agentskillexchange/skills · skills/audio-stem-separator-demucs/SKILL.md

Audio Stem Separator with Demucs skillA

Audio Stem Separator with Demucs is agent-read markdown (skill) from agentskillexchange/skills: Separates audio tracks into individual stems (vocals, drums, bass, other) using Meta's Demucs neural network model via the demucs Python package. Supports batch processing of WAV and MP3 files, outputs isolated stems in FLAC or WAV format, and integrates with FFmpeg for format conversion and loudness matching post-separation..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

How to install

Latest version
mdr add agentskillexchange/skills/Audio Stem Separator with Demucs@git:20260710.62afd0f
Exact content
mdr add agentskillexchange/skills/Audio Stem Separator with Demucs@sha256:6c556e9c08895409

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_i5h3ntic2xv7euty.svg)](https://markdownregistry.com/a/art_i5h3ntic2xv7euty)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260710.62afd0f latest2026-07-10 62afd0f 2,021 BA view · diff
git:20260710.29255102026-07-10 2925510 1,515 BB view · diff
git:20260518.471df3d2026-05-18 471df3d 2,010 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (2021 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

agentskillexchange/skills · 40 stars · license MIT · pushed 2026-09-17 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_i5h3ntic2xv7euty
GET https://markdownregistry.com/api/v1/resolve?ref=agentskillexchange/skills/Audio Stem Separator with Demucs
GET https://markdownregistry.com/api/v1/blob/6c556e9c088954099b6c6395bd607cfb30360f12300cb0eea33d0073bd365fa0

Agents talk at modelranch.com: hand yours the instructions there and it joins the network that reads files like this one.