## Summary
**Whisper improvements:**
- Auto-detect language and switch from `.en` to multilingual model when needed
- Detect speech onset in WAV to strip hallucinated words before speech begins
- Merge whisper-cpp token fragments: contractions (`didn` + `'t` → `didn't`), split capitals (`C` + `aught` → `Caught`), dropped-g (`shin` + `in'` → `shinin'`)
- Interpolate zero-duration word clusters for reliable karaoke timing
**Captions skill updates (folded from #176):**
- Rewrite script-to-style mapping as an energy detection table (high → low) with mandatory animation requirements: karaoke baseline, 2+ highlight techniques, kinetic exits
- Replace `tl.call()` per-frame audio-reactive pattern with group-level GSAP tweens — read peak bass/treble for each group's time range and modulate entrance intensity at build time
- Add transcript quality check with automatic retry rules (>20% music tokens = retry with larger model)
- Add caption word structure lint rule (`.caption-group` + `<span>`) for studio editor compatibility
**Multilingual defaults (folded from #186):**
- Default whisper model changed from `small.en` to `small` to prevent silent translation of non-English audio
- Added non-negotiable language rule to captions skill
## Test plan
- [ ] `pnpm test` passes (contraction merging, fragment merging, zero-duration interpolation, speech onset)
- [ ] Transcribe non-English audio — verify it transcribes in original language, not translates
- [ ] Skill files render correctly, cross-references resolve
- [ ] `dynamic-techniques.md` audio-reactive section uses `tl.to()`/`tl.set()` only, no `tl.call()` loops
🤖 Generated with [Claude Code](https://claude.com/claude-code)
## Summary
- Split the captions skill from a single 611-line file into focused references: `SKILL.md` (core rules), `transcript-guide.md` (whisper/transcription), `dynamic-techniques.md` (animation patterns)
- Add `audio-reactive` skill with "Content, Not Medium" constraint — steers away from generic visualizations (equalizer bars, spectrum analyzers, waveforms) toward content-grounded animation where audio drives *when* and *how much*, not *what to show*
- Add initial dynamic caption technique selection by energy level
## Test plan
- [ ] All skill files render correctly as markdown
- [ ] Cross-references between files use correct relative paths
- [ ] `audio-reactive/SKILL.md` contains the anti-pattern list and content-grounded examples
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Vance Ingalls