agentleFS
godot-fungodot-fun/gai/.agents/skills/video-to-wav/SKILL.md

video-to-wav

Skill210 starsChanged 2 days agoMITView on GitHub

Extracts audio tracks from a single video file to PCM WAV using FFmpeg while preserving source quality. Use when the user wants to extract audio from video, rip sound from MP4/MKV/MOV/WebM, or export video audio to WAV without quality loss.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    When this skill applies, read and follow dependency-manager — run scripts as documented, install missing tools into .dependency/.

    line 12
  2. Very specific:

    Use the bundled script, not hand-written ffmpeg -i … commands.

    line 54

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Video to WAV

Extract the first audio track from a supported video file to PCM WAV via FFmpeg. Defaults preserve source quality — no resampling, bit depth matched from the embedded audio (32-bit float for lossy codecs), channels preserved, video stream discarded (-vn).

Rules

When this skill applies, read and follow dependency-manager — run scripts as documented, install missing tools into .dependency/.

Quick Start

Default output: <video-dir>/video-to-wav/<basename>.wav

.dependency/python/python .ai/video-to-wav/convert.py --video path/to/video.mp4

Example: assets/clip.mp4 → assets/video-to-wav/clip.wav (same rate/depth as embedded audio)

Format Defaults

SettingDefaultNotes
Audio trackFirst (a:0)Use --track N for alternate tracks (0-based)
Sample ratePreserve sourceAlways kept; use audio-sample-rate-standardize to resample
Bit depthMatch sourceProbed per file; lossy → 32-bit float PCM
ChannelsPreserve sourceAlways kept from embedded audio
Lossless PCM in containerStream copyBit-perfect when no overrides

Common Flags

--video · -o / --output · --track · -b / --bit-depth

Alternate audio track:

.dependency/python/python .ai/video-to-wav/convert.py --video clip.mkv --track 1

Custom output path:

.dependency/python/python .ai/video-to-wav/convert.py --video clip.mp4 --output path/to/out.wav

Never overwrite source files. The script writes only under video-to-wav/ (or --output). Input must be a single video file (--video), not a directory. Supported inputs: .mp4, .mkv, .mov, .avi, .webm, .wmv, .flv, .m4v, .mpeg, .mpg, .ts, .mts, .m2ts, .3gp.

Agent Notes

  1. Use the bundled script, not hand-written ffmpeg -i … commands.
  2. Sample rate is always preserved — chain audio-sample-rate-standardize if resampling is needed.
  3. Do not reduce bit depth unless the user explicitly asks — omit -b.
  4. No audio track — script reports failure; confirm the file has an audio stream.
  5. Missing Python/FFmpeg → populate .dependency/ per dependency-manager, retry same command.
  6. Do not copy, move, or replace the source with extracted output — tell the user where output files are; they swap assets manually when ready.
  7. This skill is for video containers only; standalone audio files are out of scope.
  8. FFmpeg codec and probing details: reference.md

Tests

From repo root:

.dependency/python/python .ai/video-to-wav/test_convert.py

Manual CLI examples: cli/video-to-wav.md

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.