review-content

Evaluate topic content across nine argumentative quality and impartiality dimensions.

Updated Mar 15, 2026

Search Tags:#fact-checking #content quality #editorial review #topic analysis #argumentative integrity

Ready to run

npx skills add https://github.com/mdeutschel/facts --skill review-content-mdeutschel

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: review-content
Source: https://github.com/mdeutschel/facts/tree/main/.claude/skills/review-content
Command: npx skills add https://github.com/mdeutschel/facts --skill review-content-mdeutschel

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python, pandas, numpy, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill helps maintain high standards of argumentative quality and impartiality in the creation and review of topic content.

Core Features & Use Cases

Quality Assessment: Evaluates content against nine dimensions for accuracy, fairness, and intellectual integrity.
Review Modes: Supports both 'Review-Mode' for detailed analysis and 'Author-Mode' for proactive guidance.
Automated Correction: Identifies and suggests fixes for problematic content.

Quick Start

Run the review-content skill on the 'public/data/argument-content.json' to analyze and improve argumentative quality.

Frequently Asked Questions about review-content

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

FAQPage Schema

How do I assess argumentative quality and impartiality in topic content?▼

To assess argumentative quality and impartiality, evaluate content against nine dimensions including nuance, source reliability, assumption transparency, fact vs. interpretation, counterarguments, linguistic precision, claim-response fit, conversational utility, and political neutrality using Python scripts.

What is the best way to automate fact-checking and editorial review for argumentative content?▼

Automating editorial review involves running Python scripts on JSON argument content to identify problematic claims and enforce linguistic precision. The system supports a Review-Mode for detailed analysis and an Author-Mode for proactive guidance during content creation.

How do I run an automated editorial review on my content dataset?▼

You can run an editorial review by executing the review skill on your argument content JSON file. The Python scripts analyze the data to detect assumption transparency issues, counterarguments, and political neutrality violations, then suggest automated corrections.

Do I need Python and pandas to perform automated topic analysis and fact-checking?▼

Yes, Python, pandas, and numpy are required dependencies to run the scripts for automated topic analysis and fact-checking. These libraries process the argument content data to evaluate the nine dimensions of argumentative quality.

What dimensions are checked when evaluating political neutrality and claim-response fit?▼

Evaluating political neutrality and claim-response fit involves checking nine dimensions: nuance, source reliability, assumption transparency, fact vs. interpretation, counterarguments, linguistic precision, claim-response fit, conversational utility, and political neutrality. The scripts analyze these to ensure impartiality.

Can I use this approach for proactive guidance during content creation instead of just post-review?▼

Yes, you can use Author-Mode for proactive guidance during content creation rather than just post-review. This mode helps enforce argumentative quality and impartiality dynamically, while Review-Mode provides detailed post-creation analysis and correction suggestions.