From thinking-frameworks-skills
Extracts atomic technical claims from substacker essay drafts by segmenting, flagging technical sentences, and coalescing. Helps Technical Reviewers prepare for fact-check per draft.
How this skill is triggered — by the user, by Claude, or both
Slash command
/thinking-frameworks-skills:claim-extractorThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
```
Per draft:
- [ ] Step 1: Segment draft by heading / section
- [ ] Step 2: Within each section, split by sentence
- [ ] Step 3: Flag sentences containing technical claims:
- Math symbols / formulas
- Named systems, components, algorithms
- Quantitative assertions
- Universal quantifiers ("always", "never", "all models")
- Named papers / results
- [ ] Step 4: Coalesce adjacent claim sentences that argue the same thing into one claim
- [ ] Step 5: Output numbered list: {id, excerpt (≤200 chars), location}
Draft paragraph:
Attention is O(n²). This is why context windows are expensive. Each token looks at every other token, and the matrix is n-by-n.
Extraction:
[contrarian] annotations — still extract the claim, but flag it for classify-claim to treat specially.npx claudepluginhub lyndonkl/claude --plugin thinking-frameworks-skillsExtracts propositional claims from research paper notes.md into claims.yaml using propstore schema. Supports parameter and equation claims; uses concepts.yaml for canonical concept names.
Extracts atomic claims from citations in academic papers or PDFs, groups by sub-topic, summarizes groups for literature reviews and note-taking.
Produces grounded, citation-backed responses from source documents via direct quotes, uncertainty permission, and claim verification. Use for analyzing codebases, specs, or long documents.