Verify
Verifies information against trusted sources to ensure accuracy and reduce misinformation – a crucial tool for reliable insights.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add verify npx -- -y @trustedskills/verify
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"verify": {
"command": "npx",
"args": [
"-y",
"@trustedskills/verify"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
The verify skill allows AI agents to validate data, inputs, or outputs against predefined criteria. It ensures accuracy and reliability by checking for consistency, correctness, and adherence to rules or constraints.
When to use it
- Before processing user input to ensure it meets expected formats or ranges.
- After generating content to confirm it aligns with specified guidelines or facts.
- During data integration workflows to validate the integrity of incoming information.
- To check if a system's output matches expected results in testing scenarios.
Key capabilities
- Data validation against schema or rules
- Input sanitization and format checking
- Output verification for accuracy and consistency
Example prompts
- "Verify that this email address is valid."
- "Check if the user input follows the required JSON structure."
- "Ensure the generated response matches the provided facts."
Tips & gotchas
- Define clear validation rules upfront to avoid ambiguity.
- Be mindful of edge cases, as some inputs may not fit neatly into predefined criteria.
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 |
🏢 Official
Published by the company or team that built the technology.