Seo local

Skill Hainrixz/claude-seo-ai/skills/seo-local

Audit and generate Local SEO signals for local-business pages — verify LocalBusiness JSON-LD, NAP consistency, geo coordinates, openingHoursSpecification, and service-area, advise on Google Business Profile alignment, and produce ready-to-inject LocalBusiness JSON-LD. Module M19 (conditional). Feeds both the Search SEO and AI Visibility scores.From its SKILL.md

Install

npx -y skills add Hainrixz/claude-seo-ai --skill seo-local

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

runs commandsInstructs the agent to run 1 command, including `node ${CLAUDE_SKILL_DIR}/../../scripts/validate-jsonld.mjs --url <u>`.

SKILL.md

4.2 KB, 915 tokens by cl100k_base, as published. Nobody here has run it

seo-local (M19)

Local pages live and die on consistent, machine-readable place data. Conditional module: only runs when the page is classified local-business (storefront, service-area, multi-location, contact/location page). Reference: references/schema-tier1.md (LocalBusiness row).

Audits

Working from the PageSnapshot (rendered_dom if present, else raw_html), only for local-business pages:

LocalBusiness schema: a LocalBusiness (or correct subtype, e.g. Restaurant, Dentist) JSON-LD block with required props — name, address (PostalAddress), telephone.
NAP consistency: visible Name / Address / Phone match across the page (header, footer, contact block) and match the schema values — no formatting drift, no stale numbers.
Geo coordinates: geo (GeoCoordinates with latitude/longitude) present and plausible for the stated address.
Opening hours: openingHoursSpecification present, structured (dayOfWeek, opens, closes), and agreeing with any visible hours.
Service-area: for service-area businesses, areaServed declared rather than (or alongside) a PostalAddress storefront.
GBP alignment (advisory): NAP, categories, and hours should match the Google Business Profile — the tool cannot read GBP, so this is advisory only.

Fixes

AUTO: generate a complete, valid LocalBusiness JSON-LD block from user-confirmed NAP, hours, geo, and service-area, with a stable @id. The block is a diff for fix.
NAP / hours drift: PROPOSED — surface the mismatch and a draft correction for per-item accept (the tool cannot know which value is canonical).
GBP alignment: ADVISORY — never written by the tool. Never fabricate an address, phone, coordinates, or hours — ask the user or leave a clearly-marked TODO placeholder they fill before injection.

Verification

Offline: node ${CLAUDE_SKILL_DIR}/../../scripts/validate-jsonld.mjs --url <u> (schema_validator) — JSON validity + required LocalBusiness props; dom_assert confirms visible NAP matches schema.
Tier 1: confirm rich-result eligibility with Google Rich Results Test / schema.org validator. When the data tier (or GBP) is unavailable, status is needs_api — never a false pass.

Findings

Emit findings per schema/finding.schema.json. On a non-local page these are not_applicable (severity 0); on local pages severity is 4, axis both. Examples:

M19.localbusiness.missing — local page with no LocalBusiness schema (status fail, severity 4, fixable: auto, axis both, confidence established). evidence.observed quotes the visible address/phone with no matching ld+json; verification.reproduce runs the validator above.
M19.nap.inconsistent — footer phone differs from schema telephone (status warn, severity 4, fixable: proposed, axis both, confidence directional). evidence.observed quotes both strings; verified by dom_assert.
M19.hours.missing — no openingHoursSpecification despite visible hours (status warn, severity 4, fixable: auto, axis both, confidence established). Each finding: evidence.observed quotes the page; expected_impact is banded + confidence-tagged (no naked %).

Honesty

Consistent NAP + structured place data are established signals for local pack/maps and AI place answers; raw on-page proximity/ranking gains are not promised here — the dominant local-pack factors (proximity, GBP signals, reviews) sit outside the page DOM and are advisory.
Adding geo/openingHoursSpecification will not by itself move local rankings without an accurate, verified GBP; never ship that as a guaranteed win.
Do not invent coordinates from an address via an unverified geocode and present them as fact — mark unconfirmed values TODO.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most marketing audience skills give in 915 tokens

Counted across 690 of the 894 authors here whose files we hold, read 2026-08-07

Apply Poppins font to headingsin 41 of 690, across 6 files
Apply Lora font to body textin 41 of 690, across 6 files
Use Arial fallback for headingsin 39 of 690, across 4 files
Use Georgia fallback for body textin 39 of 690, across 4 files
Maintain text hierarchy and formattingin 39 of 690, across 4 files
Use accent colors for non-text shapesin 38 of 690, across 3 files
Use RGB values for precise color matchingin 38 of 690, across 3 files
Use brand colors for primary text and backgroundsin 36 of 690, across 1 file
Read product marketing context file before asking questions, starting, or auditingin 35 of 690, across 23 files
Use active voice instead of passive voicein 26 of 690, across 10 files
Implement or generate appropriate JSON-LD structured datain 24 of 690, across 17 files
Prioritize clarity over clevernessin 22 of 690, across 8 files

Said here and by no other author read

emit findings per finding schema
check geo coordinates
check opening hours
check service-area declarations
propose fixes for NAP or hours drift
run the jsonld validator

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.