claim-evidence-bridge

Map claims to experimental evidence and flag unsupported results in markdown.

Updated Mar 27, 2026
One-click install
npx skills add https://github.com/EmaRimoldi/Claude-scholar-extended --skill claim-evidence-bridge
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: claim-evidence-bridge
Source: https://github.com/EmaRimoldi/Claude-scholar-extended/tree/main/skills/claim-evidence-bridge
Command: npx skills add https://github.com/EmaRimoldi/Claude-scholar-extended --skill claim-evidence-bridge

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

claim-evidence-bridge helps researchers ensure every claim in a paper is explicitly mapped to its experimental evidence and flags unsupported or over-claimed conclusions, improving transparency and writing quality.

Core Features & Use Cases

  • Claim Extraction: Identify primary, secondary, and implicit claims.
  • Evidence Mapping: Link each claim to supporting data, assess evidence strength, note confounds, and suggest language.
  • Scope & Output: Decide which claims to include or hedge, generate claim-evidence-map.md, and bind to ml-paper-writing.
  • Workflow Modes: Mode A pipeline using results-analysis, or Mode B standalone with user-provided claims and evidence descriptions.

Quick Start

Provide your planned claims and evidence, then run the skill to generate a claim-evidence-map.

Frequently Asked Questions about claim-evidence-bridge

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I map claims to experimental evidence in a research paper?

To map claims to experimental evidence, you provide your planned claims and supporting data, and the skill generates a structured claim-evidence-map.md file linking each claim to its results.

What is a claim-evidence map and how does it improve paper writing?

A claim-evidence map links primary, secondary, and implicit claims to supporting data, assesses evidence strength, and flags unsupported or over-claimed results to improve research transparency and scope.

How do I identify and flag over-claimed results in my manuscript?

You can flag over-claimed results by running the skill with your claims and evidence descriptions; it evaluates evidence strength, notes confounds, and suggests hedged language for unsupported conclusions.

Do I need a results-analysis bundle to check my paper's claims?

You do not need a results-analysis bundle; the skill supports a standalone Mode B where you can directly input user-provided claims and evidence descriptions to generate the map.

Can I export a markdown checklist to guide ml-paper-writing scope decisions?

You can export a markdown map file that decides which claims to include or hedge, serving as a writing checklist that binds directly to ml-paper-writing workflows for scope refinement.