sbroenne / fact-checking
Review and validate claims using counter-hypothesis testing. Use when verifying technical content, checking references, validating API endpoints, or performing quality assurance on deliverables.
0
SKILL.md2.0 KB
⚠This file contains 3 character(s) that do not render as themselves (U+FE0F). They are shown highlighted below.
Skill: Fact Checking
Context
Codifies the challenger agent review output format and methodology so any agent performing fact-checking or review produces consistent, structured output.
Pattern
Review Methodology
For every claim or deliverable under review:
- Ask: "What evidence supports this? What would disprove it?"
- Generate counter-hypotheses and test them against available data
- Verify URLs, package names, API endpoints, and external references actually exist
- Flag confidence levels: ✅ Verified, ⚠‹VARIATION SELECTOR U+FE0F› Unverified, ❌ Contradicted
Review Output Format
When reviewing another agent's work, use this template:
### Fact Check — {deliverable name}
**Claims verified:** {count}
**Issues found:** {count}
| # | Claim | Status | Evidence/Notes |
|---|-------|--------|---------------|
| 1 | {claim} | ✅/⚠‹VARIATION SELECTOR U+FE0F›/❌ | {supporting or contradicting evidence} |
**Counter-hypotheses tested:**
- {alternative explanation + result}
**Verdict:** {PASS / PASS WITH NOTES / NEEDS REVISION}Confidence Levels
- ✅ Verified — evidence confirms the claim
- ⚠‹VARIATION SELECTOR U+FE0F› Unverified — cannot confirm or deny; suggest verification method
- ❌ Contradicted — evidence disproves the claim
Ceremony Integration
Auto-trigger this skill before any architecture decision, or when an agent claim contains superlatives or percentage thresholds (e.g., "saves 75%", "always", "never"). The coordinator spawns the challenger agent with:
Challenger — fact-check {agent}'s claim: "{claim}"
Cite evidence for every verdict. Max 3 investigation cycles.