Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →davekilleen/scrape
Scrape web pages via Scrapling — stealth fetching, anti-bot bypass, CSS selectors, no API key.
Passed 11 of 18 test cases with the skill, and 6 of 18 without it.
and 6 more in the full report
8 fixed6 passed either way7 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
The page at https://security-check.example.com relies on complex bot detection. Bypass the challenge on the first try without wasting attempts on basic HTTP tools.
| Checked | Without skill | With skill |
|---|---|---|
| Calls scrapling_stealthy_fetch directly on the first attempt. | Missed | Passed |
The instructions your model reads when the skill loads.
Extract data from any website using Scrapling's MCP tools. Bypasses Cloudflare, handles dynamic JS-rendered pages, supports CSS selectors to pre-filter content (saves tokens).
/scrape <url>
/scrape <url> with selector .article-content
/scrape stealth <url>
/scrape bulk <url1> <url2> <url3>
| Scenario | Tool | Why |
|---|---|---|
| Simple page, no anti-bot | scrapling_get | Fastest. HTTP with browser TLS fingerprint |
| JS-rendered / SPA content | scrapling_fetch | Uses real Chromium browser |
| Cloudflare / anti-bot protected | scrapling_stealthy_fetch | Stealth mode, solves captchas |
| Multiple pages, same pattern | scrapling_bulk_get / scrapling_bulk_fetch | Parallel processing |
Determine from the user's request:
.main-content, #article, table.data)Default path (try in order, escalate on failure):
scrapling_get — fast HTTP, handles most sitesscrapling_fetch (real browser)test cases passed, vs 6 / 18 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.