mcpField
C
claims-extractor

claims-extractor

github.com/willoscarProductivity51743 installsUpdated 3w ago
Repository

About claims-extractor

claims-extractor turns manuscript text into a traceable claim ledger for peer review and evidence audits. It records each claim's type, scope, and source location, distinguishing empirical from conceptual claims.

Key features

  1. 01Extract and normalize claims
  2. 02Record claim type and scope
  3. 03Attach source pointers into the manuscript
  4. 04Output Markdown and JSONL views

Use cases

  1. 01Prepare a traceable claim ledger for peer review
  2. 02Audit claims and locate their manuscript sources
  3. 03Separate empirical from conceptual claims

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/willoscar/research-units-pipeline-skills --skill claims-extractor

After installing, type/claims-extractorin Claude Code to confirm it loaded.

Bundled filesscripts/run.py

Details

From the project README

Claims Extractor

Triggers & routing

  • Trigger: claims extractor, extract claims, contributions, assumptions, peer review, 审稿, 主张提取.
  • Use when: 审稿/评审或 evidence audit，需要把主张列表落盘并可追溯到原文位置（section/page/quote）。
  • Skip if: 没有可用的稿件/全文（例如缺少 output/PAPER.md 或等价文本）。
  • Network: none.
  • Guardrail: 每条 claim 必须带可定位的 source pointer；区分 empirical vs conceptual claims。

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

Comments

Markdown supported