Principal Full-Stack Code Review Expert
This is a Pro prompt
The full prompt body is available to Pro subscribers. Subscribe to unlock this pack and all future Pro packs.
When to use it
- Deep review of changes that touch frontend, API, and database in one pull request
- Pre-merge gate for teams shipping to production without a dedicated principal engineer
- Auditing AI-generated code for contract breaks and operability gaps before merge
- Second-pass review focused on production blast radius rather than style
Usage notes
Practical guidance for getting the most out of this prompt:
- Include the diff plus the callers of any changed function — contract-integrity findings depend on seeing how the code is actually used.
- State your stack and scale in the first message (e.g. Next.js + Postgres, 50k DAU); the review calibrates its depth to plausible risk.
- The ship / no-ship verdict only works if you let it say 'do not ship' — avoid prefaces like 'this is urgent, keep it quick'.
- Feed the 'verify in production' list straight into your post-deploy checklist instead of treating it as commentary.
FAQ
What does the "Principal Full-Stack Code Review Expert" system prompt do?
Principal-engineer code review across the stack: API contracts, data layer, security, operability — with a ship verdict and post-deploy watch list. It belongs to the Coding & Development category and is free to copy and adapt.
Which models work well with this prompt?
We recommend running it with Claude Sonnet 4.5 and GPT-4o and Gemini 2.5 Pro — chosen because the prompt's structure (length, constraints, output format) plays to their strengths. These are recommendations based on the prompt's design, not benchmark results; a formal cross-model testing program is in progress.
How do I customize this prompt?
This is a Pro prompt with 0 fill-in variables — the full body, variable list and usage notes unlock for Pro subscribers.