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.
- License 许可
- MIT
- 所属仓库
- github/squad
- 最近更新
- 2026-11-15
- Stars
- ★ 3.4k
- Forks
- 520
01 前言 Front Matter
- name
- fact-checking
- license
- MIT
- metadata
- { "author": "squad", "domain": "quality, verification", "version": "1.0.0", "confidence": "low", "last_validated": "2026-03-01" }
- description
- Review and validate claims using counter-hypothesis testing. Use when verifying technical content, checking references, validating API endpoints, or performing quality assurance on deliverables.
- compatibility
- Requires access to external references and APIs
03 SKILL.md 正文
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, ⚠️ 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} | ✅/⚠️/❌ | {supporting or contradicting evidence} |
**Counter-hypotheses tested:**
- {alternative explanation + result}
**Verdict:** {PASS / PASS WITH NOTES / NEEDS REVISION}
Confidence Levels
- ✅ Verified — evidence confirms the claim
- ⚠️ 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.
04 同仓库更多 Skills
windows-compatibility
Cross-platform path handling and command patterns
versioning-policy
SemVer rules for Squad's stable, preview, insider, and local package versions
tiered-memory
Three-tier agent memory model (hot/cold/wiki) for context reduction per spawn
test-discipline
Design assertions that prove the actual contract and fail on realistic regressions
squad
Squad's command catalog and interactive menu. Invoke via /squad (slash command) or natural language ("squad commands", "what can squad do", "show me squad options"). Presents categorized operations (Install & Upgrade, Team Management, Issues & PRs, Plugins & Skills, Model & Cost, Sessions & State) as an interactive picker. Routes to the right squad CLI command or the Squad coordinator agent.
squad-version-check
Internals of how @bradygaster/squad-cli stamps its version, how `squad upgrade` works (what it preserves vs overwrites), and how to probe the npm registry for the latest version from a coordinator prompt.