Every developer has a messy prompt history—one-off queries for debugging, refactoring, or boilerplate. But the builders who consistently ship high-quality work? They have a curated set of go-to prompts, refined over time. We asked our team for their most indispensable prompts, and here’s the unfiltered list.
1. Build a Spec
Maja Bilić, Senior Outbound Product Manager
Prompt: Act as a cynical Principal Architect and Technical PM. I want to build a [product] that allows [user] to do [action]. Do not write code. Analyze this concept and list the top 5 technical, UX and architectural considerations. Then ask me key questions for each of the 5 considerations so we can work together on building the spec. Once you have all the answers, create a PRD doc and implementation plan. Don't over engineer or over simplify the design or implementation plan.
Why? This prompt forces the AI to act as a cynical architect, distilling ideas and critiquing the approach. It prevents over-engineering and ensures a solid PRD.
2. Widget Tests
Andrew Brogdon, Staff Developer Relations Engineer
Prompt: I'd like to partner with you on increasing the robustness of this project by creating widget tests. If you haven't already, please read the Flutter team's skill for creating widget tests... Then, let's do these things: Examine my application's codebase to identify areas of the UI/UX that are not being tested properly... Create an overall testing plan... Execute that plan.
Why? This prompt combines official Flutter skills with a step-by-step workflow to automate widget testing, reducing guilt and improving code reliability.
3. Find All the Tests / Clean-up Commit
Aja Hammerly, Director of Builder Relations
Prompt 1: Run all the tests and identify any missing tests and write them. Pay special attention to edge cases and race conditions.
Prompt 2: Find any unused code, embarrassing comments, comment to code inconsistencies, unresolved TODOs, or other things in this commit that shouldn't be in there.
Why? These prompts act as a pre-review cleanup, catching edge cases and embarrassing leftovers before human review.
4. Check for Correct and Compliant Permissions
Rich Hyndman, Head of Antigravity Developer Relations
Prompt: Run a comprehensive check on this Android project to ensure all permissions are correct and compliant. Perform the following steps: 1. Locate and analyze all 'AndroidManifest.xml' files... 2. Cross-reference declared permissions against the codebase... 3. Check runtime permission flows... 4. Verify hardware features... Output findings as a Markdown report.
Why? Ensures Android apps have correct permissions, avoiding Play Store delays. Works great with Google Cloud and Android plugins.
5. Conduct Code Review
Shir Meir Lador, Head of AI, Developer Relations
Prompt: Act as a strict, highly analytical Principal Engineer conducting a pre-production code review. You have incredibly high standards and zero tolerance for fragile, 'happy-path' code. Grade my uncommitted changes on an A-to-F scale for production readiness. Specifically analyze for: 1. Efficiency 2. Resilience 3. Architecture. For every issue, provide exact git diffs to fix.
Why? Cuts through AI fluff and forces a harsh, production-focused review with actionable diffs.
6. Explain Trade-offs to Aid Decision-Making
James O’Reilly, Staff Developer Relations Engineer
Prompt: Explain the pros and cons of executing your suggested Implementation Plan. Be specific about the trade-offs related to performance, cost, security and maintainability so I can make an informed decision.
Why? Forces the AI to stress-test its own logic, keeping you in control of decisions.
7. Improve AI-Generated Code Through Research
Emma Twersky, Head of Flutter & Dart Developer Relations
Prompt: Research online, focusing on X threads, StackOverflow, GitHub issues and tech blogs for common security pitfalls, architectural misalignments, and subtle logic errors found in AI-generated INSERT_TECH_YOU'RE_USING_HERE code. Based on these findings, generate a manual review checklist specifically for auditing high-risk areas...
Why? Combats AI ‘slop’ by generating a targeted checklist for high-risk areas where models typically fail.
8. Find Problems Through Iteration
Fred Sauer, Head of Frameworks & Languages Developer Relations
Prompt: Code review the uncommitted changes. Identify any unhandled corner cases. Assess performance. Summarize findings. Then iterate: Fix 1, 3 and 5.
Why? Iterative code review in fresh chat sessions uncovers blind spots and refines solutions until they’re ‘boring’ and solid.
9. Review Every Pull Request
Remigiusz Samborski, Lead Developer Relations Engineer
Prompt: A comprehensive GitHub Actions prompt (full prompt here) that acts as an autonomous code review agent.
Why? Automates PR reviews, catching issues early and freeing human reviewers for higher-level concerns.
10. Apply Directed Acyclic Graph Analysis for Tests
Karl Weinmeister, Director, Developer Relations
Prompt: Analyze the application workflow as a directed acyclic graph. Identify impactful tests for components, seams across components, and across the system. Present your findings in a markdown table as a prioritized gap analysis.
Why? Forces structural reasoning about where things break, focusing on under-tested boundaries between components.
Conclusion
The common thread? De-risking human assumptions. Whether hunting edge cases, stress-testing architecture, or automating reviews, these prompts turn AI into an adversarial thinker that asks the hard questions. Build them into your workflow, and you’ll ship with confidence—no committees required.
Original announcement published on Google Cloud.