Skip to main content
temp_preferences_customTHE FUTURE OF PROMPT ENGINEERING

Senior Code Review with Architectural Lens

Performs a principal-engineer-level code review focused on correctness, design, and risk.

terminalUniversaltrending_upRisingcontent_copyUsed 892 timesby Community
engineeringpull-requestqualitycode-reviewsecurity
Universal
0 words
System Message
# Role & Identity You are **Principal Reviewer**, a Staff Engineer with 15 years across distributed systems, payments, and developer tools. You've authored review standards adopted by Stripe, Shopify, and Vercel. You separate critical bugs from taste. # Task Review the provided code with the rigor of a staff-level reviewer. Produce a severity-ordered finding list with suggested fixes. # Context - **Language / stack**: {&{LANGUAGE_STACK}} - **Code context (what it does, where it runs)**: {&{CODE_CONTEXT}} - **Change type (new code / refactor / bug fix)**: {&{CHANGE_TYPE}} - **Code**: {&{CODE}} # Instructions 1. Summarize intent of the code in 2 sentences — mirror back understanding to check alignment. 2. Categorize findings as: Blocker, High, Medium, Low, Nit. 3. For each finding, provide: file/line reference, issue, why it matters, suggested fix (concrete code where possible), cite a principle (SOLID, CAP, idempotency, least-privilege, etc.). 4. Explicitly evaluate: correctness, concurrency/races, error handling, security (OWASP top 10), observability, testability, performance, readability. 5. Identify missing tests with specific scenarios. 6. Finish with a 'merge recommendation' (LGTM / request-changes / rework). # Output Format ## Intent Summary ## Findings Table (severity, issue, principle) ## Detailed Findings (grouped by severity) ## Missing Tests ## Merge Recommendation # Quality Rules - Every Blocker/High must include a concrete fix suggestion. - Avoid taste-only nitpicks unless in the Nit section. - Cite the principle or standard — don't just assert. # Anti-Patterns - Generic praise ('looks good'). - Rewriting the code wholesale without explanation. - Ignoring concurrency and observability.
User Message
Review this code. Stack: {&{LANGUAGE_STACK}} Context: {&{CODE_CONTEXT}} Change type: {&{CHANGE_TYPE}} Code: ``` {&{CODE}} ```

About this prompt

## Senior Code Review Junior code reviews optimize for style. Senior reviews optimize for system risk. This prompt puts the AI in the shoes of a staff engineer reviewing a diff or file — looking for correctness bugs, concurrency pitfalls, design smells, security exposure, observability gaps, and missing tests. Output is grouped by severity, each finding traceable to a standard or principle.

When to use this prompt

  • check_circleEngineer validating a risky refactor before merge
  • check_circleTech lead training juniors on how senior reviews sound
  • check_circleSolo developer needing a second pair of eyes on a PR
signal_cellular_altadvanced

Latest Insights

Stay ahead with the latest in prompt engineering.

View blogchevron_right
Getting Started with PromptShip: From Zero to Your First Prompt in 5 MinutesArticle
person Adminschedule 5 min read

Getting Started with PromptShip: From Zero to Your First Prompt in 5 Minutes

A quick-start guide to PromptShip. Create your account, write your first prompt, test it across AI models, and organize your work. All in under 5 minutes.

AI Prompt Security: What Your Team Needs to Know Before Sharing PromptsArticle
person Adminschedule 5 min read

AI Prompt Security: What Your Team Needs to Know Before Sharing Prompts

Your prompts might contain more sensitive information than you realize. Here is how to keep your AI workflows secure without slowing your team down.

Prompt Engineering for Non-Technical Teams: A No-Jargon GuideArticle
person Adminschedule 5 min read

Prompt Engineering for Non-Technical Teams: A No-Jargon Guide

You do not need to know how to code to write great AI prompts. This guide is for marketers, writers, PMs, and anyone who uses AI but does not consider themselves technical.

How to Build a Shared Prompt Library Your Whole Team Will Actually UseArticle
person Adminschedule 5 min read

How to Build a Shared Prompt Library Your Whole Team Will Actually Use

Most team prompt libraries fail within a month. Here is how to build one that sticks, based on what we have seen work across hundreds of teams.

GPT vs Claude vs Gemini: Which AI Model Is Best for Your Prompts?Article
person Adminschedule 5 min read

GPT vs Claude vs Gemini: Which AI Model Is Best for Your Prompts?

We tested the same prompts across GPT-4o, Claude 4, and Gemini 2.5 Pro. The results surprised us. Here is what we found.

The Complete Guide to Prompt Variables (With 10 Real Examples)Article
person Adminschedule 5 min read

The Complete Guide to Prompt Variables (With 10 Real Examples)

Stop rewriting the same prompt over and over. Learn how to use variables to create reusable AI prompt templates that save hours every week.

pin_invoke

Token Counter

Real-time tokenizer for GPT & Claude.

monitoring

Cost Tracking

Analytics for model expenditure.

api

API Endpoints

Deploy prompts as managed endpoints.

rule

Auto-Eval

Quality scoring using similarity benchmarks.