Audio Quality Check

Diagnoses echo, loudness, SNR, and speech intelligibility in call recordings with real DSP metrics.

Tested · Works

Test report

Verdict
Tested · Works
Score
9.6/10
Tested
Jul 14, 2026
Environment
Claude Code 2.x (agent harness)
Upstream re-checked
Aug 10, 2026 · a85ee2a

⚠ The author changed this skill after we tested it. The verdict below describes the version we ran on Jul 14, 2026; it's queued for a re-test.

Ran the bundled analyzer for real on a synthetic dual-track M4A with a 53ms echo injected into the system track: it correctly isolated the echo there (r=0.93 at ~32ms) and reported near-zero cross-track correlation (0.005-0.01), correctly ruling out mic bleed - though it also flagged the clean mic track due to pitch-harmonic aliasing in the synthetic test tone, a false-positive mode the SKILL.md itself discloses (peaks below 0.15 are harmless pitch harmonics; ours were an edge case from an unnaturally pure tone).

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

  • Installs cleanly 5/5
  • Triggers reliably 5/5
  • Output vs. baseline 9/10
  • Docs & honesty 5/5

What Audio Quality Check does

Runs a bundled Python script (ffmpeg + numpy/scipy/pyloudnorm/pesq/pystoi/librosa) against dual-track call recordings to measure EBU R128 loudness, autocorrelation-based echo/duplication, cross-track bleed, PESQ/STOI speech quality, and SNR, with documented thresholds for each metric. Triggers when a user wants to check why a recording sounds bad, detect echo/duplication, or compare original vs AEC-processed audio, including Blackbox call recordings.

How to install Audio Quality Check

git clone https://github.com/tenequm/skills
cd skills
mkdir -p ~/.claude/skills
cp -r skills/audio-quality-check ~/.claude/skills/audio-quality-check

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Audio Quality Check

  • /audio-quality-check Diagnoses echo, loudness, SNR, and speech intelligibility in call recordings with real DSP metrics.

It also activates on plain-language prompts like these:

  • Why does this call recording sound so echoey and muffled?
  • Check this dual-track recording for echo, loudness, and SNR issues
  • Compare our original and AEC-processed audio to see what improved

Frequently asked questions

Is the Audio Quality Check skill free?
Yes. The skill itself is free from tenequm/skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does Audio Quality Check work with Claude Code?
We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Tested · Works. Ran the bundled analyzer for real on a synthetic dual-track M4A with a 53ms echo injected into the system track: it correctly isolated the echo there (r=0.93 at ~32ms) and reported near-zero cross-track correlation (0.005-0.01), correctly ruling out mic bleed - though it also flagged the clean mic track due to pitch-harmonic aliasing in the synthetic test tone, a false-positive mode the SKILL.md itself discloses (peaks below 0.15 are harmless pitch harmonics; ours were an edge case from an unnaturally pure tone).
What is the Audio Quality Check SkillProof Score?
9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.
How do I install Audio Quality Check?
Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Audio Quality Check with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.