Seo Maps logo

Seo Maps

CommunityPopular
AgriciDaniel
seo-maps

Maps intelligence for local SEO: geo-grid rank tracking, GBP profile auditing via API, review intelligence across Google/Tripadvisor/Trustpilot, cross-platform NAP verification, competitor radius mapping, and LocalBusiness schema generation. Three tiers: free (Overpass + Geoapify), DataForSEO, and DataForSEO + Google. Use when user says "maps", "geo-grid", "rank tracking", "GBP audit", "review velocity", "competitor radius", or "SoLV".

Overview

PublisherAgriciDaniel
Repositoryclaude-seo
Skill nameseo-maps
Stars
17.1K
Forks
2.5K
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by AgriciDaniel on GitHub. Read the source before you install it.

Installation

Install the Seo Maps AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/AgriciDaniel/claude-seo.git /tmp/claude-seo
mkdir -p .claude/skills
cp -r /tmp/claude-seo/skills/seo-maps .claude/skills/seo-maps
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Seo Maps in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Seo Maps on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Seo Maps is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Maps Intelligence (March 2026)

Maps platform analysis for local businesses. Works with external APIs to assess how a business appears on Google Maps, Bing Places, Apple Maps, and OpenStreetMap.

Boundary with seo-local: This skill analyzes the business on maps PLATFORMS (via APIs). seo-local analyzes local SEO signals on the WEBSITE (via HTML fetch). Do not duplicate seo-local on-page analysis. Recommend /seo local <url> for website-level checks.


Quick Reference

CommandWhat it doesTier
/seo maps <url>Full maps presence audit (auto-selects tier)0+
/seo maps grid <keyword> <location>Geo-grid rank scan (7x7, 1 keyword default)1+
/seo maps reviews <business> <location>Cross-platform review intelligence1+
/seo maps competitors <keyword> <location>Competitor radius mapping0+
/seo maps nap <business-name>Cross-platform NAP verification0+
/seo maps schema <business-name>Generate LocalBusiness JSON-LD from data0+
/seo maps gbp <business> <location>GBP completeness audit1+

Three-Tier Capability Detection

Before any analysis, detect the available capability tier:

Tier 0 (Free)

Detection: DataForSEO MCP tools NOT available. Capabilities: Overpass API competitor discovery, Geoapify POI search, Nominatim geocoding, static GBP checklist, schema generation, cross-platform NAP guidance. Load: ../seo/references/maps-free-apis.md

Tier 1 (DataForSEO)

Detection: business_data_business_listings_search MCP tool IS available. Capabilities: Everything in Tier 0 PLUS geo-grid rank tracking, live GBP profile audit, review intelligence (velocity, sentiment, distribution), GBP post activity, Q&A data, Tripadvisor/Trustpilot reviews. Load: ../seo/references/maps-api-endpoints.md

Tier 2 (DataForSEO + Google Maps Platform)

Detection: Tier 1 available AND Google Maps API key in environment. Capabilities: Everything in Tier 1 PLUS Google Places details, real-time business status, AI-powered place summaries, photo analysis. Note: Google ToS restricts storage to place_id only. Lat/lng cached 30 days max.

Always communicate the detected tier to the user at the start of analysis.


Geo-Grid Rank Tracking (Tier 1+)

Simulates Google Maps searches from multiple GPS coordinates to show ranking variation across a geographic area. Requires DataForSEO.

Load: ../seo/references/maps-geo-grid.md for algorithm, SoLV formula, heatmap format. Load: ../seo/references/maps-api-endpoints.md for Maps SERP endpoint details.

Workflow

  1. Geocode business address to get center lat/lng
  2. Generate grid points (default: 7x7, 5km radius) using Haversine offset formula
  3. Display cost estimate and ask for confirmation before proceeding
  4. Fire DataForSEO Maps SERP API calls with location_coordinate per grid point
  5. Find target business rank at each point
  6. Calculate SoLV: (top_3_count / total_points) * 100
  7. Render ASCII heatmap in output

Cost Warning (REQUIRED)

Before every geo-grid scan, display:

Geo-Grid Scan: [keyword] at [location]
Grid: 7x7 (49 points) | Keywords: [N] | Est. cost: $[amount]
DataForSEO credits will be consumed. Proceed?

