Back to Skills

iterative-verification

verified

"Is this ACTUALLY verified, or did I just say it is?" - Ralph-wiggum methodology applied to factual accuracy. Use when (1) claims require evidence not assumption, (2) verification must be demonstrable, (3) single-pass investigation insufficient, (4) factual accuracy is critical. Provides the loop logic: iterate until verification thresholds met. Does NOT trigger for: opinions, preferences, how-to instructions, or when user explicitly wants quick answer.

View on GitHub

Marketplace

cognitive-mechanisms

bogheorghiu/cognitive-mechanisms

Plugin

research-toolkit

Repository

bogheorghiu/cognitive-mechanisms

research-toolkit/skills/iterative-verification/SKILL.md

Last Verified

January 20, 2026

Install Skill

Select agents to install to:

Scope:
npx add-skill https://github.com/bogheorghiu/cognitive-mechanisms/blob/main/research-toolkit/skills/iterative-verification/SKILL.md -a claude-code --skill iterative-verification

Installation paths:

Claude
.claude/skills/iterative-verification/
Powered by add-skill CLI

Instructions

# Iterative Verification: Ralph-Wiggum for Facts

**Seed question:** *Is this ACTUALLY verified, or did I just say it is?*

## Core Principle

Ralph-wiggum = iterative workflows.
Iterative workflows = keep going until genuinely complete.
For facts: keep verifying until claims meet evidence thresholds.

**The anti-pattern this counters:**
```
❌ "I searched once, found something, called it verified"
❌ "The claim sounds right, I'll present it as fact"
❌ "I'm confident, so I don't need to check"
```

**The pattern this enforces:**
```
✅ Search → Label evidence tier → Check threshold → Iterate if gaps
✅ Claim is VERIFIED only when evidence supports it
✅ Keep iterating until criteria actually pass
```

## When This Applies

**TRIGGER:**
- Any claim that must be factually accurate
- Investigation outputs with evidence requirements
- Trust/reliability assessments
- Decisions based on facts, not preferences
- User asks "is this actually true?" or "can you verify?"

**DO NOT TRIGGER:**
- Opinion requests
- Preference questions
- How-to instructions
- User says "quick answer" or "don't need sources"
- Creative/generative tasks

## The Verification Loop

```
1. INVESTIGATE
   - Gather information
   - Make claims

2. LABEL
   - Assign evidence tier to each claim:
     * VERIFIED: Primary sources, court docs, regulatory filings
     * CREDIBLE: Multiple independent sources
     * ALLEGED: Single source, unverified
     * SPECULATIVE: Inference, theoretical

3. CHECK THRESHOLDS
   - ≥80% claims labeled?
   - ≥2 independent sources?
   - Flow traced ≥3 steps?
   - Evidence fresh (<2 years for reliability data)?

4. IF GAPS → ITERATE
   - Identify what's missing
   - Search for specific evidence
   - Return to step 1

5. IF ALL PASS → COMPLETE
   - Output with confidence
   - All claims have evidence basis
```

## Evidence Tier Definitions

| Tier | Definition | Examples |
|------|------------|----------|
| **VERIFIED** | Primary sources directly confirm | Regulatory filings, court

Validation Details

Front Matter
Required Fields
Valid Name Format
Valid Description
Has Sections
Allowed Tools
Instruction Length:
5133 chars