npx skills add ...
npx skills add letta-ai/skills --skill 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".
npx skills add letta-ai/skills --skill yelp-search
Search for local businesses on Yelp to find services, get contact information, check ratings, and retrieve hours of operation.
Add to your .env file:
Only needed if you want to extract review text (slow, ~30-60s per request).
Install dependencies:
Add to .env:
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.
All scripts are in tools/yelp-search/scripts/ and should be run with uv run python.
Options:
| Flag | Description | Example |
|---|---|---|
--location, -l | City, address, or zip | "San Francisco" or "94123" |
--latitude/--longitude | GPS coordinates | --latitude 37.78 --longitude -122.41 |
--limit, -n | Number of results (default: 5) | -n 10 |
--sort-by | Sort order | rating, distance, review_count, best_match |
--price | Price filter (1-4) | --price 1,2 for $ and $$ only |
--json | Output raw JSON |
Examples:
The business alias is in the Yelp URL (e.g., the-laundry-corner-san-francisco).
Note: Uses browser-use which is slow (~30-60s). Yelp blocks direct scraping, so it searches DuckDuckGo for cached reviews as a workaround.
Requires Browserbase credentials:
Note: Uses Browserbase with proxies to bypass Yelp's CAPTCHA. More reliable than get_reviews.py but requires a Browserbase account.
The API provides rating + review_count which is usually sufficient:
| Rating | Review Count | Interpretation |
|---|---|---|
| 4.5+ | 50+ | Excellent, reliable data |
| 4.5+ | <20 | Promising but limited data |
| 4.0-4.4 | 100+ | Good, well-established |
| <4.0 | any | Proceed with caution |
When looking for services with specific requirements (weekend hours, pickup/delivery, etc.):
--sort-by rating to get best options"laundry pickup" not just "laundry"-l "123 Main St, City"rating first, then check distance on resultsreview_count - high ratings with few reviews may be unreliableEach business result includes:
| Feature | Status | Notes |
|---|---|---|
| Business search | ✅ Works | Fast, reliable |
| Business details | ✅ Works | Includes hours |
| Phone lookup | ✅ Works | Reverse search |
| Review text (API) | ❌ Paid only | Requires enterprise tier |
| Review text (scraping) | ⚠️ Slow | browser-use workaround via DuckDuckGo |
uv run python tools/yelp-search/scripts/search.py "search term" --location "City, State"# 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"uv run python tools/yelp-search/scripts/details.py "business-alias"uv run python tools/yelp-search/scripts/phone_search.py "+14155551234"uv run python tools/yelp-search/scripts/get_reviews.py "Business Name" -l "City" -n 3uv run python tools/yelp-search/scripts/scrape_reviews.py "https://www.yelp.com/biz/business-alias" -n 5BROWSERBASE_API_KEY=your_key_here
BROWSERBASE_PROJECT_ID=your_project_id