GBP Profile Audit (Tier 1 preferred, Tier 0 manual)

Audits the 25 fields that affect Google Business Profile quality and ranking.

Load: ../seo/references/maps-gbp-checklist.md for full checklist and scoring.

AI & 2026 context (third-party reported): Ask Maps, reported by AP News as a Gemini conversational Maps feature launched 2026-03-12 (iOS/Android, US + India). AI Mode (1B+ MAU, reported from Google I/O 2026 keynote coverage; not confirmed on a Google-owned source) increasingly surfaces 1-2 business local AI interfaces in third-party terminology, and agentic booking/calling for local services (home repair, beauty, pet care) rolls out to all US users summer 2026 (Google can call businesses on the user's behalf). New 2026 GBP API additions: review media URLs, recurring local-post scheduling, review reply-state/moderation, and invitation Place ID. Source: blog.google/products-and-platforms/products/search/search-io-2026/ · developers.google.com/my-business/content/latest-updates

Tier 1 Workflow

  1. Fetch business profile via DataForSEO My Business Info API (keyword or CID)
  2. Map API response fields to 25-field checklist
  3. Score each field: Present + Optimized = 2pts, Present = 1pt, Missing = 0pts
  4. Apply industry-specific weight multipliers
  5. Normalize to 0-100 scale

Tier 0 Workflow

  1. Fetch the business website via WebFetch
  2. Extract any visible GBP signals (Maps embed, place references, review widgets)
  3. Apply static checklist based on detectable signals
  4. Mark undetectable fields as "Unknown (requires DataForSEO for live data)"

Review Intelligence (Tier 1+)

Cross-platform review analysis: velocity, sentiment, rating distribution, fake detection.

Reference: ../seo/references/local-seo-signals.md for benchmarks (shared with seo-local).

Workflow

  1. Fetch Google reviews via DataForSEO Reviews API (sort by newest)
  2. Calculate review velocity: reviews per month over last 6 months
  3. Check 18-day rule (Sterling Sky): any 3-week gap = ranking risk
  4. Analyze rating distribution: healthy = bell curve skewed to 5-star
  5. Calculate owner response rate: responses / total reviews
  6. Fetch Tripadvisor and Trustpilot reviews (if available)
  7. Cross-platform comparison table

Fake Review Detection Signals

Flag reviews matching 2+ of these patterns:

  • Uniform timing (multiple reviews same day/hour)
  • Reviewer accounts with limited history or single review
  • Geographic inconsistencies (reviewer location vs business location)
  • Exclusively 5-star velocity spike (vs historical baseline)
  • Identical or near-identical text across reviews
  • Sudden volume spike without corresponding marketing activity

Competitor Radius Mapping (Tier 0+)

Identify and analyze competitors within a defined radius.

Tier 0 (Overpass API)

Load: ../seo/references/maps-free-apis.md for query templates.

  1. Geocode business address
  2. Query Overpass API for businesses with same OSM tag within radius
  3. Parse results: name, address, phone, website, distance from center
  4. Sort by distance, present as competitor landscape table

Tier 1 (DataForSEO)

  1. Use Maps SERP API with business keyword + location
  2. Extract top 20 competitors with full profile data
  3. Compare: rating, review count, categories, photos, attributes
  4. Calculate competitive density score: competitors per km^2

Cross-Platform NAP Verification (Tier 0+)

Check business listing consistency across Google, Bing Places, Apple, and OSM.

Workflow

  1. Search for business name on each platform:
    • Google: infer from GBP data or Maps SERP result
    • Bing: WebFetch https://www.bing.com/maps?q=BUSINESS+NAME+LOCATION
    • Apple: manual check (no public API -- verify/claim Apple business listing presence; treat Apple Business launch/rename claims as TechRadar-sourced until confirmed by Apple primary)
    • OSM: Overpass or Nominatim search
  2. Extract NAP (Name, Address, Phone) from each source
  3. Compare for consistency: exact match, partial match, missing, or conflicting
  4. Flag discrepancies as Critical (name mismatch), High (address mismatch), Medium (phone mismatch)
  5. Recommend claiming unclaimed profiles

Schema Generation (Tier 0+)

Generate LocalBusiness JSON-LD markup from collected data.

