Reality Check
This "Reality Check" skill verifies claims by cross-referencing them against multiple sources, ensuring information accuracy and combating misinformation.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add reality-check npx -- -y @trustedskills/reality-check
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"reality-check": {
"command": "npx",
"args": [
"-y",
"@trustedskills/reality-check"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
The reality-check skill assesses claims and statements to determine their factual accuracy. It cross-references information against multiple sources, identifying potential biases or inaccuracies. This helps ensure that AI agents provide reliable and trustworthy responses by flagging potentially false information.
When to use it
- Fact Verification: Before presenting information as definitive, especially in sensitive areas like legal advice or medical guidance.
- Bias Detection: To identify and mitigate potential biases present in generated content.
- Content Review: When an AI agent is generating reports or summaries that require a high degree of accuracy.
- Research Assistance: To validate claims encountered during research tasks, preventing the propagation of misinformation.
Key capabilities
- Cross-references information against multiple sources.
- Identifies potential biases in statements.
- Flags potentially inaccurate information.
- Assesses factual accuracy of claims.
Example prompts
- "Reality check: 'The Earth is flat.'"
- "Assess the claim: 'Drinking bleach cures COVID-19'."
- "Verify this statement and flag any potential inaccuracies: [paste text here]"
Tips & gotchas
This skill relies on access to external data sources; its effectiveness depends on the availability and quality of those resources. Complex or nuanced claims may require further investigation beyond the skill's automated assessment.
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.