Technical AI Prompt Templates
Copy-ready technical prompts with fill-in fields. Pick one, fill in the blanks, and paste it into ChatGPT, Claude, or Gemini. Free to browse.
- Accessibility Audit Checklist - Ordered by who gets locked out, not by checklist number.
- AI Agent System Prompt Designer - A production-grade agent system prompt with role, tool rules, edge-case policy, guardrails, and an output contract, plus three test inputs aimed at its…
- AI Pair-Programming Session Kickoff - Writes the opening message for an AI coding session so the assistant starts with your stack, goal and ground rules instead of guessing.
- Browser QA Session Script - Reproduces a bug in a real browser, captures evidence, writes the regression test, and verifies the fix against it.
- Bug Report Triage Assistant - Turns a messy bug report into a ticket an engineer can act on: a one-line summary, numbered repro steps, expected versus actual behaviour, a severity call…
- Build Error Resolver - Reads a failing build log, finds the first real error behind the cascade, fixes it, and confirms the build passes instead of guessing at the later noise.
- CI Pipeline Design - A CI pipeline redesign that fails fast, runs in parallel where it safely can, caches well, and quarantines flaky tests, with a target total runtime and a list…
- Coding Standards Enforcer - Applies one shared floor of naming, structure, error handling, and readability rules to a file or diff and returns the edits that bring it up to standard.
- Data Cleaning Plan - Clean it in the right order, or you'll do half of it twice.
- Design System Component Spec - Specify it once, properly, so engineering does not have to guess.
- Dockerfile Review and Optimisation - Takes a pasted Dockerfile and returns a smaller, faster-building, non-root version with a comment on each change, a size and time estimate, and the trade-offs…
- Flaky Test Hunter - Finds out why a test passes sometimes and fails others, checking timing, shared state, ordering and environment, then fixes the cause instead of adding retries.
- Idiomatic Go Patterns Review - Reviews Go code for the habits that cause production trouble: lost error context, leaked goroutines, misused contexts, bloated interfaces, and tangled packages.
- Infrastructure as Code Review - Catch the resource that quietly gets destroyed on next apply.
- Kubernetes Manifest Check - Reviews Kubernetes manifests for resource limits, probes, rollout settings, disruption budgets, and security context, then returns corrected YAML with special…
- MCP Server Spec Writer - Specifies a Model Context Protocol server end to end, with tool schemas, auth and error cases, before any code is written.
- Minimal-Change Coding Guidelines - Guides an agent to make the smallest change that solves the problem, with no speculative abstractions and no unrelated edits in the diff.
- OWASP and STRIDE Security Audit - Audits an application against the OWASP Top 10 and STRIDE threats, returning findings ranked by how easily each can be exploited.
- Performance Benchmark Baseline - Establishes a performance baseline for load and Core Web Vitals, with the numbers to beat and a record of exactly how they were measured.
- Playwright E2E Test Planner - Turns a described user flow into a Playwright test plan and runnable specs with stable locators, shared fixtures, and screenshots captured when a step fails.
- Post-Deploy Canary Watch - Sets out what to watch in the first hour after a deploy, with numeric thresholds that tell you when to roll back.
- Prompt Rewriter: ChatGPT to Claude - Adapts a prompt tuned for one assistant to a model that favours structure and explicit context, and explains the three biggest changes.
- Python Patterns Review - Reviews Python code for typing, data modelling, exception handling, packaging, and test layout, with fixes that make it easier to read and safer to change.
- Rate Limiting and Abuse Review - Finds where an API can be abused and sets the rate limits, quotas, backoff and responses that stop scraping, credential stuffing and runaway clients.
- Refactor Without Behaviour Change - Plans a refactor in small safe steps and names the tests that must pass before and after, so behaviour is proven unchanged rather than assumed.
- Repository Threat Model - Builds a threat model of a repository: its assets, trust boundaries, attacker capabilities, and abuse paths, each tied to the code that enables it.
- REST API Design Review - Checks a REST API design for resource naming, verb use, pagination, error shape, versioning, and auth, and returns a consistent contract with the fixes needed.
- Security Best Practices Baseline - A secure-defaults checklist for a new service, covering secrets, auth, dependencies, logging and headers, with a pass or fail verdict on each line.
- Security Review Checklist Runner - Runs a code change through auth, input handling, secrets, data exposure, and payment checks and returns findings ranked by severity, each with a fix.
- SQL Query Builder - A correct SQL query for a plain-English question, with the join risks called out so row counts and totals are not silently inflated.
- Staff Engineer Code Review - Reviews a change like a staff engineer: finds the bugs that pass CI yet fail in production, and blocks only on findings that deserve it.
- Systematic Debugging Investigator - Finds the real cause of a bug before any fix: reproduce it, narrow it, test one hypothesis at a time, then lock it in with a regression test.
- Technical Article Enhancer - Rewrites a rough technical draft into a clear, accurate article for a chosen audience, with precise terminology and optional diagram markers.
- Test Suite Audit - Audits a test suite for tests that cost more than they protect and for missing coverage that matters, reporting findings without changing any code.
- Test-Driven Development Loop - Drives a change with red, green, refactor: a failing test seen to fail for the right reason comes before any production code.
- TypeScript Strictness Review - Tightens a TypeScript codebase by turning on strict flags, removing any, narrowing safely, modelling states as unions, and making async code fail loudly.
- Web App Smoke Test Plan - Produces a short browser test plan for a web app that covers the critical paths and different data states, with a screenshot as evidence for each check.