The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill provides instructions to install various official packages from the @remotion scope (e.g., @remotion/three, @remotion/media, @remotion/captions, etc.) and the mediabunny utility using standard package managers.
[COMMAND_EXECUTION]: Rule files contain shell commands for project dependency management (e.g., npx remotion add ...). These are standard developer workflow instructions for adding functionality to a Remotion project.
[PROMPT_INJECTION]: The skill demonstrates patterns for fetching and processing external data, creating a surface for indirect prompt injection.
Ingestion points: Files calculate-metadata.md, compositions.md, import-srt-captions.md, and lottie.md describe patterns for fetching external data (JSON, SRT, Lottie assets). tailwind.md instructs the agent to fetch documentation from an external site.
Boundary markers: None. The provided code snippets do not include explicit boundary markers or instructions to ignore embedded commands in the fetched data.
Capability inventory: Processing is confined to fetch operations and the Remotion rendering environment; no direct shell execution capabilities are exposed to the content of the fetched data.
Sanitization: Examples do not demonstrate validation or sanitization of the fetched external content before it is processed or used to populate component props.

remotion-best-practices