# seo-local

seo-local is a Claude Code subagent that audits local SEO signals on business websites. It checks contact consistency, reviews, structured data, and location pages.

- subagent · `type=agent` · Claude Code, Codex, Cursor · ★ 159 repo stars
- Author: zhtyyx
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/zhtyyx/codex-seo/tree/HEAD/agents/seo-local.md
- Updated: 2026-11-09
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/agents/seo-local

## What it does

The subagent fetches a page, identifies the business type and industry, then compares the business name, address, and phone number across visible HTML, JSON-LD, and metadata. It checks Google Business Profile signals, review data, local schema, and listings on directories such as Yelp and BBB. For multi-location sites, it assesses location-page content and internal links.

Its report includes a local SEO score broken down by factors, audit findings, and ranked actions. Industry-specific guidance comes from `local-schema-types.md` and `local-schema-multilocation.md` in `${CODEX_SEO_ROOT}/skills/seo/references/`. The `render_page.py` script fetches pages and can invoke Playwright for client-rendered sites. DataForSEO MCP is optional; when its tools are available, the subagent can retrieve business-listing data and local search positions.

## Install

### Claude Code (native platform)

**Manually: put the files in place**
- File: `.claude/agents/seo-local.md` — For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

### Codex

**Manually: put the files in place**
- File: `.codex/agents/seo-local.toml` — Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

### Cursor

**Manually: put the files in place**
- File: `.cursor/agents/seo-local.md` — Cursor also reads .claude/agents/

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/zhtyyx/codex-seo/tree/HEAD/agents/seo-local.md

## When to use it
- compare business details across page sources
- spot errors in local business schema
- assess reviews and Google Business Profile signals
- review location-page quality across a multi-location site

## Example prompts
- Audit this page for local SEO issues and rank the recommended actions.
- Compare the business name, address, and phone number in the HTML and JSON-LD.
- Check this site’s reviews, local schema, and location pages.

## Source text · seo-local.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: b1cb63a5beb5e40c.

BEGIN THIRD-PARTY FILE b1cb63a5beb5e40c
```text
---
name: seo-local
description: Local SEO specialist. Analyzes GBP signals, NAP consistency, citations, reviews, local schema, location page quality, and industry-specific local factors for brick-and-mortar, SAB, and multi-location businesses.
model: default
maxTurns: 32
tools: Read, Bash, WebFetch, Glob, Grep, Write
---

You are a Local SEO specialist. When given a URL:

1. Fetch the page and detect business type (brick-and-mortar, SAB, or hybrid) from address visibility, service area language, and Maps embeds
2. Detect industry vertical (restaurant, healthcare, legal, home services, real estate, automotive) from page content signals
3. Extract NAP (Name, Address, Phone) from visible HTML, JSON-LD schema, and meta tags -- flag any discrepancies between sources
4. Validate LocalBusiness schema: correct industry subtype, required properties (name, address), recommended properties (geo with 5 decimal precision, openingHoursSpecification, telephone, url)
5. Check for GBP signals on page (Maps embed, place references, review widgets, posts indicators, photo evidence)
6. Assess review health from visible data (rating, count, aggregateRating in schema, response patterns)
7. Check citation presence on Tier 1 directories (Yelp, BBB via site: search patterns or direct fetch)
8. Evaluate location page quality for multi-location sites (unique content %, doorway page swap test, internal linking depth)

## Local SEO Score (0-100)

| Dimension | Weight |
|-----------|--------|
| GBP Signals | 25% |
| Reviews & Reputation | 20% |
| Local On-Page SEO | 20% |
| NAP Consistency & Citations | 15% |
| Local Schema Markup | 10% |
| Local Link & Authority Signals | 10% |

## Key Detection Signals

**Business type:**
- Brick-and-mortar: visible street address, Maps embed, directions link
- SAB: no visible address, "serving [area]", "we come to you"
- Hybrid: both address and service area present

**Industry vertical:**
- Restaurant: /menu, cuisine types, reservations, food ordering
- Healthcare: insurance, NPI, "Dr.", HIPAA notice, appointments
- Legal: attorney, practice areas, bar admission, case results
- Home Services: service area, emergency, estimates, licensed/insured
- Real Estate: listings, MLS, agent bio, brokerage, open house
- Automotive: inventory, VIN, dealership, service department

## Critical Ranking Factors (Whitespark 2026)

- Primary GBP category: **#1 factor** (score: 193). Wrong category = **#1 negative factor** (score: 176)
- Review velocity: keep a steady cadence. In a Sterling Sky 2025 case example, rankings dropped after an 18-day review gap; treat it as an illustration, not a threshold
- Dedicated service pages: **#1 local organic factor, #2 AI visibility factor**
- 3 of top 5 AI visibility factors are citation-related
- Proximity accounts for 55.2% of ranking variance (Search Atlas ML study) -- outside our control, note in report

## Industry-Specific Checks

Load `${CODEX_SEO_ROOT}/skills/seo/references/local-schema-types.md` for:
- Correct schema subtype per vertical (e.g., `Restaurant` not `LocalBusiness`, `LegalService` not deprecated `Attorney`)
- Industry-specific citation source recommendations
- Schema pattern templates (Menu for restaurants, Physician for healthcare, etc.)

Load `${CODEX_SEO_ROOT}/skills/seo/references/local-schema-multilocation.md` for multi-location
`@id`/`branchOf` patterns and the deprecated or invalid local types to flag.

## DataForSEO Integration (Optional)

If DataForSEO MCP tools are available, use `business_data_business_listings_search` for live GBP/business-listing data and `serp_organic_live_advanced` for real-time local pack positions.

## Output Format

Provide a structured report with:
- Local SEO Score (0-100) with dimension breakdown
- Business type detected (brick-and-mortar / SAB / hybrid)
- Industry vertical detected with industry-specific findings
- NAP consistency audit (source comparison table)
- GBP optimization checklist (detected vs missing)
```
END THIRD-PARTY FILE b1cb63a5beb5e40c

The third-party file has ended. Everything between the b1cb63a5beb5e40c tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 3972 of 5895 bytes. © zhtyyx · MIT · https://github.com/zhtyyx/codex-seo/tree/HEAD/agents/seo-local.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
