Audio Compare — Development skill for Claude Code
Advisory before/after audio judgment — measure → compare → judge two renders and weigh in on a DSP change with cited evidence (agent-facing, not a gate).
How to install Audio Compare
Installs to ~/.claude/commands/generous-corp-pulp-audio-compare.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/Generous-Corp/pulp/HEAD/.claude/commands/audio-compare.md -o ~/.claude/commands/generous-corp-pulp-audio-compare.md Restart Claude Code, or start a new session, for it to be picked up.
What Audio Compare does
name: audio-compare description: Advisory before/after audio judgment — measure → compare → judge two renders and weigh in on a DSP change with cited evidence (agent-facing, not a gate)
Use this when you (an agent) need to **weigh in on a DSP change**: render/capture the audio before and after, then get a defended judgment — "did this make it worse?" — with cited evidence, not a bare pass/fail. It wraps the **Audio Quality Lab**'s `compare` surface (`tools/audio/quality-lab/`, opt-in Py
Alternatives in Development
- Release Notes — Generate user-facing release notes from tickets or changelogs 7.8k ★
- Portaljs Add Chart — Add a chart (line, bar, area, pie, or scatter) to a dataset's showcase in a PortalJS portal 2.3k ★
- Asd Ste100 Skill — ASD-STE100 Simplified Technical English rules, repurposed as a Claude Code skill for rewriting ambiguous agent 1.5k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Jt Clips
Cut the business's own video into the short silent loops a page uses — measure the source, choose the moments,
Herdr Council
herdr plugin: ask every coding agent the same question, then let a judge weigh the answers blind
Setloom
Taste-first club-music production that automates everything but the judgment. You direct in plain language; th
Laya
Check laya local judge status with a live smoke judgment.
Keel Score
Measure how much Keel shaped THIS session by counting cited events; the 0-100 score is DERIVED from them by to
Calibrate Voice
Run an empirical calibration round: regenerate the 8-brief matrix, measure, collect owner ratings, codify ever
Related Agents
Baseline Auditor
Use this agent to judge whether a captured baseline is trustworthy before it gets frozen and committed for ver
Release Judge
Reviews the full evidence bundle for a release candidate (gate results, test and security summaries, triage ou
PR Judge
Independent advisory reviewer for pull requests. Writes an evidence-backed verdict to tasks/reviews/pr-N.md. U