The Agent Skills Directory

[SAFE]: The skill incorporates a 'legal gate' framework that mandates checking Terms of Service, robots.txt, and GDPR requirements before initiating any network requests. It explicitly instructs the agent to stop if a CAPTCHA or hard block is encountered, preventing unauthorized access circumvention.
[EXTERNAL_DOWNLOADS]: The skill references established and well-known libraries such as Playwright, Crawlee, Scrapy, and curl_cffi. Documentation links point to official domains (crawlee.dev, playwright.dev, readthedocs.io). These are documented for use in scraper development and are not used for malicious payload delivery.
[COMMAND_EXECUTION]: The provided scripts/verify.sh is a local utility for static analysis of user-written scrapers. It uses standard shell tools (grep, find) to check for the presence of pacing and compliance markers. It does not execute the code it scans, nor does it perform network operations.
[DATA_EXFILTRATION]: While the skill is designed for data collection (scraping), it contains explicit warnings against collecting personal data without a lawful basis and provides guidance on data minimization and filtering sensitive fields at the source.

data-scraper