Verify factual claims in content using deep research methodology - fact-checks key assertions and updates NCI scores
Fact-checks factual claims using deep research methodology and source reliability scoring.
/plugin marketplace add synaptiai/synapti-marketplace/plugin install decipon@synapti-marketplaceVerify factual claims in content using deep research methodology. Can be run standalone or after NCI analysis.
/decipon:verify <URL or text content>
/decipon:verify --claims "claim1" "claim2" "claim3"
$ARGUMENTS: Content to analyze OR specific claims to verify
--claims: Verify specific claims directlyFact-check key claims using deep research:
Extract Claims (if content provided)
Research Each Claim
Evaluate Sources
Generate Report
| Status | Meaning |
|---|---|
| VERIFIED | 2+ high-confidence sources support claim |
| PARTIALLY VERIFIED | Core claim true but with caveats |
| UNVERIFIED | Cannot find supporting evidence |
| CONTRADICTED | High-confidence sources refute claim |
═══════════════════════════════════════════════════
CLAIM VERIFICATION REPORT
═══════════════════════════════════════════════════
SUMMARY
───────
Claims Analyzed: [N]
✓ Verified: [N]
~ Partial: [N]
? Unverified: [N]
✗ Contradicted: [N]
DETAILED FINDINGS
─────────────────
CLAIM 1: "[Statement]"
Status: [STATUS]
Confidence: [%]
Sources:
[1] example.com (Confidence: 85) - Supports
[2] reuters.com (Confidence: 90) - Supports
Finding: [What research revealed]
───────────────────────────────────────────────────
CLAIM 2: "[Statement]"
[Continue for each claim...]
═══════════════════════════════════════════════════
METHODOLOGY
Applied deep research verification protocol
Consulted [N] sources total
Source confidence scoring: 1-100 scale
RECOMMENDATIONS
[Any suggested follow-up verification]
═══════════════════════════════════════════════════
/decipon:analyzeIf NCI analysis shows elevated manipulation risk (score > 40), verification is recommended:
/decipon:analyze https://example.com/article
# Returns NCI score of 55 with key claims identified
/decipon:verify https://example.com/article
# Verifies claims and may adjust manipulation assessment
Verification is automatically suggested when:
After verification, NCI scores may be adjusted:
Verify content from URL:
/decipon:verify https://example.com/news-article
Verify specific claims:
/decipon:verify --claims "The study showed 90% improvement" "Experts unanimously agree"
After NCI analysis:
/decipon:analyze <content>
# If score elevated:
/decipon:verify <content>
Uses the deep research skill for:
See skills/deep-research/SKILL.md for full methodology.
| Source Type | Confidence Range |
|---|---|
| Peer-reviewed research | 85-100 |
| Official documentation | 85-95 |
| Government/institutional | 75-90 |
| Major news (Reuters, AP) | 70-85 |
| Established newspapers | 60-80 |
| Industry publications | 50-75 |
| Blogs/forums | 20-50 |
| Anonymous/undated | 5-20 |
| Command | Focus | Depth |
|---|---|---|
/decipon:score | Quick manipulation score | Light |
/decipon:analyze | Full pattern analysis | Thorough |
/decipon:verify | Claim fact-checking | Deep research |
/decipon:report | Formal documentation | Complete |
/decipon:score - Get initial manipulation score/decipon:analyze - If score > 20/decipon:verify - If score > 40 or claims seem dubious/decipon:report - For formal records/verifySmart verification command - run quality checks and final verification
/verifyFinal verification - run all Pest tests, validate Playwright UI flows, and check production checklist