The Agent Skills Directory

[COMMAND_EXECUTION]: The workflow incorporates the use of shell commands such as grep to perform quality checks on generated script files, ensuring they adhere to length and vocabulary requirements.\n- [DYNAMIC_EXECUTION]: The skill uses a hardcoded Python script executed via python3 -c to count characters and words in the generated Markdown files. This script processes text by removing metadata and specific placeholders before counting.\n- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its processing of external data.\n
Ingestion points: User-provided themes and external information retrieved through research tools enter the context via file optimization and web search steps.\n
Boundary markers: No delimiters are defined in the instructions to isolate external data from internal instructions.\n
Capability inventory: The skill has the ability to execute terminal commands (python3, grep) and manage files in the docs/src/ai/video/ directory.\n
Sanitization: No sanitization procedures are specified for external content processed by the agent.

video-script