The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Fetches font metadata from Google Fonts and utilizes well-known transcription services from OpenAI and Groq for generating captions. These are well-known technology services and are documented for legitimate functionality.
[COMMAND_EXECUTION]: Provides developer-focused CLI commands via npx hyperframes for project initialization, transcription, and validation tasks. These are standard development workflows.
[DYNAMIC_EXECUTION]: Uses Puppeteer-based scripts (animation-map.mjs, contrast-report.mjs) to perform technical audits of HTML compositions, measuring layout, animation choreography, and WCAG contrast compliance. This is a functional requirement for the skill's purpose.
[PROMPT_INJECTION]: No evidence of instructions designed to override agent safety protocols, bypass system guidelines, or extract system prompts.
[DATA_EXFILTRATION]: Does not attempt to access or exfiltrate sensitive user data like credentials or SSH keys; network operations are restricted to well-known technological service providers for project-specific tasks.

hyperframes