Local Citations

Community

garrettjsmith

local-citations

When the user wants to build citations, fix NAP inconsistencies, manage business directory listings, or audit citation presence. Also use when the user mentions "citations," "NAP consistency," "business directories," "listing management," "data aggregators," or "citation cleanup." For GBP profile work, see gbp-optimization. For full audit, see local-seo-audit.

Overview

Publisher	garrettjsmith
Repository	`localseoskills`
Skill name	`local-citations`
Stars	140
Forks	27
Bundled files	Instructions only
License	MIT
Links	Skill source Repository Homepage

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 garrettjsmith on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/garrettjsmith/localseoskills/tree/main/skills/local-citations
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.

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/garrettjsmith/localseoskills.git /tmp/localseoskills
mkdir -p .claude/skills
cp -r /tmp/localseoskills/skills/local-citations .claude/skills/local-citations

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Local Citations 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 Local Citations 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 Local Citations 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.

Local Citations

Default data tool: LocalSEOData (localseodata-tool). Use citation_audit to check NAP consistency across 20 directories in one call (50 credits). For citation building/submission, use Whitespark or BrightLocal.

You are an expert in local citation strategy. Your goal is to build a consistent, authoritative citation profile that reinforces NAP data across the web and supports local ranking signals.

What is a Citation?

A citation is any online mention of a business's Name, Address, and Phone number (NAP). Two types:

Structured citations: Directory listings (Yelp, BBB, industry directories) with formatted NAP fields
Unstructured citations: Mentions on blogs, news sites, or other pages where NAP appears in text

NAP Consistency Rules

Name: Character-for-character match. "Smith's Plumbing" ≠ "Smiths Plumbing" ≠ "Smith Plumbing LLC" Address: Exact formatting. "123 Main St Ste 200" everywhere — not "Suite" on some and "Ste" on others Phone: Same primary number everywhere. If using a tracking number, it must also appear on your website

Common Inconsistencies

Old addresses from a previous location
DBA vs. legal name variations
Suite/unit number present on some, missing on others
Toll-free vs. local number
Different phone from call tracking implementations
Abbreviation mismatches (St/Street, Ave/Avenue)

Citation Building Priority

Tier 1: Essential (Do First)

Google Business Profile
Apple Maps / Apple Business Connect
Bing Places for Business
Facebook Business Page
Yelp

Tier 2: Data Aggregators

These feed data to hundreds of smaller directories:

Data Axle (formerly Infogroup)
Neustar/Localeze
Foursquare

Tier 3: Major Directories

BBB (Better Business Bureau)
Yellow Pages / YP.com
Angi (Angie's List)
Thumbtack
MapQuest
Superpages
Manta
Citysearch

Tier 4: Industry-Specific

Examples by vertical:

Healthcare: Healthgrades, Vitals, WebMD, Zocdoc
Legal: Avvo, FindLaw, Justia, Martindale
Home services: HomeAdvisor, Porch, Houzz
Restaurants: OpenTable, TripAdvisor, Zomato
Real estate: Zillow, Realtor.com, Redfin
Auto: CarFax, Cars.com, AutoTrader

Tier 5: Local & Niche

Local Chamber of Commerce
Local business associations
City/town business directories
State professional association directories
Niche industry directories

Citation Audit Process

Search "business name" "phone number" to find existing citations
Search "business name" "address" for additional mentions
Check major directories manually
Use citation audit tools (BrightLocal, Whitespark, Moz Local)
Document every listing: URL, current NAP, accuracy status
Prioritize fixes: wrong info on high-authority sites first

Citation Cleanup

Fix Priority Order

Tier 1 directories (Google, Apple, Bing, Yelp, Facebook)
Data aggregators (Data Axle, Neustar, Foursquare)
High-authority directories with wrong information
Duplicate listings on any directory
Industry-specific directories
Lower-authority directories

How to Fix

Claim and update: Most directories allow you to claim the listing
Submit corrections: Use the directory's correction/update form
Data aggregator updates: Fix at the source — changes propagate downstream
Duplicate suppression: Merge or mark duplicates on each platform

Citation Building for Multi-Location

At Scale

Use data aggregator submissions to cascade to smaller directories
Bulk submit to Tier 1-3 directories
Prioritize industry-specific directories by location
Maintain a master spreadsheet of all citations per location

Per-Location Tracking

Track per location:

Total citations
Percentage accurate
Missing from which Tier 1 directories
Industry-specific directory coverage

Output Format

Citation Audit Report

Total citations found
Accuracy rate (% consistent NAP)
Tier-by-tier coverage
Specific listings needing correction
Missing directory opportunities
Prioritized action plan

Task-Specific Questions

What is the exact NAP (as it should appear everywhere)?
Has the business moved, changed names, or changed phone numbers?
Single location or multi-location?
What industry? (determines industry-specific directories)
Has any citation work been done previously?

What to Do Next

What You Found	Next Action	Skill
Citations are clean but GBP isn't optimized	GBP is the #1 citation — optimize it first	`gbp-optimization`
Found NAP inconsistencies during audit	Fix citations as part of the broader audit action plan	`local-seo-audit`
Website schema doesn't match citation data	Align schema with corrected NAP	`local-schema`
Managing citations for multiple locations	Build a citation management system per-location	`multi-location-seo`
Citations are clean but still not ranking	Citations alone won't fix ranking — run a geogrid scan to diagnose	`geogrid-analysis`

Default next step: After citation cleanup, wait 4-8 weeks for changes to propagate through aggregators and downstream directories, then re-audit to verify.

Tools for This Skill

See docs/tool-routing to pick based on what's connected.

Citation audit (find listings, check accuracy) → citation tools (multiple options)
Citation building (submit to directories) → citation tools (multiple options — quality varies)

Frequently asked questions

What does the Local Citations AI skill do?

Why use Local Citations on TypingMind?

Because you install it once and use it with any model. Local Citations 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 Local Citations in TypingMind?

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

Which AI models can use Local Citations?

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 Local Citations?

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

Is the Local Citations AI skill free?

Yes. It is published on GitHub by garrettjsmith 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

3 Statement Model

NousResearch

OrganizationPopular

Build integrated IS/BS/CF financial workbooks in Excel.

Comps Analysis

Build comparable-company valuation workbooks in Excel.

Lbo Model

Build leveraged buyout workbooks with IRR/MOIC in Excel.

Pptx Author

Build PowerPoint decks headless with python-pptx.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Local Citations

What is a Citation?

NAP Consistency Rules

Common Inconsistencies

Citation Building Priority

Tier 1: Essential (Do First)

Tier 2: Data Aggregators

Tier 3: Major Directories

Tier 4: Industry-Specific

Tier 5: Local & Niche

Citation Audit Process

Citation Cleanup

Fix Priority Order

How to Fix

Citation Building for Multi-Location

At Scale

Per-Location Tracking

Output Format

Citation Audit Report

Task-Specific Questions

What to Do Next

Tools for This Skill

Frequently asked questions

Related AI Skills

Set up your own AI workspace now