feat(skills): add dynamic caption techniques and split captions skill into references (#173)

## 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)

skills/hyperframes-compose/SKILL.md

@@ -140,6 +140,7 @@ Video must be `muted playsinline`. Audio is always a separate `<audio>` element:
 For PiP, title cards, and slide show patterns, see [patterns.md](./patterns.md).
 For data, stats, and infographics, see [data-in-motion.md](./data-in-motion.md).
 For typewriter text and other GSAP animation effects, see the `gsap-effects` skill.
+For audio-driven animation (beat sync, glow, pulse), see the `audio-reactive` skill.
 
 ## Output Checklist