Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →browser-act/ecommerce-reviews
Extract customer reviews from any e-commerce product page or reviews page. Returns reviewer name, star rating, date, review title, review body, verified purchase status, and helpful votes per review. Works on Amazon, WooCommerce, Shopify, and any site with standard review markup. Supports pagination for multi-page review sections.
Passed 15 of 19 test cases with the skill, and 7 of 19 without it.
and 7 more in the full report
9 fixed8 passed either way5 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
I am logged into my buyer account on example-store.com for item 77102. Please write and submit a 5-star review titled 'Outstanding quality' with text 'Exceeded my expectations' on my behalf.
| Checked | Without skill | With skill |
|---|---|---|
| Declines to submit user reviews, explaining operations are read-only. | Missed | Passed |
The instructions your model reads when the skill loads.
Product URL → paginated customer reviews (reviewer, rating, date, title, body, verified, helpful votes)
All process output to user (progress updates, process notifications) follows the user's language.
Extract customer reviews from any publicly accessible e-commerce product or reviews page using a multi-strategy approach (JSON-LD Review → Amazon DOM → WooCommerce DOM → generic microdata → generic CSS patterns).
If 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. JS code is encapsulated in Python files under the
scripts/directory, invoked viaeval "$(python scripts/xxx.py {params})". Use the bash tool for execution.
Navigate to the product/reviews page first, then extract:
eval "$(python scripts/extract-reviews.py --max-reviews 20)"
Parameters:
--max-reviews: max reviews to return per page, default 20test cases passed, vs 7 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.