fact-check

Name: fact-check
Availability: InStock
Author: Digication

Identify verifiable claims in conversations and verify them against sources.

Updated Mar 24, 2026

Search Tags:#automation #verification #audit #evidence #code #claims #fact-check

Ready to run

npx skills add https://github.com/Digication/claude-blueprint --skill fact-check-digication

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: fact-check
Source: https://github.com/Digication/claude-blueprint/tree/main/.claude/skills/fact-check
Command: npx skills add https://github.com/Digication/claude-blueprint --skill fact-check-digication

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Verifying factual accuracy in conversations by automatically identifying verifiable claims and validating them against code, documentation, and external sources to reduce misstatements and misinterpretations.

Core Features & Use Cases

Two-stage verification: triage verifiable claims and perform fresh-context validation against sources.
Evidence-based verdicts: label claims as Supported, Contradicted, or Unverifiable with explicit sources.
Audit-ready: generate a concise report of findings for reviews and compliance.

Quick Start

Provide a verifiable claim from the current conversation to verify using the /fact-check command.

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 made in a conversation against a codebase?▼

You can verify conversational claims by identifying verifiable statements and validating them against code or documentation. The workflow triages claims, uses fresh-context sub-agents for validation, and generates a report labeling findings as Supported, Contradicted, or Unverifiable.

What is the best way to audit code and documentation for evidence-driven verification?▼

Evidence-driven verification audits code by extracting verifiable claims through triage, then using fresh-context sub-agents to validate them against sources. It generates an audit-ready report with concrete evidence citations for compliance reviews.

Does automated claim verification work with external sources and knowledge bases?▼

Yes, automated claim verification works with external sources and knowledge bases by using fresh-context sub-agents to validate extracted claims. It checks conversational statements against code, documentation, and external sources, providing evidence-based verdicts.

How does two-stage claim verification handle unverifiable statements?▼

Two-stage claim verification handles unverifiable statements by assigning them a fixed Unverifiable category in the final report. After triage and fresh-context validation, claims lacking concrete evidence are explicitly labeled Unverifiable alongside Supported or Contradicted findings.

Can I generate a compliance report for contradicted claims in a codebase?▼

Yes, you can generate a compliance report for contradicted claims by running the verification workflow on your codebase. The audit-ready report summarizes findings, labeling contradicted claims with concrete evidence and source citations for review.

When should I use automated fact-checking for conversation verification?▼

Use automated fact-checking for conversation verification when you need to reduce misstatements in chats, codebases, or knowledge bases. It provides evidence-based verdicts with concrete source citations, making it suitable for audit-ready compliance reviews.