claims-extractor
将论文/手稿中的关键主张、贡献和假设提取到“output/CLAIMS.md”中,并可追溯至源位置。**触发器**:主张提取器、提取主张、贡献、假设、同行评审、审稿、协商。提取**使用时**:审稿/评审或证据审计,需要把辩护列表落盘并可继续原位置(节/页/引用)。**如果**:没有可用的稿件/全文(缺少例如),则跳过`output/PAPER.md` 或等价文本)。**网络**:无。**护栏**:每条声明必须可定位的源指针;区分经验声明与概念声明。
📖 中文导读:将论文/手稿中的关键主张、贡献和假设提取到“output/CLAIMS.md”中,并可追溯至源位置。**触发器**:主张提取器、提取主张、贡献、假设、同行评审、审稿、协商。提取**使用时**:审稿/评审或证据审计,需要把辩护列表落盘并可继续原位置(节/页/引用)。**如果**:没有可用的稿件/全文(缺少例如),则跳过`output/PAPER.md` 或等价文本)。**网络**:无。**护栏**:每条声明必须可定位的源指针;区分经验声明与概念声明。 以下正文为该技能的原始 SKILL.md 内容(英文),上方安装命令可直接使用。
name: claims-extractor
description: |
Extract key claims, contributions, and assumptions from a paper/manuscript into output/CLAIMS.md with traceability to source locations.
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。
Claims Extractor (peer review)
Goal: turn a manuscript into an auditable list of claims that downstream skills can check.
Inputs
Required:
output/PAPER.md(or equivalent plain-text manuscript)
Optional:
DECISIONS.md(review scope or constraints)
Outputs
output/CLAIMS.md
Output format (recommended)
For each claim, include at minimum:
Claim: one sentenceType:empirical|conceptualScope: what the claim applies to / what it does not apply toSource: a locatable pointer intooutput/PAPER.md(section + page/figure/table + a short quote)
Workflow
- If
DECISIONS.mdexists, apply any review scope/format constraints. - Read the manuscript (
output/PAPER.md) end-to-end (at least abstract + intro + method + experiments + limitations). - Extract:
- primary contributions (what is new)
- key claims (what is asserted)
- assumptions (what must be true for claims to hold)
- Normalize each item into one sentence.
- Attach a source pointer for every item.
- Split into two sections:
- Empirical claims (must be backed by experiments/data)
- Conceptual claims (must be backed by argument/definition)
Definition of Done
-
output/CLAIMS.mdexists. - Every claim has a source pointer that can be located in
output/PAPER.md. - Empirical vs conceptual claims are clearly separated.
Troubleshooting
Issue: the paper is only a PDF or HTML
Fix:
- Convert/extract it into a plain-text
output/PAPER.mdfirst (even rough extraction is OK), then run claim extraction.
Issue: claims are vague (“significant”, “better”, “state-of-the-art”)
Fix:
- Rewrite each claim to include the measurable dimension (metric/dataset/baseline) or mark it as “underspecified” with a note.