ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified utilities Safety 5/5

verify-claim

Verify factual claims against live data sources. Returns structured verdicts with confidence scores.

Why use this skill?

Use the verify-claim skill to ensure your AI agent delivers accurate information. Validate factual claims with confidence scores and live data.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/cutthemustard/cs-verify
Or

What This Skill Does

The verify-claim skill is an essential tool for any AI agent tasked with maintaining high factual accuracy. It provides an interface to query real-time data sources to validate specific statements. Unlike general-purpose web search tools, this skill performs an structured verification, returning not just a confirmation, but a confidence score, the current truth value, and metadata about the data's freshness. By integrating this into your OpenClaw agent, you can effectively mitigate hallucinations and ensure that the information provided to end-users is based on the latest available, verified data.

Installation

To integrate this skill into your OpenClaw environment, use the command-line interface to pull the module directly from the repository. Execute the following command in your terminal:

clawhub install openclaw/skills/skills/cutthemustard/cs-verify

Ensure that you have the necessary environment permissions for network egress, as the skill communicates with the verification API at 636865636b73756d.com. For enterprise use, consider utilizing the MCP server implementation by running npm install -g @636865636b73756d/mcp-v1 to enjoy better integration with local agent workflows.

Use Cases

This skill is perfect for scenarios requiring high data integrity. Use it for financial reporting where exchange rates or cryptocurrency prices must be accurate to the second. It is also excellent for entity validation, such as checking current corporate leadership, population statistics, or geographic data. Fact-checking bots benefit significantly from the 'factcheck' category, which taps into specialized APIs to debunk or confirm viral claims.

Example Prompts

  1. "Verify the current gold price in USD and tell me if the claim 'Gold is trading above $2,300' is true."
  2. "Check if the population of Tokyo is currently estimated to be over 14 million people."
  3. "Is it true that the USD to EUR exchange rate is 0.92? Provide the confidence score."

Tips & Limitations

To optimize costs and speed, always include the 'category' parameter in your requests (e.g., 'financial', 'geo', 'entity'). This allows the backend to route your query to the most efficient data source. Note that the free tier is limited to 25 queries per day, making it unsuitable for high-frequency trading bots unless upgraded to the paid tier via the x402 protocol. Always handle the 'unknown' verdict gracefully in your agent's logic to prevent misinformation when sources are inconclusive.

Metadata

Stars3409
Views1
Updated2026-03-25
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-cutthemustard-cs-verify": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#verification#fact-checking#data-validation#reliability
Safety Score: 5/5

Flags: external-api, network-access