triangulate

Cross-check claims against three or more independent sources and produce a structured verdict.

17|1|Updated Feb 21, 2026
One-click install
npx skills add https://github.com/vasilievyakov/miracle-infrastructure --skill triangulate
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: triangulate
Source: https://github.com/vasilievyakov/miracle-infrastructure/tree/main/skills/triangulate
Command: npx skills add https://github.com/vasilievyakov/miracle-infrastructure --skill triangulate

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Verifies information by cross-checking claims against 3+ independent sources, delivering transparent confidence and identifying bias.

Core Features & Use Cases

  • Classifies the claim type (FACT/OPINION/PREDICTION) to tailor verification strategies.
  • Searches 3+ independent sources in parallel and scores each source by type, independence, and recency.
  • Produces a structured verdict with confidence metrics and warnings about bias, echo, or outdated information.
  • Use Cases: fact-checking articles, due-diligence for research, evaluating predictions with evidence.

Quick Start

Provide the claim text to triangulate and review the verdict, sources, and confidence breakdown.

Frequently Asked Questions about triangulate

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

FAQPage Schema
How do I verify a claim across multiple sources?

Fact-checking a claim involves classifying it as a FACT, OPINION, or PREDICTION to tailor the verification strategy. The system then searches 3+ independent sources in parallel, scores each by recency and independence, and generates a confidence score with bias warnings.

How do I assess bias and confidence when evaluating evidence?

Assessing bias and confidence involves scoring multiple independent sources by their type, recency, and independence from each other. The evaluation produces a calculated confidence score and flags potential echo chambers, bias, or outdated information within the evidence.

What is the best way to corroborate information for due diligence?

The best way to corroborate information for due diligence is triangulating the claim across 3+ independent sources. This delivers a structured verdict that classifies the claim type, evaluates source independence, and provides transparent confidence metrics and bias warnings.

Can I use source triangulation for evaluating predictions?

Yes, you can use source triangulation for evaluating predictions by classifying the claim as a PREDICTION to tailor the verification strategy. It searches 3+ independent sources in parallel to gather up-to-date evidence and scores the confidence of the outcome.

When do I need to cross-check claims with independent sources?

You need to cross-check claims with independent sources during journalism, research, or due-diligence scenarios where a claim requires corroboration. It is necessary when validating facts, assessing potential bias, and ensuring the evidence is up-to-date before reaching a final verdict.