Reference: ../seo/references/local-schema-types.md for industry subtypes (shared with seo-local).

Workflow

  1. Determine most specific schema subtype for the industry
  2. Populate required properties: @type, name, address, image
  3. Add recommended properties: telephone, url, geo, openingHoursSpecification, priceRange
  4. Add strategic properties for multi-location: branchOf, areaServed, sameAs
  5. Add aggregateRating if review data available
  6. Output valid JSON-LD block ready for implementation

Do NOT generate self-serving review markup -- Google ignores LocalBusiness review markup from the business itself. Only mark up third-party reviews visible on the page.


Reference Files

Load on-demand as needed (do NOT load all at startup):

  • ../seo/references/maps-api-endpoints.md: DataForSEO endpoint details, params, costs
  • ../seo/references/maps-free-apis.md: Overpass, Geoapify, Nominatim query templates
  • ../seo/references/maps-geo-grid.md: Grid algorithm, SoLV formula, heatmap rendering
  • ../seo/references/maps-gbp-checklist.md: 25-field GBP audit with industry weights
  • ../seo/references/local-seo-signals.md: Ranking factors, review benchmarks (shared)
  • ../seo/references/local-schema-types.md: LocalBusiness subtypes by industry (shared)

Output

Generate MAPS-ANALYSIS-{domain}.md with:

  1. Maps Health Score: XX/100 with dimension breakdown table
  2. Capability tier detected (Tier 0 or Tier 1) with explanation of what's available
  3. Geo-grid heatmap (Tier 1): ASCII grid with SoLV percentage and average rank
  4. GBP profile audit: field-by-field scoring with industry-specific weights
  5. Review intelligence: velocity chart, rating distribution, response rate, cross-platform comparison
  6. Competitor landscape: count in radius, top 5 by rating/reviews, competitive density
  7. Cross-platform presence: Google/Bing/Apple/OSM listing status
  8. Schema recommendation: generated LocalBusiness JSON-LD (if missing or incomplete)
  9. Top 10 prioritized actions (Critical > High > Medium > Low)
  10. Cost report: DataForSEO credits consumed during analysis (Tier 1 only)
  11. Limitations disclaimer: what could not be assessed at current tier

Cross-Skill Delegation

  • Website on-page local signals: recommend /seo local <url>
  • Full AI search visibility: recommend /seo geo <url>
  • Schema validation and fixes: recommend /seo schema <url>
  • Live SERP and keyword data: recommend /seo dataforseo [command]

Error Handling

ScenarioAction
DataForSEO MCP not availableDrop to Tier 0. Inform user: "DataForSEO not detected. Running free-tier analysis. For geo-grid tracking and review intelligence, install the DataForSEO extension."
Business not found in Maps SERPTry My Business Info with keyword. If still not found, report "Business not found in Google Maps for this location."
Geocoding fails (Nominatim)Ask user to provide coordinates or a more specific address.
API rate limit hitReport the limit. Suggest waiting or using standard (queued) method instead of live.
No reviews foundReport zero review state. Recommend review generation strategy with 18-day cadence target.
Multi-location detectedAsk user which location to analyze, or offer batch mode with per-location cost estimate.

Frequently asked questions

What does the Seo Maps AI skill do?

Maps intelligence for local SEO: geo-grid rank tracking, GBP profile auditing via API, review intelligence across Google/Tripadvisor/Trustpilot, cross-platform NAP verification, competitor radius mapping, and LocalBusiness schema generation. Three tiers: free (Overpass + Geoapify), DataForSEO, and DataForSEO + Google. Use when user says "maps", "geo-grid", "rank tracking", "GBP audit", "review velocity", "competitor radius", or "SoLV".

Why use Seo Maps on TypingMind?

Because you install it once and use it with any model. Seo Maps is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Seo Maps in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/AgriciDaniel/claude-seo/tree/main/skills/seo-maps. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Seo Maps?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Seo Maps?

As many as you like. As long as a model supports skills, you can use Seo Maps with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Seo Maps AI skill free?

Yes. It is published on GitHub by AgriciDaniel under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