agentleFS
peterfoxpeterfox/agent-skills/serpapi/SKILL.md

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...".

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
  1. Distinctive:

    Use the SerpApi REST API (via WebFetch) to retrieve structured search results from Google, Google Shopping, Google Jobs, eBay, and Amazon.

    line 8
  2. Distinctive:

    Read the relevant reference file before constructing any request.

    line 25
  3. Very specific:

    Always show prices with currency and extracted_price for computation.

    line 39

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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

Engineengine valueReference
Google Searchgooglereferences/google-search-api.md
Google Shoppinggoogle_shoppingreferences/google-shopping-api.md
Google Jobsgoogle_jobsreferences/google-jobs-api.md
Google Immersive Productgoogle_immersive_productreferences/google-immersive-product-api.md
eBayebayreferences/ebay-api.md
Amazon Searchamazonreferences/amazon-search-api.md
Amazon Productamazon_productreferences/amazon-product-api.md

Read the relevant reference file before constructing any request.

Key Patterns

Chaining APIs

  • Google Shopping → Immersive Product: A shopping_results item's immersive_product_page_token is the page_token for google_immersive_product.
  • Amazon search → Product detail: A organic_results item's serpapi_link links directly to amazon_product for full product details, or use the asin manually.

Filters from responses

  • Google Shopping: shoprs tokens for category-specific filters (brand, colour, size, etc.) come from filters[].options[].shoprs or carousel_filters[].shoprs in the response — never construct them manually.
  • Google Jobs: uds filter tokens come from filters in the response. chips and ltype are deprecated; use uds instead.
  • Google Jobs pagination: start is discontinued — use next_page_token from serpapi_pagination.

Presenting results

  • Always show prices with currency and extracted_price for computation.
  • For job listings: show title, company_name, location, via, and key detected_extensions fields (schedule type, remote, salary).
  • For product results: show title, price, rating, reviews, and source/seller.
  • For eBay: distinguish sponsored listings clearly.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.