Derive Section Voice Overlay

Workflow

When a section reaches ≥3 posts:
- [ ] Step 1: Read all posts in corpus/published/{section}/
- [ ] Step 2: Read global shared-context/voice-profile.md
- [ ] Step 3: Extract patterns present in this section's posts but different from global:
    - Tone shifts (confessional vs technical; register)
    - Structural shifts (scoreboard required; code fences allowed; H2 permitted)
    - Vocabulary shifts (term-of-art allowed; jargon defined on first use)
    - Register permissions (epistolary, second-person, etc.)
- [ ] Step 4: Draft the overlay as a delta (bullet list per category; NOT a full voice profile)
- [ ] Step 5: Write shared-context/voices/{slug}.md for writer review
- [ ] Step 6: Emit draft status: "awaits writer commit" in the Curator review artifact

Overlay schema