Fact Check

Verify user claims against Context7 and web sources, producing discrepancy reports.

4|Updated Oct 20, 2025
One-click install
npx skills add https://github.com/motoki317/dotfiles --skill fact-check-motoki317
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Fact Check
Source: https://github.com/motoki317/dotfiles/tree/main/.claude/skills/fact-check
Command: npx skills add https://github.com/motoki317/dotfiles --skill fact-check-motoki317

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill provides a structured approach to verify factual claims by guiding users through evidence-based checks against authoritative sources, reducing misinformation and ambiguity.

Core Features & Use Cases

  • Context7 as the primary tool for library/API claims verification.
  • WebSearch and WebFetch as fallbacks for standards, specifications, and official documentation.
  • Generates a discrepancy report with sources, confidence levels, and actionable recommendations.

Quick Start

Ask the AI to verify a claim by locating authoritative sources and summarizing the evidence.

Frequently Asked Questions about Fact Check

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

FAQPage Schema
How do I verify factual claims against trusted sources?

You can verify library and API claims by checking them against Context7 evidence, and when unavailable, use WebSearch and WebFetch for standards and official documentation to produce a discrepancy report with confidence scores.

What is the best way to check if a statement contains verifiable claims?

Checking for verifiable claims involves identifying factual statements within user inputs and matching them against authoritative sources, resulting in a discrepancy report with evidence, confidence levels, and recommended corrections.

Does fact-checking work with Context7 for API documentation verification?

Yes, Context7 is the primary source for verifying library and API claims, while WebSearch and WebFetch serve as fallbacks for checking standards, specifications, and official documentation when Context7 evidence is unavailable.

What sources can I use for claims verification when Context7 evidence is unavailable?

When Context7 evidence is unavailable for claims verification, you can use WebSearch and WebFetch to check standards, specifications, and official documentation to generate a discrepancy report with confidence scores.

How do I generate a discrepancy report with evidence and confidence scores?

You generate a discrepancy report by identifying verifiable claims in user statements, verifying them against trusted sources like Context7 or WebSearch, and producing structured evidence with confidence levels and recommended corrections.

Are there limitations when verifying claims against official documentation?

A limitation is that Context7 is limited to library and API claims, requiring fallback to WebSearch and WebFetch for other types of official documentation, standards, and specifications to complete the discrepancy report.