The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses local shell commands including ffmpeg, ffprobe, and open (macOS) to process video assets, extract frames, and display output folders to the user. These operations are essential for the video analysis and generation workflows described in the skill.
[CREDENTIALS_UNSAFE]: The skill handles an ARCADS_API_KEY for authentication. It implements safe handling practices by instructing the user to store the key in a local .env file rather than pasting it into the chat or public context, and it explicitly directs the agent to avoid printing the key in its responses.
[EXTERNAL_DOWNLOADS]: The skill references standard third-party tools such as ffmpeg and the openai-whisper Python package. These are reputable utilities used for video processing and audio transcription respectively.
[SAFE]: The skill implements several safety-oriented design patterns, including mandatory dialogue confirmation gates and credit cost estimation approvals. These 'human-in-the-loop' requirements ensure the user maintains control over the agent's actions and expenditures.

arcads-external-api