---
name: Claims Extractor
slug: claims-extractor
category: Quality
description: Claims Extractor turns manuscript text into a traceable claim ledger for review work. It records each claim with a source pointer and separates empirical from conceptual claims.
github: "https://github.com/WILLOSCAR/research-units-pipeline-skills/tree/main/.codex/skills/claims-extractor"
language: Python
stars: 499
forks: 39
install: "npx degit https://github.com/WILLOSCAR/research-units-pipeline-skills/tree/main/.codex/skills/claims-extractor ~/.claude/skills/claims-extractor"
installs_to: ~/.claude/skills/claims-extractor
source_path: .codex/skills/claims-extractor/SKILL.md
collection_size: 25
category_size: 1354
collection_url: "https://dirskills.com/collections/WILLOSCAR/research-units-pipeline-skills"
added: 2026-08-26T05:12:54.617Z
last_synced: 2026-08-26T05:12:54.617Z
canonical_url: "https://dirskills.com/skills/claims-extractor"
---

# Claims Extractor

Claims Extractor turns manuscript text into a traceable claim ledger for review work. It records each claim with a source pointer and separates empirical from conceptual claims.

**Install:**

```bash
npx degit https://github.com/WILLOSCAR/research-units-pipeline-skills/tree/main/.codex/skills/claims-extractor ~/.claude/skills/claims-extractor
```

## README

# Claims Extractor

Transforms manuscript text into a traceable claim ledger for `paper-review`.

## Input

- `output/PAPER.md`

## Output

- `output/CLAIMS.md`
- `output/CLAIMS.jsonl` (`review-claim.v1`, one addressable claim per line)

## Contract

Each claim block must include:
- claim text
- type: `empirical` or `conceptual`
- scope
- source pointer back into `output/PAPER.md`

The Markdown and JSONL files are two views of the same claim records. Downstream
skills should prefer JSONL and retain Markdown fallback for older Workspaces.

## Script boundary

`scripts/run.py` should:
- detect claim-like sentences
- normalize them into stable claim blocks
- attach source pointers
- separate empirical and conceptual claims

Keep parsing and ranking heuristics in shared review tooling, not in the skill script.

## Acceptance

- `output/CLAIMS.md` exists
- `output/CLAIMS.jsonl` exists and every record has a stable `claim_id`
- every claim has a source pointer
- empirical and conceptual claims are separated

## Non-goals

- judging whether a claim is good
- generating evidence gaps
- writing review prose