Code Review Prompts: Beyond "Looks Good to Me"
13 prompts for AI code review that surfaces real issues — bugs, security, performance, readability, tests.
Code review, bug audit, SEO audit, Claude Code, Codex, refactor, tests, README, security audit.
36 articles
Coding prompts are not "write me this app" — good ones execute one concrete action in a known context: review a diff, write a test set, generate a README. This hub covers 12 dev scenarios: code review, bug audit, SEO audit, Claude Code execution, Codex review, refactor, test generation, READMEs, migration planning, architecture review, security audit, and deployment checks. Built for developers using Claude Code, Codex, Cursor, or similar AI coding tools.
New to this hub? Read these three first:
13 prompts for AI code review that surfaces real issues — bugs, security, performance, readability, tests.
Whole-repo audit prompts for Claude Code / Codex — architecture smells, dead code, security risks, dependency drift, test coverage gaps, in one structured pass.
12 prompts to brief Claude Code (or Codex) on real engineering tasks — scoped features, surgical bug fixes, migrations, refactors, TDD, perf work, debugging, code review.
Stop shipping a11y regressions hidden behind "no axe violations". 12 prompts for keyboard order, focus management, screen-reader copy, and motion preferences.
Get from "it broke" to a minimal reproduction in one prompt. 12 templates for narrowing inputs, isolating env, capturing logs, and writing a repro that lasts.
Stop guessing at red CI. 12 prompt templates for narrowing build / test failures by environment, cache, dependency, flake, and order of operations.
Stop dumping git log into release notes. 12 prompt templates to turn commits / PRs into a user-facing changelog that's honest, brief, and useful.
When CI is slow, flaky, or lies green, you need an audit. 12 prompt templates for GitHub Actions / GitLab CI / CircleCI on caching, parallelism, secrets, and gates.
Inherited a 200-file codebase? 12 prompt templates to infer naming, layering, error-handling, and dependency conventions before you write a single new line.
Stop shipping a11y regressions hidden behind "no axe violations". 12 prompts for keyboard order, focus management, screen-reader copy, and motion preferences.
Get from "it broke" to a minimal reproduction in one prompt. 12 templates for narrowing inputs, isolating env, capturing logs, and writing a repro that lasts.
Stop guessing at red CI. 12 prompt templates for narrowing build / test failures by environment, cache, dependency, flake, and order of operations.
Stop dumping git log into release notes. 12 prompt templates to turn commits / PRs into a user-facing changelog that's honest, brief, and useful.
When CI is slow, flaky, or lies green, you need an audit. 12 prompt templates for GitHub Actions / GitLab CI / CircleCI on caching, parallelism, secrets, and gates.
Inherited a 200-file codebase? 12 prompt templates to infer naming, layering, error-handling, and dependency conventions before you write a single new line.
Stop shipping a11y regressions hidden behind "no axe violations". 12 prompts for keyboard order, focus management, screen-reader copy, and motion preferences.
Get from "it broke" to a minimal reproduction in one prompt. 12 templates for narrowing inputs, isolating env, capturing logs, and writing a repro that lasts.
Stop guessing at red CI. 12 prompt templates for narrowing build / test failures by environment, cache, dependency, flake, and order of operations.
Stop dumping git log into release notes. 12 prompt templates to turn commits / PRs into a user-facing changelog that's honest, brief, and useful.
When CI is slow, flaky, or lies green, you need an audit. 12 prompt templates for GitHub Actions / GitLab CI / CircleCI on caching, parallelism, secrets, and gates.
Inherited a 200-file codebase? 12 prompt templates to infer naming, layering, error-handling, and dependency conventions before you write a single new line.
Migration review prompts that catch lock-table-for-an-hour bugs, backfill races, and silent column drops. 12 templates for Postgres / MySQL / SQLite reviews.
Turn flaky, screenshot-heavy e2e suites into a small, fast, deterministic plan. 13 prompt templates for selectors, fixtures, auth, flakes, and PR coverage.
