The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on the execution of external commands via the npx hyperframes CLI for website capture, text-to-speech generation, transcription, linting, validation, and snapshotting. It also invokes a custom script node skills/hyperframes-animation-map/scripts/animation-map.mjs to analyze generated compositions.
[DYNAMIC_EXECUTION]: The skill's primary workflow involves generating executable HTML, CSS, and JavaScript files (compositions/*.html) based on data extracted from external URLs. These generated files incorporate logic from the storyboard and are subsequently executed in a headless browser environment through the validate and snapshot commands.
[PROMPT_INJECTION]: There is a high risk of indirect prompt injection because the skill ingests untrusted data from arbitrary websites (text, screenshots, asset descriptions) and passes this content to sub-agents for script writing and code generation.
Ingestion points: extracted/visible-text.txt, extracted/asset-descriptions.md, and direct viewing of screenshots in references/step-1-capture.md and references/step-6-build.md.
Boundary markers: No explicit boundary markers or instructions to ignore embedded commands in the captured website data are specified.
Capability inventory: The agent can write files, execute shell commands via npx, and spawn sub-agents to process the data.
Sanitization: No sanitization or validation of the scraped website content is documented before it is used to generate the final code compositions.
[EXTERNAL_DOWNLOADS]: The skill references external JavaScript libraries from well-known CDNs, including @dotlottie/player-component and gsap via cdn.jsdelivr.net, as well as typography from fonts.googleapis.com.

website-to-hyperframes