The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes several standard command-line tools to perform its tasks, including git for accessing repository content, npx remotion for frame rendering, ffmpeg for image processing, and local Python scripts (voiceover.py, qc.py) for audio and quality control. These operations are consistent with the skill's objective of generating video demos from code.\n- [INDIRECT_PROMPT_INJECTION]: The skill's methodology involves reading external data such as application source code, localization files, and icon metadata. This creates an indirect prompt injection surface where content from the analyzed repository could theoretically influence the agent's behavior. However, the instructions are scoped to extracting specific UI elements and strings for visual reconstruction.

synthetic-ui-demo