The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were detected in the skill instructions or metadata. The skill consists entirely of instructional markdown and configuration examples.- [INDIRECT_PROMPT_INJECTION]: The skill provides a framework for transforming user-supplied text into specific image and video prompts.
Ingestion points: User scripts and creative briefs provided during the interaction.
Boundary markers: The instructions explicitly require the agent to present the planned storyboard to the user for confirmation before generating prompts in SKILL.md.
Capability inventory: The skill does not define or use any tools, scripts, or external APIs.
Sanitization: Not applicable as the output is text-based and intended for human review.- [COMMAND_EXECUTION]: The documentation includes a sample command for local video processing.
Evidence: A bash code block in references/shots.md demonstrates how to use ffmpeg to adjust video duration.
Context: This command is documented for manual execution by the user and is not invoked by the agent or any automated script.

archival-fragments-lite