mastering-prep — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited mastering-prep (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Pre-master audit. Confirm the mix is in a clean state for either external mastering or self-mastering. Does NOT apply final mastering — that's a separate workflow with explicit user intent.
get_track_info for masterget_device_parameters for any plugins on masterFor each item, mark ✅ pass or ❌ fail with the specific reading:
| Check | Target | What to look for |
|---|---|---|
| Peak level | -3 to -6 dB | Master should have headroom — never above -1 dB |
| No master limiter active for export-to-mastering | Off | Mastering engineer wants raw mix; remove limiter from master |
| No master compressor over 2 dB GR | <2 dB | Heavy mastering compression on a pre-master is destructive |
| LUFS integrated | -16 to -20 LUFS for pre-master | Too loud = no headroom for mastering |
| Mono compatibility | All elements audible in mono | Toggle Utility's mono switch — verify nothing disappears |
| Phase coherence | Above 0.0 (positive) | Use Spectrum or Stereo & Phase — dips below 0 = destructive cancellation |
| Frequency balance | No spikes >6 dB above neighbors | Bass vs mids vs highs evenly spread |
| Sub-bass below 40 Hz | Cut or controlled | Anything below 30 Hz wastes headroom and clouds masters |
| Above 18 kHz | Cut if no musical content | Tames hiss/artifacts; saves headroom |
| DC offset | None | Use Utility's DC filter on the master |
| Track-level clipping | None | Inspect each track's meter — yellow is fine, red is not |
| Inactive devices | Bypass or remove | Unused devices on tracks waste CPU and confuse archiving |
Print the audit table with results. Lead with failures, then warnings, then passes.
"Audit results: ❌ Master peaking at -0.8 dB — needs at least 3 dB more headroom ❌ Vocals on track 3 mono-incompatible — disappears 30% in mono fold ⚠️ LUFS integrated -10.2 — too loud for pre-master, drop master fader 4 dB ✅ Phase coherence 0.7 — good ✅ No DC offset ✅ Sub-bass clean below 30 Hz"*
For each failure, propose a specific fix. Apply only on user confirmation:
If user is exporting now, also confirm:
track-name-95bpm-Cm-v3.wav)~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.