Stats
Actions
Tags
From wet-mcp
Verifies claims using adversarial search: finds supporting and contradicting evidence, assesses source quality by tiers, and issues structured verdict with confidence. Counters LLM confirmation bias.
How this skill is triggered — by the user, by Claude, or both
Slash command
/wet-mcp:fact-check [claim to verify][claim to verify]The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Verify a claim by actively searching for BOTH supporting and contradicting evidence. Counteracts LLM confirmation bias by enforcing adversarial search.
Verify a claim by actively searching for BOTH supporting and contradicting evidence. Counteracts LLM confirmation bias by enforcing adversarial search.
Decompose the claim into verifiable sub-claims:
Search for SUPPORTING evidence using search:
search(action="search", query="[claim as stated]")search(action="search", query="[claim] research evidence", search_type="academic")extractSearch for CONTRADICTING evidence (mandatory — do NOT skip):
search(action="search", query="[claim] debunked OR wrong OR myth OR criticism")search(action="search", query="[opposite of claim] evidence")search(action="search", query="[claim] replication failure OR meta-analysis", search_type="academic")extractAssess source quality for each piece of evidence:
Produce verdict with structured output:
npx claudepluginhub n24q02m/wet-mcpAdversarially tests claims by seeking counterevidence, identifying logical fallacies, and demanding empirical proof using Wheat tools and web searches.
Investigates complex claims across diverse sources or fact-checks contradictory information via triangulation, credibility audits, and verification matrices using WebSearch, WebFetch, Read, Grep, Glob.
Evaluates claims by triangulating sources, rating evidence quality, and reaching confidence-rated conclusions. Use for fact-checking, due diligence, or resolving conflicting evidence.