Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →shobcoder/web-scraper
Scrape, crawl, and extract data from websites.
Passed 18 of 22 test cases with the skill, and 9 of 22 without it.
and 10 more in the full report
11 fixed8 passed either way3 still failing1 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.
Extract all product titles, current sale prices, original MSRP, and stock badges from https://deals.example.com/today.
| Checked | Without skill | With skill |
|---|---|---|
| Invokes extract_content_from_websites targeting the deals catalog URL. | Missed | Passed |
The instructions your model reads when the skill loads.
Extract content and data from websites using various techniques including crawling, scraping, and structured data extraction.
// Use extract_content_from_websites for structured extraction
// Supports batch processing of multiple URLs
// Returns JSON format with extracted content
{
tasks: [
{
url: "https://example.com",
prompt: "Extract specific information",
task_name: "optional_name"
}
]
}
// Extract main content from a page
test cases passed, vs 9 / 22 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.