The Agent Skills Directory

[SAFE]: The skill is designed for local media processing and follows best practices for data privacy, such as instructing the agent to crop out browser chrome and personal information from screen recordings. It does not attempt to access credentials, perform network operations, or obfuscate its behavior.- [COMMAND_EXECUTION]: The skill utilizes standard system binaries (ffmpeg and ffprobe) to perform its core functions. These commands are used locally to transform and validate asset files within the project directory. The execution is strictly limited to the stated technical purpose.- [PROMPT_INJECTION]: No evidence of prompt injection, role-play bypasses, or instructions to ignore safety guidelines were found in the skill metadata or instructions.

asset-prep