audio-production

90 / 100 · Low risk

Fine to try. Some of what it can do is expected: a media skill usually calls an AI service over the internet.

By mphinance/alpha-skills (GitHub) · media · 32 stars · scanned at commit 78b6ee6

Transcribe, surgically edit, master, and clean audio recordings (trading streams, community calls, podcasts, meetings) with automated silence/fluff trimming, noise reduction, loudness normalization (-16 LUFS), and transcription via OpenRouter mai-transcribe-2 or local faster-whisper. Always consolidate output into a single dedicated folder.

Works with any agent that supports SKILL.md skills.

What this skill can do

Can call paid AI services billed to you

This is disclosed by the author in the skill's SKILL.md or README. Expected for a media skill.

Found in 2 places.

skills/audio-production/SKILL.md, line 25- **Endpoint:** `https://openrouter.ai/api/v1/audio/transcriptions`
skills/audio-production/scripts/audio_pipeline.py, line 17OPENROUTER_STT_URL = "https://openrouter.ai/api/v1/audio/transcriptions"

Runs commands on your computer

The author does not mention this.

Found in 6 places.

skills/audio-production/SKILL.md, line 91python3 audio_pipeline.py -i recording.m4a \
skills/audio-production/SKILL.md, line 106ffmpeg -i input.mp3 \
skills/audio-production/scripts/audio_pipeline.py, line 46res = subprocess.run(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)

Show 3 more

skills/audio-production/scripts/audio_pipeline.py, line 75res = subprocess.run(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
skills/audio-production/scripts/audio_pipeline.py, line 122res = subprocess.run(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
skills/audio-production/scripts/audio_pipeline.py, line 215res = subprocess.run(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'audio-production' ] || [ -L ~/.agents/skills/'audio-production' ]; then echo 'A skill folder named audio-production already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/mphinance/alpha-skills' "$d" && git -C "$d" checkout --quiet '78b6ee6816aca6e5660cc7f0382650e9e7687086' -- 'skills/audio-production' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/audio-production' ~/.agents/skills/'audio-production' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'audio-production' ~/.claude/skills/'audio-production' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for mphinance/alpha-skills shows the score of its lowest-scoring skill.

SkillTrust badge for mphinance/alpha-skills

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/mphinance/alpha-skills.svg)](https://zalavijaysinh.github.io/skilltrust/repos/mphinance/alpha-skills/)

Score history

Date	Version	Score
2026-11-10	`78b6ee6`	90