Before you flip the flag, run a rollout risk review. 12 prompts for gradual rollout plans, observability gates, abort criteria, and customer comms.
Migration prompts that produce a real phased plan — not "rewrite everything in Rust". 12 templates for Next.js, React Router, Postgres, auth provider, monorepo, monolith→service.
12 prompt templates to hand work between Claude Code subagents — research → plan → implement → review → ship — without losing context.
When p99 spikes, you need triage not vibes. 12 prompt templates for diffing perf signals, hunting N+1s, JS bundle bloat, render storms, and DB plan changes.
AI PR review prompts that surface real issues — diff-scoped, change-aware, blast-radius aware. 14 templates for security / perf / tests / docs / risk.
Release-day prompts that build a real go/no-go checklist — not a generic "check the build". 13 templates for staging / canary / rollback / observability.
12 prompt templates to triage tech debt by impact × effort × decay risk — not by "how loud the engineer who hates it is".
Stop asking AI to "write tests for this." 14 unit-test prompt templates for boundary cases, error paths, mocks, fakes, parameterized suites, and regression locks.
Architecture review prompts that surface real layering bugs, dependency cycles, and boundary leaks — not generic "consider DDD" advice.
Firebase config audit prompts — Firestore / Realtime DB / Storage rules, indexes, Cloud Functions, Auth, App Check, hosting.
Whole-repo audit prompts for Claude Code / Codex — architecture smells, dead code, security risks, dependency drift, test coverage gaps, in one structured pass.
Next.js App Router code review prompts — server vs client boundaries, server actions, route handlers, fetch caching, revalidation, streaming.
Supabase Row-Level Security review prompts — auth.uid() checks, role policies, INSERT/UPDATE/DELETE coverage, storage bucket RLS, function security.
12 prompts that walk a page like a keyboard-only and screen-reader user — semantics, focus, ARIA widgets, contrast, modal stacks, live regions, WCAG mapping.
15 prompts that pressure-test REST and GraphQL contracts before they ship — naming, status codes, error model, breaking changes, pagination, N+1, field-level auth.
13 prompts to systematically hunt hidden bugs in code before they ship.
12 prompts to brief Claude Code (or Codex) on real engineering tasks — scoped features, surgical bug fixes, migrations, refactors, TDD, perf work, debugging, code review.
13 prompts for AI code review that surfaces real issues — bugs, security, performance, readability, tests.
12 prompts that walk a schema like a future migrator — normalization, indexes, FK cascades, nullability, soft-delete, JSON columns, migration safety, ORM diff.
12 prompts to pre-flight your deployment — env vars, DNS, cache, observability, rollback drill, post-launch monitoring, security headers, status page comms.
13 prompts for performance work that actually moves a number — measure-first bottleneck ID, LCP / CLS / N+1 / TTFB / bundle / cache fixes, before-after Web Vitals diffs, and a premature-optimization detector.
13 prompts to refactor React components — extract hooks, lift state, split server vs client, memoize correctly, kill prop-drilling.
12 prompts for READMEs that get a new reader from git clone to a working install in 60 seconds — skeleton, quickstart, install troubleshooting, examples, API reference, and audit.
18 copy-ready prompts to plan, execute, and verify AI refactors without breaking behavior — module extraction, renames, async migrations, and god-function splits.
12 prompts to AI-audit your code for OWASP-grade security issues — auth, authz, secrets, deps, file uploads, CORS, PII logging — without hiring a pentester.
12 prompts to AI-audit a content site — metadata, internal links, hreflang, thin content, canonical, schema, cannibalization, Core Web Vitals — with measurable thresholds and fixes.
13 prompts for integration, E2E, snapshot, and contract tests — for unit-test prompts specifically, see the unit-test article. Tests that catch real bugs, not noise.
14 prompts to diagnose TypeScript errors fast — generics, conditional types, narrowing, module resolution, declaration files.