serpapi
Skill25 starsChanged 9 months agoMITView on GitHub
Search the web and e-commerce platforms using the SerpApi API. Use when the user wants to search Google, Google Shopping, Google Jobs, eBay, or Amazon via SerpApi. Triggers on phrases like "search Google for...", "find products on eBay", "search Amazon for...", "find jobs on Google", "Google Shopping results for...", "use SerpApi to...", "search with SerpApi", "look up a product on Amazon", "find eBay listings for...", "search Amazon listings for...".
In this repository11 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- composer-upgradeSkill
- gritqlSkill
- laravel-advanced-conceptsSkill
- npm-upgradeSkill
- packagistSkill
- phpstan-developerSkill
- php-type-safetySkill
- rector-developerSkill
- remotion-3d-background-developerSkill
- slidewire-developerSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use the SerpApi REST API (via WebFetch) to retrieve structured search results from Google, Google Shopping, Google Jobs, eBay, and Amazon.
- Distinctive: line 25
Read the relevant reference file before constructing any request.
- Very specific: line 39
Always show prices with currency and extracted_price for computation.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
SerpApi
Use the SerpApi REST API (via WebFetch) to retrieve structured search results from Google, Google Shopping, Google Jobs, eBay, and Amazon.
Base endpoint: https://serpapi.com/search
Authentication: Pass api_key as a query parameter on every request.
Engines
| Engine | engine value | Reference |
| Google Search | google | references/google-search-api.md |
| Google Shopping | google_shopping | references/google-shopping-api.md |
| Google Jobs | google_jobs | references/google-jobs-api.md |
| Google Immersive Product | google_immersive_product | references/google-immersive-product-api.md |
| eBay | ebay | references/ebay-api.md |
| Amazon Search | amazon | references/amazon-search-api.md |
| Amazon Product | amazon_product | references/amazon-product-api.md |
Read the relevant reference file before constructing any request.
Key Patterns
Chaining APIs
- Google Shopping → Immersive Product: A
shopping_resultsitem'simmersive_product_page_tokenis thepage_tokenforgoogle_immersive_product. - Amazon search → Product detail: A
organic_resultsitem'sserpapi_linklinks directly toamazon_productfor full product details, or use theasinmanually.
Filters from responses
- Google Shopping:
shoprstokens for category-specific filters (brand, colour, size, etc.) come fromfilters[].options[].shoprsorcarousel_filters[].shoprsin the response — never construct them manually. - Google Jobs:
udsfilter tokens come fromfiltersin the response.chipsandltypeare deprecated; useudsinstead. - Google Jobs pagination:
startis discontinued — usenext_page_tokenfromserpapi_pagination.
Presenting results
- Always show prices with currency and
extracted_pricefor computation. - For job listings: show
title,company_name,location,via, and keydetected_extensionsfields (schedule type, remote, salary). - For product results: show
title,price,rating,reviews, andsource/seller. - For eBay: distinguish
sponsoredlistings clearly.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

