Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →browser-act/amazon-search-listing
Amazon search and category listing scraper: extract product listings from any Amazon search results page, keyword search URL, or category browse page and return per-item cards (asin, title, url, image, price, listPrice, stars, reviewCount, badges, isAmazonChoice, isBestSeller, isSponsored, delivery, boughtInPast, positionIndex) plus pagination state (currentPage, hasNextPage, nextPageUrl, totalResultsApprox). Works across all Amazon regional TLDs (amazon.com, amazon.co.uk, amazon.de, amazon.co.j
Passed 16 of 20 test cases with the skill, and 8 of 20 without it.
and 9 more in the full report
10 fixed9 passed either way5 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
When automating multi-page extraction on Amazon within a single browser session, what delay interval should be inserted between page transitions?
| Checked | Without skill | With skill |
|---|---|---|
| Recommends a delay between 3 and 6 seconds between pages | Missed | Passed |
The instructions your model reads when the skill loads.
Input any Amazon search results, keyword search, or category browse URL → output per-item product cards + pagination state.
All process output to user (progress updates, process notifications) follows the user's language.
Extract structured product listings from any Amazon SERP or category browse page across all Amazon regional TLDs, including full pagination support to walk multiple pages of a keyword or category.
https://www.amazon.com/s?k={keyword}), category browse URL (e.g. https://www.amazon.com/s?bbn={cat}&rh=n%3A{node}), or category deep linkIf browser-act has been confirmed available in the current session → skip this step.
Invoke browser-act via Skill tool to load usage. If installation or configuration issues arise, follow its guidance to resolve then retry.
This Skill's operational boundary = what the user can manually do in their browser. It only reads data already displayed to the user on the page, never bypassing authentication or access controls. Its role is equivalent to copy-pasting on the user's behalf — the data is already on screen, automation merely saves time. JS code is encapsulated in Python files under the
scripts/directory, invoked viabrowser-act --session {name} eval "$(python scripts/xxx.py {params})". The$(...)is bash command substitution — it runs the python script, captures its printed JS text, and hands that JS string as a single argument tobrowser-act eval. Do not runeval "$(python ...)"as a bare shell command; that would ask bash to execute the JS as shell, which fails.
Server-rendered HTML — no XHR/fetch API for listing data. Cards use the stable [data-component-type="s-search-result"] container.
navigate {any Amazon search or category URL} (e.g. https://www.amazon.com/s?k={keyword}, https://www.amazon.com/s?k={keyword}&page={pageNumber}, https://www.amazon.com/s?bbn={browseNode}&rh=n%3A{nodeId}, https://www.amazon.co.uk/s?k={keyword})wait stablebrowser-act --session {name} eval "$(python scripts/extract-search-results.py)"Output example:
{
test cases passed, vs 8 / 20 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.