rank for the business's primary keywords. Deliverable is one prioritised fix list, anchored in observable signals.

Adapted from AgriciDaniel/claude-seo's seo-local skill (MIT). Concept and dimension structure mirror the upstream; backend rewired to SE Ranking + Firecrawl + Google APIs. DataForSEO Maps geo-grid and Business Listings checks from the upstream are dropped (no equivalent backend) — see "Limitations" in the deliverable.

Prerequisites

• SE Ranking MCP server connected (used for local-pack rank, on-page audit data, domain context).
• Claude's WebFetch tool available (used for sense-check fallback when Firecrawl is unavailable).
• User provides: (a) a target domain or homepage URL, (b) at least one primary local keyword (e.g. "dentist Brooklyn", "plumber near me"), (c) target country and ideally city/region for local-pack scoping. Optional: GBP listing URL, Yelp/Trustpilot URLs for review scraping.

Process

1. Validate target & preflight. See skills/seo-firecrawl/references/preflight.md for the canonical 3-stage preflight (credit balance, Firecrawl availability, Google APIs). Skill-specific notes:
2. Normalise the target (strip protocol from domain; confirm homepage is fetchable). Confirm at least one local keyword was provided — if none, infer from <title> + <h1> of the homepage; if still ambiguous, ask the user before continuing.
3. Estimated SE Ranking cost for this skill: ~15–25 credits (1 audit re-check + 3–5 SERP queries + 1 domain overview).
4. Firecrawl: optional with WebFetch fallback, ~6–9 Firecrawl credits if available (hard cap 12). When available, steps 4 (GBP-on-page audit), 5 (NAP extraction), and 7 (review scraping) run on the homepage + 5 sample pages + provided review URLs. Without Firecrawl those steps degrade to WebFetch-only — schema/JSON-LD detection and tel: / address element extraction become best-effort prose inspection. Pass --no-firecrawl to force WebFetch-only.
5. Google APIs: tier 1 (GSC) unlocks step 8b (GSC local query performance) after the local-pack rank step; tier 2 (GA4) additionally unlocks step 8c (GA4 organic-by-landing-page enrichment). See skills/seo-google/references/cross-skill-integration.md for the full enrichment contract.

1. Business-type detection
2. Read homepage + /contact + footer prose (WebFetch markdown is enough for this).
3. Classify as one of:
4. Brick-and-Mortar — visible street address, "Visit us at", embedded Maps iframe.
5. Service Area Business (SAB) — no street address, "serving {region}", "we come to you", areaServed in schema without address.streetAddress.
6. Hybrid — both signals present (e.g. showroom + service area).
7. This determines which checks apply downstream. SAB skips embedded-map and physical-address consistency. Record in LOCAL-SEO-REPORT.md "Snapshot".

1. Industry-vertical detection
2. From URL patterns (/menu, /practice-areas, /listings, /inventory), <title>, page prose, infer one of: Restaurant / Healthcare / Legal / Home Services / Real Estate / Automotive / Generic.
3. This routes citation-source recommendations and schema-subtype recommendations later — load references/local-citation-sources.md for the vertical's Tier-1 directories.

1. GBP signals on the page mcp__firecrawl-mcp__firecrawl_scrape (with formats: ["rawHtml"])
2. Scrape homepage + /contact (or whichever page has the most local intent).
3. From rawHtml extract:
4. Embedded Google Maps iframe (<iframe src="https://www.google.com/maps/embed?...">) — record place ID if present.
5. Reviews widget / GBP rich snippet markup.
6. aggregateRating JSON-LD block (presence is the strongest signal that the site wants stars in SERPs).
7. Business hours visibility on page (open-at-search-time correlates with rank — Whitespark's #5 factor).
8. Click-to-call: count of <a href="tel:..."> elements.
9. GBP profile link: any <a href> to https://g.page/... or https://maps.app.goo.gl/... or https://www.google.com/maps/place/....
10. If Firecrawl unavailable: WebFetch markdown can detect a tel: link in some renderings but loses iframes and JSON-LD. Mark Maps embed / aggregateRating / GBP profile-link detection as (skipped — Firecrawl required).

1. NAP consistency mcp__firecrawl-mcp__firecrawl_scrape on homepage + 5 sample pages
2. Sample pages: homepage, /contact, /about, plus 2 service or location pages (pick from sitemap or top traffic pages).
3. For each, extract:
4. Visible NAP from rendered prose. Address pattern (street + city + region + postal), phone (tel: href + display format), business name (logo alt, footer, schema name).
5. NAP from JSON-LD. Parse every <script type="application/ld+json"> block. Pull name, address.streetAddress, address.addressLocality, address.addressRegion, address.postalCode, telephone.
6. Compare across the 6 page samples + schema. Any divergence (different phone format on the contact page vs homepage; "Suite 200" missing from one footer; schema phone in international format while page shows local format) → record in nap-inconsistencies.csv.
7. Brick-and-mortar only: if a Maps iframe is present, attempt to read the embedded address from the iframe URL (the place ID and address are URL-encoded). Compare to page/schema NAP. SAB skips this.
8. If nap-inconsistencies.csv is empty after the scan, write nap-inconsistencies.csv as a one-line file with header only and note "NAP consistent across {n} pages and schema" in LOCAL-SEO-REPORT.md.

1. Local-pack rank tracking DATA_getSerpResults with country/region filters
2. For each user-provided local keyword (or the 1–3 inferred from homepage):
3. Call DATA_getSerpResults with the user's country and the most specific region/city the API supports (use DATA_getSerpLocations first to confirm a valid location code if the user supplied a city).
4. Capture: top 10 organic, local-pack presence (yes/no), the 3 businesses in the local pack if shown (name, rating, review count), AIO presence.
5. Cross-check: is the target domain in the top 10 organic? Is the target business name in the local pack?
6. Save the parsed result per keyword to local-keywords.csv (columns: keyword,country,location,local_pack_present,target_in_pack,target_pack_position,target_organic_position,top_pack_competitor_1,top_pack_competitor_2,top_pack_competitor_3).
7. Note the local-pack-ads caveat: the SE Ranking SERP returns the AI/ads-modified pack as Google serves it. If the local pack shows ads, record that — local-pack ad density jumped from 1% to 22% of mobile US local searches in 2025–2026 per Sterling Sky.

1. Reviews scraping mcp__firecrawl-mcp__firecrawl_scrape on user-provided review URLs
2. Inputs (user-provided, optional). GBP listing URL (https://www.google.com/maps/place/...), Yelp business URL, Trustpilot business URL, BBB profile URL.
3. For each provided URL: scrape with formats: ["rawHtml"]. From the parsed DOM, extract: total review count, average rating, date of most recent review (review velocity proxy), count of owner responses on the most recent 10 reviews.
4. Aggregate signals:
5. Velocity: ≥1 new review in last 18 days = healthy (Sterling Sky 18-day rule). >21 days since last = "review cliff" risk.
6. Volume: <10 Google reviews flags below the magic threshold.
7. Star rating: 4.5+ matches c