Fact Check
Verifies claims by cross-referencing sources, ensuring accuracy and combating misinformation for reliable information.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add jwynia-fact-check npx -- -y @trustedskills/jwynia-fact-check
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"jwynia-fact-check": {
"command": "npx",
"args": [
"-y",
"@trustedskills/jwynia-fact-check"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
This skill systematically verifies claims within generated content to combat hallucinations and ensure accuracy. It operates by performing a separate verification pass, distinct from the initial generation process, focusing solely on checking each claim against external sources. The goal is to identify unsupported assertions and provide reliable information by avoiding self-verification or reliance on internal memory.
When to use it
- When generating content that requires high accuracy and factual correctness (e.g., reports, articles).
- To mitigate the risk of hallucinations and confabulations in AI-generated text.
- After initial content generation, before delivery or publication, as a final quality check.
Key capabilities
- Claim Extraction: Identifies verifiable statements including factual assertions, statistics, attributions, definitions, historical claims, causal claims, and comparative claims.
- Separate Verification Pass: Performs verification independently of the content generation process.
- External Source Checking: Relies on external sources for validation rather than internal memory or training data.
- Claim Categorization: Classifies extracted claims to determine appropriate verification methods.
- Diagnostic States: Identifies and addresses common errors in verification processes (e.g., self-verification, memory-based verification).
Example prompts
- "Please fact-check the following text: [insert generated content here]"
- "Verify all claims within this document and provide source citations."
- "Run a separate verification pass on the generated report before delivery."
Tips & gotchas
- The skill requires a complete generation phase before running the verification pass. Asking it to "check your facts" during content creation will be ineffective.
- Ensure all verifiable claims are systematically extracted; selectively verifying only some claims can leave errors undetected.
- Explicit source citations are crucial for reliable verification – if a claim cannot be verified with an external source, it should be marked as unverified.
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🌐 Community
Passed automated security scans.