atomicbot-ai/atomic-agent/ffmpeg

ffmpeg

Transform audio and video files with `ffmpeg` and inspect them with ffprobe. Operations are non-destructive: always write to a new output file. Re-encoding can be slow on long media — set realistic expectations.

Setup health check (run first, every session)

Verify with one solo step:

[{ "tool": "os.shell.run", "args": { "cmd": "ffmpeg", "args": ["-version"] } }]

Outcome map:

• exit 0 + version → ready, proceed.
• command not found: ffmpeg → enter Setup playbook → "ffmpeg missing".

Setup playbook (when prerequisites are missing)

ffmpeg missing

Reply (solo reply step):

"ffmpeg is not installed. I can install it: brew install ffmpeg. Install it?"

On yes:

[{ "tool": "os.shell.run", "args": { "cmd": "brew", "args": ["install", "ffmpeg"] } }]

On Linux: apt-get install ffmpeg.

When to use

• "Convert this video/audio to <format>", "extract the audio from this mp4".
• "Trim from 0:30 to 1:00", "resize to 720p", "make a GIF from this clip".
• "What codec / duration / resolution is this file?" (use ffprobe).

When NOT to use

• Downloading media from URLs — that's yt-dlp territory (separate skill).
• Still-image editing — use the imagemagick skill.
• Lossless container-only edits where a remux suffices — still fine here, just

use -c copy to avoid re-encoding.

Common operations

All examples invoke os.shell.run. Inspect first with ffprobe; the approval gate surfaces each write. Use -c copy to remux without re-encoding when only the container changes.

Rules

1. Always write to a NEW output path; never overwrite the source.
2. Inspect with ffprobe first when unsure of codecs/duration/resolution.
3. Warn the user that long re-encodes can take a while; prefer -c copy when

only the container changes.

1. Echo the output path (and ffprobe duration if relevant) after each run.