contradiction_detect

Pair claims from distinct sources to detect and characterize cross-source contradictions.

1|Updated Mar 23, 2026

Search Tags:#analysis #evidence #contradiction #risk-assessment #claims #data-quality #cross-source

Ready to run

npx skills add https://github.com/hellonish/singularity --skill contradiction-detect

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: contradiction_detect
Source: https://github.com/hellonish/singularity/tree/main/SKILLS/tier2_analysis/contradiction_detect
Command: npx skills add https://github.com/hellonish/singularity --skill contradiction-detect

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill systematically identifies and characterizes explicit and implicit contradictions between factual claims across multiple information sources, enabling better quality control and decision support.

Core Features & Use Cases

Cross-source claim pairing and comparison to surface inconsistencies.
Typology and severity labeling (factual, methodological, interpretive) with grounding evidence.
Output structured signals for downstream resolution, prioritization, and human-in-the-loop escalation.

Quick Start

Provide a list of claims annotated with their sources to be analyzed for cross-source contradictions and receive a structured contradiction report.

Frequently Asked Questions about contradiction_detect

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

FAQPage Schema

How do I identify cross-source contradictions in literature reviews?▼

You detect cross-source contradictions by pairing claims from different sources and analyzing their propositions. The Skill outputs a structured list of disputes featuring type, severity, source_a, source_b, and supporting evidence for literature reviews and technical reports.

What is cross-source claim pairing for risk assessment?▼

Cross-source claim pairing for risk assessment compares factual claims from multiple sources to surface inconsistencies. It characterizes explicit and implicit contradictions using a typology and severity labels to enable better quality control and decision support.

Does this tool work with investigative datasets to find factual disputes?▼

Yes, this tool works with investigative datasets to find factual disputes. It applies to cross-source claim sets in investigative datasets to surface disputes, ensuring claim-pairs are limited to distinct sources for accurate contradiction detection.

How do I structure claims to detect methodological and interpretive contradictions?▼

To detect methodological and interpretive contradictions, provide a list of claims annotated with their sources. The Skill analyzes these cross-source claim sets, applies typology labels like factual, methodological, or interpretive, and outputs a structured contradiction report.

What is the best way to surface inconsistencies across technical reports?▼

The best way to surface inconsistencies across technical reports is to use cross-source claim pairing and comparison. This approach identifies explicit and implicit contradictions and outputs structured signals for downstream resolution, prioritization, and human-in-the-loop escalation.

Can I use this for data quality control in large datasets?▼

Yes, you can use this for data quality control in large datasets. It systematically characterizes contradictions across multiple information sources, outputting structured signals that support downstream resolution, prioritization, and human-in-the-loop escalation.