quad-fact-check

Original：🇨🇳 Chinese
Translated

Cross fact-checking with 4 models: Claude + Gemini + Codex. Conduct independent checks with Opus itself, Gemini Flash, Gemini Pro, and Codex (gpt-5.3-codex) → extract issues → discuss → output a consensus report.

2installs
Sourcedaiki48/dotfiles
Added on

NPX Install

npx skill4agent add daiki48/dotfiles quad-fact-check

Tags

Translated version includes tags in frontmatter
cross-fact-checkingai-model-validationconsensus-reportai-workflowcli-tool-usage

SKILL.md Content (Chinese)

View Translation Comparison →

4-Model Cross Fact-Checking (Claude + Gemini + Codex)

Perform independent fact-checks on the target document using four different AIs: Claude Opus, Gemini Flash, Gemini Pro, and Codex, then discuss the issues and output a consensus report.

Prerequisites

  • Gemini CLI (
    gemini
    ) is already installed
  • Codex CLI (
    codex
    ) is already installed
  • Flash is the default model (no need to specify 
    -m
    )
  • Specify Pro with 
    -m gemini-3-pro-preview
  • Specify Codex with 
    -m gpt-5.3-codex

Steps

Step 1: Identify the Target

  • Identify the target document from the conversation context
  • If the target is ambiguous, confirm with Daiki

Step 2: Independent Checks by 4 Models

Opus (Self)

  • Read through the target document and perform fact-checking
  • Verify primary sources via WebSearch

Gemini Flash

  • Execute the following in Bash:
bash
cat <file-path> | gemini -p "Please fact-check the following document. Verify the accuracy of technical facts, consistency of numerical values, internal contradictions, and correctness of code examples. Clearly state the basis for each observation, and classify it as 'Needs Correction / Recommend Improvement / Accurate' in your report."

Gemini Pro

  • Execute the following in Bash:
bash
cat <file-path> | gemini -m gemini-3-pro-preview -p "Please fact-check the following document. Verify the accuracy of technical facts, consistency of numerical values, internal contradictions, and correctness of code examples. Clearly state the basis for each observation, and classify it as 'Needs Correction / Recommend Improvement / Accurate' in your report."

Codex (gpt-5.3-codex)

  • Execute the following in Bash:
bash
codex exec -m gpt-5.3-codex --ephemeral -s read-only "Please fact-check the following document. Verify the accuracy of technical facts, consistency of numerical values, internal contradictions, and correctness of code examples. Clearly state the basis for each observation, and classify it as 'Needs Correction / Recommend Improvement / Accurate' in your report.

$(cat <file-path>)"

Step 3: Compare Results & Extract Issues

  • Cross-reference the results from the 4 models
  • Unanimous agreement: Adopt directly (Reliability: Highest)
  • 3 agree + 1 disagree: Extract as an issue
  • 2 vs 2: Extract as a critical issue
  • Detected by only one model: Opus performs additional verification

Step 4: Discuss Issues

For each issue:
  1. Opus collects additional verification information via WebSearch
  2. Re-query each AI with the verification information attached:
bash
echo "<Issue content and additional verification information>" | gemini -p "Please state your opinion on the following issue based on the additional information provided."
echo "<Issue content and additional verification information>" | gemini -m gemini-3-pro-preview -p "Please state your opinion on the following issue based on the additional information provided."
codex exec -m gpt-5.3-codex --ephemeral -s read-only "Please state your opinion on the following issue based on the additional information provided.

<Issue content and additional verification information>"
  1. Make a final judgment by synthesizing all responses

Step 5: Output Consensus Report

markdown
## 4-Model Cross Fact-Check Results

**Target**: <Document Name>
**Checkers**: Claude Opus 4.6 / Gemini Flash / Gemini Pro / Codex (gpt-5.3-codex)

### Needs Correction
| # | Section | Content | Consensus |
|---|-----------|------|------|
| 1 | ... | ... | Opus ✅ Flash ✅ Pro ✅ Codex ✅ |

### Recommend Improvement
| # | Section | Content | Consensus |
|---|-----------|------|------|

### Issues & Discussions
| Issue | Opus | Flash | Pro | Codex | Conclusion |
|------|------|-------|-----|-------|------|

### Detection Capability Comparison
| Detection Item | Opus | Flash | Pro | Codex |
|---------|------|-------|-----|-------|

### Verified (Accurate)
<List of key verified items>

Notes

  • Opus must verify the results from Gemini and Codex (there is a possibility of false positives)
  • Resolve issues based on evidence, not majority vote
  • Re-query each AI individually for each issue
  • If Codex is unavailable, fall back to 3-model cross fact-checking