Check
Verifies code, configurations, and documentation against established best practices and security guidelines using AI analysis.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add mthds-ai-check npx -- -y @trustedskills/mthds-ai-check
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"mthds-ai-check": {
"command": "npx",
"args": [
"-y",
"@trustedskills/mthds-ai-check"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
The check skill allows an AI agent to verify the accuracy of information or claims. It can assess statements against a knowledge base, identify potential inconsistencies, and provide confidence scores for assertions. This helps ensure that responses are reliable and grounded in factual data.
When to use it
- Fact-checking research: When synthesizing information from multiple sources, use
checkto validate the accuracy of key claims before presenting them. - Evaluating generated content: If an AI agent is creating articles or reports, utilize
checkto flag potentially inaccurate statements for review. - Confirming user inputs: Before acting on a user's request that involves critical information (e.g., financial transactions), use
checkto verify the data’s validity. - Assessing legal documents: When analyzing contracts or other legal texts, leverage
checkto identify potential errors or inconsistencies.
Key capabilities
- Accuracy verification
- Knowledge base assessment
- Inconsistency detection
- Confidence scoring
Example prompts
- "Check the statement: 'The capital of France is Berlin.'"
- "Verify this claim against my internal knowledge base: [paste text here]"
- “Assess the confidence level for the assertion: ‘Water boils at 100 degrees Celsius.’”
Tips & gotchas
The skill’s effectiveness depends on the quality and comprehensiveness of the underlying knowledge base it accesses. Ensure that this knowledge base is regularly updated to maintain accuracy.
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.