feat(captions): energy-based technique selection and mandatory quality checks (#176)

## Summary

- 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, no per-frame callbacks needed
- 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
- Add multilingual model guidance and decision tree for model selection

## Test plan

- [ ] Skill files render correctly as markdown
- [ ] Cross-references between SKILL.md, dynamic-techniques.md, and transcript-guide.md resolve correctly
- [ ] `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)

skills/hyperframes-compose/SKILL.md

@@ -151,3 +151,5 @@ For audio-driven animation (beat sync, glow, pulse), see the `audio-reactive` sk
 - [ ] `window.__timelines` registered for every composition
 - [ ] 100% deterministic — no randomness
 - [ ] Each composition includes GSAP: `<script src="https://cdn.jsdelivr.net/npm/gsap@3.14.2/dist/gsap.min.js"></script>`
+- [ ] `npx hyperframes lint` passes with 0 errors
+- [ ] `npx hyperframes validate` passes with 0 errors (run both before opening the studio)