Cardio review
External-model cross-examination review with optional git context for code and architecture decisionsFrom its SKILL.md
npx -y skills add supportersimulator/3-surgeons --skill cardio-reviewAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.4 KB, as published. Nobody here has run it
Cardio Review
The Cardiologist (GPT-4.1-mini) provides cross-examination reviews that combine external analysis with neurologist blind-spot detection.
When to Use
- After implementing a significant change (>3 files touched)
- Before merging a feature branch
- When you want an external perspective on an architectural decision
- When git context would help (pass recent changes for targeted review)
How It Works
- Cardiologist analyzes the topic independently
- Neurologist identifies blind spots the cardiologist might miss
- Results are synthesized with any dissent preserved
- Recommendations generated
With Git Context
Pass --git-context to include recent changes:
3s cardio-review "authentication refactor" --git-context "$(git diff HEAD~3)"
The cardiologist will analyze the actual code changes alongside the topic.
Output
cardiologist_findings— external analysisneurologist_blind_spots— what the cardiologist might have missedsynthesis— combined viewdissent— any unresolved disagreements (preserved, not hidden)recommendations— actionable next steps
MCP tool: cardio_review_tool
CLI: 3s cardio-review "topic" [--git-context "changes"]
Cost
~$0.002-0.005 per review (cardiologist API call + neurologist is free).