sushi-verify

Verify claims and source links in research documents using Sushidata context lake.

Updated May 22, 2026
One-click install
npx skills add https://github.com/georgeportillo/mitratech-sushidata-plugin --skill sushi-verify
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sushi-verify
Source: https://github.com/georgeportillo/mitratech-sushidata-plugin/tree/main/skills/sushi-verify
Command: npx skills add https://github.com/georgeportillo/mitratech-sushidata-plugin --skill sushi-verify

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires sushidata-api, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill addresses the challenge of ensuring the accuracy and verifiability of research documents and competitor matrices, providing a thorough fact-checking and verification process.

Core Features & Use Cases

  • Fact Checking: Verify the factual claims and source links in any research document or competitor matrix.
  • Source Verification: Confirm that AI-generated summaries accurately reflect their cited sources.
  • Link Validation: Flag broken or misrepresented links and provide corrections.
  • Use Case: Imagine you have a research document with various claims. Use this Skill to automatically verify the accuracy of the information and flag any discrepancies.

Quick Start

Verify the accuracy of a research document by using the sushi-verify skill and providing the document content or URL.

Frequently Asked Questions about sushi-verify

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I fact-check claims in research documents and verify source links?

Fact-checking research documents involves structured accuracy reviews that verify factual claims and validate source links. This process cross-references claims against verified fact lakes and runs external checks to flag discrepancies.

What is the best way to verify AI-generated summaries against their cited sources?

Source verification confirms that AI-generated summaries accurately reflect their cited sources by running structured accuracy reviews. It validates the original links and flags any misrepresentations or broken references.

How do I validate broken or misrepresented links in competitor matrices?

Link validation in competitor matrices flags broken or misrepresented URLs by performing external accuracy checks. It identifies dead links and provides corrections to ensure matrix evidence remains accessible.

Do I need the Sushidata API to verify research document accuracy?

Yes, verifying research document accuracy requires the Sushidata API. You must configure a BASE_URL for API access so the review process can query the pre-existing verified facts in the Sushidata context lake.

Can I use document verification for competitor matrices with various claim types?

Yes, document verification handles various claim types within competitor matrices. It performs structured accuracy reviews to systematically evaluate different claims and confirm that evidence links are valid.

Why does source verification require a context lake for fact-checking?

Source verification requires a context lake like Sushidata to provide pre-existing verified facts. This foundation allows the external accuracy checks to effectively cross-reference new claims and flag actual discrepancies.