The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes shell scripts (scripts/scaffold_project.sh and scripts/render.sh) to automate the environment setup and video production workflow.
[REMOTE_CODE_EXECUTION]: New projects are initialized using npx create-video, and rendering is performed via npx remotion render. These commands download and execute official Remotion tools from the npm registry.
[EXTERNAL_DOWNLOADS]: The scaffolding process installs several packages, including tailwindcss and @remotion/tailwind, directly from public registries during project initialization.
[PROMPT_INJECTION]: The skill processes external data (JSON, CSV, SRT) to drive video content, creating a surface for indirect prompt injection.
Ingestion points: Data is ingested in references/rules/data-driven.md (JSON datasets), references/rules/subtitles.md (SRT files), and via CLI arguments in scripts/render.sh.
Boundary markers: No specific boundary markers or instruction-guarding delimiters are implemented for the ingested data.
Capability inventory: The skill can execute shell commands (scripts/scaffold_project.sh, scripts/render.sh) and perform file system operations.
Sanitization: There is no evidence of explicit sanitization or validation of the content within the ingested data files.

remotion-video