research-assessor

Extract research methodology, claims, evidence, and infrastructure from humanities and social sciences papers.

1|Updated Oct 14, 2025
One-click install
npx skills add https://github.com/saross/llm-reproducibility --skill research-assessor
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: research-assessor
Source: https://github.com/saross/llm-reproducibility/tree/main/.claude/skills/research-assessor
Command: npx skills add https://github.com/saross/llm-reproducibility --skill research-assessor

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

The Research Assessor skill enables rigorous extraction of research methodology, claims, evidence, and infrastructure from Humanities and Social Sciences papers, paired with a credibility assessment using the adapted repliCATS Seven Signals and a structured eight-pass workflow (Passes 0-7) that culminates in a machine-readable canonical assessment.

Core Features & Use Cases

  • Provides core decision frameworks for distinguishing evidence versus claims, explicit versus implicit RDMAP items, and cross-section validation across passes.
  • Delivers complete schema definitions, reference materials, and runtime prompts to support extraction prompts across Passes 1-9 and generate outputs such as extraction.json, classification.json, and assessment artifacts.
  • Produces narrative cluster reports and corpus-level metrics suitable for dashboards, governance, and reproducibility studies, while ensuring source verification through verbatim quotes and trigger passages.

Quick Start

Provide a target research paper and run the eight-pass extraction and credibility assessment workflow to generate outputs.

Frequently Asked Questions about research-assessor

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

FAQPage Schema
How do I assess the credibility of humanities research methodology?

You can assess humanities research methodology credibility by running an eight-pass extraction workflow that isolates RDMAP items, applies the repliCATS Seven Signals, and outputs a canonical assessment JSON.

What is the best way to extract implicit arguments from social sciences papers?

Extracting implicit arguments from social sciences papers is achieved through a structured multi-pass workflow that uses explicit triggers and verbatim quotes to validate claims and evidence across sections.

Can I generate machine-readable assessment reports for fieldwork and HASS papers?

Generating machine-readable assessment reports for fieldwork and HASS papers is possible by producing extraction.json, classification.json, and a full assessment package with reproducibility readiness metadata.

Does this credibility assessment workflow support cross-paper corpus analysis?

This credibility assessment workflow supports cross-paper corpus analysis by generating narrative cluster reports and corpus-level metrics suitable for reproducibility studies and dashboards.

What sources do I need to provide for humanities research credibility assessment?

To start a humanities research credibility assessment, you need to provide a target research paper, and the workflow will handle source verification through verbatim quotes and trigger passages.