Extract Thread Spine

Workflow

For a published essay P:
- [ ] Step 1: Read P end-to-end
- [ ] Step 2: Identify thesis (usually opening confession + first pivot sentence)
- [ ] Step 3: Extract 5-7 load-bearing claims IN ORDER
- [ ] Step 4: Tag each claim: evidence_type (confession / claim / paper / analogy / formula / maxim), essay_section, translatability (1-5)
- [ ] Step 5: Extract closing_maxim verbatim
- [ ] Step 6: Extract 3 candidate hook sentences (from the essay itself, not paraphrases)
- [ ] Step 7: Write _spine.json

Output schema