The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes shell commands to manage the generation and hosting of sensory reports.
Executes wrangler deploy to publish generated reports to Cloudflare Workers.
Uses the open command to display local HTML files to the user.
Employs Unix utilities like tr and head to generate unique identifiers for deployment subdomains.
[EXTERNAL_DOWNLOADS]: The skill references external assets from well-known services to build visual reports.
Loads Chart.js and html2pdf.js from the JSDelivr CDN for data visualization and PDF conversion.
Fetches typography assets from Google Fonts.
[PROMPT_INJECTION]: The skill processes external data which creates a surface for indirect prompt injection.
Ingestion points: Analyzes content from user-uploaded PDFs, images, and text files as specified in the 'Analyze Cupping Documents' section of SKILL.md.
Boundary markers: There are no explicit delimiters or specific instructions provided to the agent to ignore embedded commands within the extracted document text.
Capability inventory: The agent has access to shell execution and deployment capabilities through the wrangler CLI.
Sanitization: No specific filtering or sanitization of document content is described prior to the analysis and report generation steps.

catador-pro