Yelp Search logo

Yelp Search

Organization
letta-ai
yelp-search

Search Yelp for local businesses, get contact info, ratings, and hours. Use when finding services (cleaners, groomers, restaurants, etc.), looking up business phone numbers to text, or checking ratings before booking. Triggers on queries about finding businesses, restaurants, services, or "look up on Yelp".

Overview

Publisherletta-ai
Repositoryskills
Skill nameyelp-search
Stars
144
Forks
25
Bundled files
5
Links
Skill sourceRepositoryHomepage
  • 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.

  • 5 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by letta-ai on GitHub. Read the source before you install it.

Installation

Install the Yelp Search 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/letta-ai/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/tools/yelp-search .claude/skills/yelp-search
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Yelp Search 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 Yelp Search 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 Yelp Search 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.

Yelp Search Integration

Search for local businesses on Yelp to find services, get contact information, check ratings, and retrieve hours of operation.

Setup

1. Yelp API Key (Required)

  1. Go to https://www.yelp.com/developers
  2. Create an account or sign in
  3. Click "Create App" and fill out the form
  4. Copy your API Key

Add to your .env file:

YELP_API_KEY=your_api_key_here

2. Browser-Use for Reviews (Optional)

Only needed if you want to extract review text (slow, ~30-60s per request).

Install dependencies:

bash
uv add browser-use playwright langchain-openai
uv run playwright install chromium

Add to .env:

OPENAI_API_KEY=your_openai_key_here

Note: Review extraction uses browser-use to search DuckDuckGo (since Yelp blocks direct scraping). For most use cases, the rating + review_count from the API is sufficient.

Scripts

All scripts are in tools/yelp-search/scripts/ and should be run with uv run python.

search.py - Find Businesses (Primary Tool)

bash
uv run python tools/yelp-search/scripts/search.py "search term" --location "City, State"

Options:

FlagDescriptionExample
--location, -lCity, address, or zip"San Francisco" or "94123"
--latitude/--longitudeGPS coordinates--latitude 37.78 --longitude -122.41
--limit, -nNumber of results (default: 5)-n 10
--sort-bySort orderrating, distance, review_count, best_match
--pricePrice filter (1-4)--price 1,2 for $ and $$ only
--jsonOutput raw JSON

Examples:

bash
# Find top-rated dog groomers
uv run python tools/yelp-search/scripts/search.py "dog groomer" -l "San Francisco" --sort-by rating

# Find cheap restaurants nearby
uv run python tools/yelp-search/scripts/search.py "restaurants" -l "94123" --price 1,2 --sort-by distance

# Search near a specific address
uv run python tools/yelp-search/scripts/search.py "laundry pickup" -l "123 Main St, San Francisco"

details.py - Get Business Hours & Info

bash
uv run python tools/yelp-search/scripts/details.py "business-alias"

The business alias is in the Yelp URL (e.g., the-laundry-corner-san-francisco).

phone_search.py - Reverse Lookup

bash
uv run python tools/yelp-search/scripts/phone_search.py "+14155551234"

get_reviews.py - Extract Review Text (Slow)

bash
uv run python tools/yelp-search/scripts/get_reviews.py "Business Name" -l "City" -n 3

Note: Uses browser-use which is slow (~30-60s). Yelp blocks direct scraping, so it searches DuckDuckGo for cached reviews as a workaround.

scrape_reviews.py - Direct Yelp Scraping (Alternative)

bash
uv run python tools/yelp-search/scripts/scrape_reviews.py "https://www.yelp.com/biz/business-alias" -n 5

Requires Browserbase credentials:

BROWSERBASE_API_KEY=your_key_here
BROWSERBASE_PROJECT_ID=your_project_id

Note: Uses Browserbase with proxies to bypass Yelp's CAPTCHA. More reliable than get_reviews.py but requires a Browserbase account.

Best Practices

Evaluating Quality Without Review Text

The API provides rating + review_count which is usually sufficient:

RatingReview CountInterpretation
4.5+50+Excellent, reliable data
4.5+<20Promising but limited data
4.0-4.4100+Good, well-established
<4.0anyProceed with caution

Finding Services with Specific Needs

When looking for services with specific requirements (weekend hours, pickup/delivery, etc.):

  1. Search with --sort-by rating to get best options
  2. Get details on top candidates to check hours
  3. Filter for businesses open when you need them
  4. Contact directly to confirm specific services (pickup, delivery, etc.) since Yelp doesn't always have this info

Search Tips

  • Use specific terms: "laundry pickup" not just "laundry"
  • Search near an address for accurate distance: -l "123 Main St, City"
  • Sort by rating first, then check distance on results
  • Check review_count - high ratings with few reviews may be unreliable

Response Data

Each business result includes:

  • name - Business name
  • phone - Phone number (use for texting/calling)
  • rating - Yelp rating (1-5 stars)
  • review_count - Number of reviews
  • price - Price level ($ to $$$$)
  • location - Full address
  • hours - Operating hours by day (in details)
  • distance - Distance from search location
  • categories - Business categories
  • is_open_now - Current open/closed status

Limitations

FeatureStatusNotes
Business search✅ WorksFast, reliable
Business details✅ WorksIncludes hours
Phone lookup✅ WorksReverse search
Review text (API)❌ Paid onlyRequires enterprise tier
Review text (scraping)⚠️ Slowbrowser-use workaround via DuckDuckGo
  • Free API tier: 500 calls/day
  • Results limited to 50 per request
  • Some business info (pickup/delivery) not in API - contact directly

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Yelp Search AI skill do?

Search Yelp for local businesses, get contact info, ratings, and hours. Use when finding services (cleaners, groomers, restaurants, etc.), looking up business phone numbers to text, or checking ratings before booking. Triggers on queries about finding businesses, restaurants, services, or "look up on Yelp".

Why use Yelp Search on TypingMind?

Because you install it once and use it with any model. Yelp Search 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 Yelp Search in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/letta-ai/skills/tree/main/tools/yelp-search. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Yelp Search?

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 Yelp Search?

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

Is the Yelp Search AI skill free?

It is published on GitHub by letta-ai. Check the repository for licensing terms. 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.

Related AI Skills

View all
mattpocock logo

Diagnosing Bugs

mattpocock
CommunityPopular

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

22.3K
264.4K
2 files
View
mattpocock logo

Implement

mattpocock
CommunityPopular

Implement a piece of work based on a spec or set of tickets.

22.3K
264.4K
1 files
View
mattpocock logo

Improve Codebase Architecture

mattpocock
CommunityPopular

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

22.3K
264.4K
2 files
View
mattpocock logo

Prototype

mattpocock
CommunityPopular

Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

22.3K
264.4K
3 files
View

Set up your own AI workspace now

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