The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run various CLI commands using npx hyperframes for linting, validation, inspection, and rendering of video compositions. It also executes a local utility script node skills/hyperframes/scripts/animation-map.mjs to analyze animation choreography.
[EXTERNAL_DOWNLOADS]: The generated HTML templates reference the GSAP library from a well-known content delivery network (https://cdn.jsdelivr.net/npm/gsap@3.14.2/dist/gsap.min.js) to enable animation capabilities. This download targets a well-known service and is standard for web-based animation tools.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon data from external project files, such as design.md, house-style.md, and variable definitions in JSON format. These files serve as the 'source of truth' for the agent's output, creating a surface where malicious instructions in project data could influence the agent's behavior.
Ingestion points: Reads design.md, house-style.md, references/ documentation, and variable files provided via the --variables-file flag.
Boundary markers: The instructions do not define specific delimiters or isolation techniques for the content of these project files.
Capability inventory: The agent has the ability to execute shell commands (npx, node) and write HTML/JS files to the local file system.
Sanitization: There is no mention of sanitizing or validating the content of the imported design and variable files before they are used to generate code.

hyperframes