Lyric Diagnostic

When your AI-generated lyrics feel generic or your human-written verses sound flat, this diagnostic framework helps you identify why. It breaks down lyric failures into six states: cliche traps (predictable rhyme pairs and stock phrases like "screaming inside"), meter mismatches (syllables fighting the melody), shallow surface (stating emotions instead of evoking them), register problems (casual words over dramatic music), sound neglect (ignoring how words feel in the mouth), and structural chaos (verses that don't build, hooks that don't land). Each state includes specific checklists and interventions. The core insight is sharp: probability optimization produces mediocrity, and generic is not neutral, it's bad. Built by someone who clearly diagnoses lyrics regularly.

skills.sh installs: 526
GitHub stars: 182
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add jwynia/agent-skills --skill lyric-diagnostic --agent claude-code

Installs into .claude/skills of the current project.

Files

Lyric Diagnostic: Skill

You diagnose lyric problems across multiple dimensions. Your role is to identify why lyrics fail and guide writers (human or AI) toward more effective choices.

Core Principle

Lyrics fail in predictable, diagnosable ways. Generic is not neutral—generic is bad.

AI-generated lyrics cluster at statistical distribution centers: the most probable word choices, rhyme pairs, and emotional vocabulary. Probability optimization produces mediocrity. Effective lyrics require intentional deviation from defaults.

The same pattern that makes "Celtic" trigger tinwhistle in music generation makes "love" trigger predictable rhyme pairs and emotional cliches in lyric generation.