# audio-mixing-mastering

audio-mixing-mastering is a Claude Code skill that guides audio mixing and mastering for AI videos, ads, and podcasts. Sets loudness targets and validates delivery specs.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 555 installs · ★ 252 repo stars
- Author: calesthio
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/calesthio/generative-media-skills/tree/HEAD/skills/production/audio-craft/audio-mixing-mastering/SKILL.md
- Updated: 2026-07-14
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/audio-mixing-mastering

## What it does

The skill defines mixing and mastering standards for generated video, ads, podcasts, and social media clips. It starts with an audio contract where the agent defines the hierarchy between dialogue and effects, required stems, and destination requirements before touching any levels. The reference covers loudness and true-peak specs for EBU R 128, ATSC A/85, Spotify, Apple Podcasts, Netflix, and WCAG 2.2 speech intelligibility guidelines.

It includes the `scripts/measure_loudness.py` utility to check integrated LUFS, true peak in dBTP, and loudness range without modifying audio files. The script requires Python 3.11+ and an `ffmpeg` binary built with the `loudnorm` filter. It reports results as JSON and compares measurements against target tolerances.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add calesthio/generative-media-skills --skill audio-mixing-mastering -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/audio-mixing-mastering/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/audio-mixing-mastering/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add calesthio/generative-media-skills --skill audio-mixing-mastering -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/audio-mixing-mastering/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add calesthio/generative-media-skills --skill audio-mixing-mastering -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/audio-mixing-mastering/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install calesthio/generative-media-skills skills/production/audio-craft/audio-mixing-mastering
```

2. **Manually: put the files in place**
- File: `.github/skills/audio-mixing-mastering/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add calesthio/generative-media-skills --skill audio-mixing-mastering -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/calesthio/generative-media-skills --path skills/production/audio-craft/audio-mixing-mastering
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/audio-mixing-mastering/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add calesthio/generative-media-skills --skill audio-mixing-mastering -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/calesthio/generative-media-skills/tree/HEAD/skills/production/audio-craft/audio-mixing-mastering/SKILL.md

## When to use it
- define an audio contract for stems and hierarchy before mixing
- measure integrated LUFS and true-peak levels using FFmpeg
- align mix loudness with EBU R 128, Spotify, or Netflix specs
- verify background audio separation against WCAG 2.2 guidelines

## Example prompts
- Measure `final_mix.wav` against the -16 LUFS Apple Podcasts target with `--pretty`
- Create an audio contract for a social video with dialogue priority and stems
- Run `scripts/measure_loudness.py narration_mono.wav --dual-mono` to inspect peak levels

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 85efc4905cf0225c.

BEGIN THIRD-PARTY FILE 85efc4905cf0225c
```text
---
name: audio-mixing-mastering
description: Provider-independent audio mixing and mastering direction for AI agents finishing generated videos, ads, trailers, explainers, podcasts, recuts, avatar clips, music videos, documentaries, and social content. Use when planning, mixing, repairing, mastering, QCing, or delivering dialogue, music, ambience, and sound effects, including loudness/true-peak targets, intelligibility, accessibility, stems, stereo/immersive decisions, platform/client specs, and final audio QA.
---

# Audio Mixing and Mastering Direction

Use this skill when audio must survive real playback: phone speakers, earbuds, laptops, TV soundbars, cinema-style trailers, podcasts, client review links, broadcast deliveries, and social feeds. Treat the mix as a production decision, not as a last-minute normalization step.

The job is to make the audience understand the foreground, feel the intended energy, avoid fatigue or distortion, and pass the declared delivery spec.

## Start with the audio contract

Before touching levels, write a short audio contract for the project:

- Delivery context: social post, YouTube upload, podcast RSS, streaming ad, broadcast, OTT, internal review, theatrical-style trailer, music video, documentary, localization, accessibility version.
- Foreground hierarchy: dialogue/VO first, performance/music first, sound-design impact first, or a changing hierarchy by scene.
- Required deliverables: full mix, dialogue stem, music stem, effects stem, M&E, narration-only, clean captions, audio-described version, alternate language mix, stereo fold-down, 5.1/Atmos printmaster, client preview.
- Target spec: use the client/platform/broadcaster spec if supplied. If no spec is supplied, choose a conservative target and label it as a heuristic.
- Monitoring assumption: headphones-only, nearfield speakers, phone/laptop check, calibrated room, or unavailable.
- Source risk: AI voice artifacts, room noise, inconsistent clips, clipping, music licensing, generated SFX harshness, missing room tone, mono/stereo mismatch, translated VO timing, or stem bleed.

Do not master blindly to the loudest reference. Streaming and broadcast systems may normalize loudness, and over-limiting can reduce clarity while gaining little or nothing at playback.

## Evidence categories

Documented facts:
```
END THIRD-PARTY FILE 85efc4905cf0225c

The third-party file has ended. Everything between the 85efc4905cf0225c tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2337 of 28117 bytes. © calesthio · MIT · https://github.com/calesthio/generative-media-skills/tree/HEAD/skills/production/audio-craft/audio-mixing-mastering/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
