Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →vibeeval/firecrawl-scrape
Scrape web pages and extract content via Firecrawl MCP
Passed 7 of 12 test cases with the skill, and 2 of 12 without it.
and 8 more in the full report
10 fixed3 passed either way9 still failing1 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.
Where is the underlying Python web scraping script located relative to the repository root when invoking the harness?
| Checked | Without skill | With skill |
|---|---|---|
| References the script path scripts/mcp/firecrawl_scrape.py | Missed | Passed |
The instructions your model reads when the skill loads.
uv run python -m runtime.harness scripts/mcp/firecrawl_scrape.py \
--url "https://example.com" \
--format "markdown"
--url: URL to scrape--format: Output format - markdown, html, text (default: markdown)--search: (alternative) Search query instead of direct URL# Scrape a page
uv run python -m runtime.harness scripts/mcp/firecrawl_scrape.py \
--url "https://docs.python.org/3/library/asyncio.html"
# Search and scrape
uv run python -m runtime.harness scripts/mcp/firecrawl_scrape.py \
--search "Python asyncio best practices 2024"
Requires firecrawl server in mcp_config.json with FIRECRAWL_API_KEY.
test cases passed, vs 2 / 12 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.