The Agent Skills Directory

[SAFE]: The skill uses uv run to execute internal Python scripts for HTML cleaning and metadata extraction. These scripts are provided within the skill package and do not perform any network operations or access sensitive system files.
[SAFE]: The clean_html.py script uses the standard lxml library to remove noisy or dangerous tags (scripts, styles, etc.) from HTML files, which is a security best practice for processing untrusted content.
[SAFE]: The extract_metadata.py script uses extruct to parse structured data (like JSON-LD) from HTML files, which is a routine data extraction task.
[SAFE]: All file access is performed on paths provided as arguments or derived from them (e.g., meta.json in the same directory), following standard workflow for data processing skills.

scrape-analyze-page