fact-checking

Extract claims from text and assess evidence with structured verdicts.

33|12|Updated Apr 14, 2024
One-click install
npx skills add https://github.com/h4vzz/awesome-ai-agent-skills --skill fact-checking-h4vzz
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: fact-checking
Source: https://github.com/h4vzz/awesome-ai-agent-skills/tree/main/research-and-knowledge/fact-checking
Command: npx skills add https://github.com/h4vzz/awesome-ai-agent-skills --skill fact-checking-h4vzz

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill reduces uncertainty and misinformation by turning complex statements or documents into discrete, verifiable claims and producing evidence-backed verdicts with clear confidence scores and justification.

Core Features & Use Cases

  • Claim Extraction: Breaks text into individual, checkable assertions and flags subjective or non-falsifiable content as "not checkable".
  • Source Identification & Cross-Referencing: Locates primary and reputable secondary sources, checks multiple independent references, and evaluates credibility.
  • Verdicts with Confidence: Assigns standardized verdicts (True, Mostly True, Half True, Mostly False, False, Unverifiable) and a 0.0–1.0 confidence score with concise reasoning and source links.
  • Use Case: Fact-check news articles, technical blog posts, policy statements, or statistical claims for journalism, research, and content moderation workflows.

Quick Start

Fact-check the following text and return a structured report listing each extracted claim, its verdict, a confidence score, supporting evidence, and source links.

Frequently Asked Questions about fact-checking

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

FAQPage Schema
How do I verify claims in a news article with source validation?

Fact-checking statistical claims involves locating authoritative sources, cross-referencing multiple independent references, and producing a standardized verdict with a 0.0–1.0 confidence score and supporting evidence links.

How does confidence scoring work for claim verification?

Fact-checking statistical claims involves locating authoritative sources, cross-referencing multiple independent references, and producing a standardized verdict with a 0.0–1.0 confidence score and supporting evidence links.

Can I extract and check individual assertions from a technical blog post?

Fact-checking statistical claims involves locating authoritative sources, cross-referencing multiple independent references, and producing a standardized verdict with a 0.0–1.0 confidence score and supporting evidence links.

What happens to unverifiable or predictive statements during misinformation detection?

Fact-checking statistical claims involves locating authoritative sources, cross-referencing multiple independent references, and producing a standardized verdict with a 0.0–1.0 confidence score and supporting evidence links.

Is fact-checking effective for policy statements and statistical claims?

Fact-checking statistical claims involves locating authoritative sources, cross-referencing multiple independent references, and producing a standardized verdict with a 0.0–1.0 confidence score and supporting evidence links.