Development prompts
Code generation, review, debugging and refactoring prompts for real engineering work. Fill in the fields, then copy for Claude, ChatGPT or Gemini.
Build a React component from a description
Turn a plain-English description into a production-ready, accessible React + Tailwind component with a usage example.
Senior code review that catches real bugs
Paste a snippet or PR diff and get a senior-engineer review: real issues ranked by severity, each with the exact input that breaks it and a concrete fix — not a wall of style nitpicks.
Debug an error by root cause, not guesswork
Paste an error and its context to get a traced root-cause diagnosis, a fix that addresses the real cause, and a concrete way to verify the bug is gone.
Write thorough unit tests for a function or component
A fill-in prompt that turns any function or component into a runnable unit test suite covering happy paths, edge cases, boundaries, and error handling in your chosen framework.
Refactor a messy function into clean, maintainable code
A copy-paste ChatGPT prompt that refactors a messy function into clean, maintainable code without changing its behavior — it audits the code, rewrites it, explains each change, and suggests tests to prove nothing broke.
Build a regex from a plain-English description (with test cases)
A fill-in-the-blank ChatGPT prompt that turns a plain-English rule into a working regex for your exact language — with a line-by-line breakdown and a pass/fail table of positive and negative test cases.
Write a clear, conventional git commit message from a diff
A fill-in prompt that turns any git diff into a clean, convention-compliant commit message with a tight subject line and a what-and-why body a reviewer can trust.
Generate a professional README for any repo
A fill-in ChatGPT prompt that turns your repository's actual files into a complete, professional README.md — real install and usage commands, no invented features.
Convert code from one language to another
A fill-in prompt that translates code from one programming language to another — producing idiomatic, behavior-preserving output plus dependency mapping and flagged caveats, not a literal line-by-line transliteration.
API design advisor: interview me, then output the endpoint spec
A paste-and-go system prompt that interviews you one question at a time about your REST API, then outputs a complete, implementation-ready endpoint specification.
Write a reviewer-ready pull request description
A fill-in prompt that turns your diff, commits, and test notes into a reviewer-ready pull request description — summary, context, test steps, and a risks-and-review-focus section a reviewer can approve from.
Explain unfamiliar code in plain English
A ready-to-use ChatGPT prompt that explains unfamiliar code in plain English — what it does, how it works block by block, and what to watch out for — pitched to your experience level.
Architecture Decision Record (ADR) facilitator
A paste-and-go prompt that interviews you about one technical decision, then writes a clean, numbered Architecture Decision Record (ADR) in markdown — context, options considered, and honest tradeoffs included.
Write a production-ready, secure Dockerfile
A fill-in-the-blank prompt that turns your app's stack into a hardened, multi-stage Dockerfile — pinned minimal base, non-root user, no secrets in layers, cache-optimized, with a matching .dockerignore and build/run commands.
Database schema designer: from feature idea to tables and migrations
A paste-and-go prompt to design a database schema: it interviews you one question at a time, then delivers normalized tables, an ER diagram, indexes, and a reversible migration plan.
Tech stack advisor: interview me, then recommend a stack with trade-offs
A paste-and-go prompt that interviews you one question at a time about your app, then recommends a specific tech stack with honest trade-offs, an alternative, and a phased build order.
TDD pair-programming coach (red-green-refactor loop)
A paste-and-go prompt for test-driven development with AI: it becomes your TDD pair programmer and walks you through the red-green-refactor loop one failing test at a time.
Performance-bottleneck advisor: find what's slow and give a fix plan
A paste-and-go prompt to find performance bottlenecks in code: it interviews you for evidence, pinpoints what's actually slow on the hot path, and returns a ranked fix plan with expected impact and effort for each item.
Blameless incident postmortem writer
A paste-and-go prompt that interviews you about an outage and writes a structured, blameless incident postmortem — timeline, impact, contributing factors, and assigned action items.
Design a strict JSON schema so my LLM returns reliable structured output
Turn a plain-English description of the data you need into a strict, validator-passing JSON schema that forces your LLM to return reliable structured output on every call.