The Agent Skills Directory

[PROMPT_INJECTION]: The skill reads external project files such as scripts and edit notes which could contain instructions that influence the agent's behavior during the generation process. * Ingestion points: workspace/video-projects//script.md, workspace/video-projects//edit-notes.md, and workspace/episode-ideas/.md. * Boundary markers: The instructions do not define explicit delimiters or 'ignore' warnings for the data being read from these files. * Capability inventory: The skill uses the Read and Write tools to ingest project content and generate an output file. * Sanitization: No specific filtering or validation of the ingested text content is defined.

youtube-metadata