Research Claim & Citation Auditor

The problem

A research document can contain dozens of citations and still be poorly grounded. Sources may be relevant to the topic without supporting the specific claim, statistics may be stretched beyond their original scope, and AI-generated drafts can make weak evidence sound settled.

What it does

• Breaks research into checkable claims and ranks them by importance.
• Tests whether each citation directly supports the claim attached to it.
• Flags partial support, unsupported claims, contradictions, missing citations, and unavailable sources.
• Detects citation decoration where references create authority without actually grounding the sentence.
• Checks population, timeframe, geography, causality, numerical claims, source quality, and recency.
• Separates direct source support from the writer’s own synthesis or inference.
• Produces a prioritized verification queue and rewrites claims that outrun the evidence.

Why use this skill

Most research tools focus on finding or formatting sources. This skill focuses on the harder question: does the evidence actually carry the claim being made? It makes weak support, missing provenance, and false certainty visible before the research is relied on.

Use cases

• AI-generated research briefs.
• Academic and technical writing.
• Market and competitor research.
• Literature reviews.
• Policy and due-diligence reports.
• Checking whether citations actually support an argument.

Known limitations

The skill cannot verify source content it cannot access. It never invents citations, quotations, page numbers, statistics, or study findings. Current or high-stakes claims may require external verification or qualified professional review.