👨💻 Promptolis Originals · Coding & Development
For the engineer who wants to level up, not just ship.
AI prompts for software engineers that teach, not just correct — code review with pattern-naming, codebase archaeology for legacy refactors, structured learning for new stacks. Built by and for working engineers.
39 Originals in this category · Curated by Promptolis Editorial · Last updated
🥇 Tier 3 — Gold / Moat
Premium Originals with low volume but high intent. The ones worth your full attention.
Figma Design Spec Writer
Reads your Figma design + writes the engineering spec: component structure, prop names, edge cases, accessibility notes, the 7 ambiguities engineers will ask about, and the design tokens to use.
Concurrency Bug Debugger
Diagnoses race conditions, deadlocks, and async ordering bugs from your code + logs — names the specific concurrency failure mode + provides the fix that doesn't just paper over the symptom.
Migration Rollout Plan Designer
Designs your DB migration / framework upgrade / dependency change rollout: the staged plan, the rollback gate at each phase, the verification checks, and the 'kill switch' if something breaks at 3am.
OAuth Flow Designer
Designs your OAuth 2.1 + OIDC implementation: authorization code with PKCE, refresh token rotation, the 6 security gotchas that leak tokens — without the bugs that hit security audits.
MCP Server Prompt Engineering (Claude / Cursor / Custom)
Model Context Protocol — Anthropic's open standard (Nov 2024) for AI-tool integration. Pre-built server configs (Linear, Postgres, GitHub, Notion, Slack) + Cursor/Claude Desktop setup + custom server starter. 2026 early-mover.
🥈 Tier 2 — Sweet Spot
Core Originals — mid-volume problems where sharpness beats generic AI output.
GitHub Issue Template Engineer
Designs your repo's GitHub issue templates so contributors actually file useful bugs and feature requests — with the YAML frontmatter, the right form fields, and the labels/assignees automation that makes triage fast.
Google Sheets Formula Translator
Plain-English description in, working Google Sheets formula out — with explanation, edge cases, and the cleaner alternative using QUERY/LAMBDA/LET when applicable.
Jira Ticket Quality Rewriter
Rewrites your vague Jira ticket into the structured spec engineers can actually start work on — with acceptance criteria, edge cases, and the 5 questions PMs always forget to answer.
Linear Project Status Narrator
Reads your Linear project + active issues + recent activity, writes the weekly status update stakeholders actually want to read — risks named, decisions surfaced, and the explicit asks that unblock you.
Webflow CMS Architecture Planner
Designs your Webflow CMS structure: collections, fields, references, dynamic templates, and the 5 architecture decisions that determine whether your site scales to 10 pages or 10,000.
Architecture Decision Record Writer
Writes the ADR (Architecture Decision Record) that future engineers actually read: the context, the alternatives, the trade-offs, and the explicit consequences — instead of '~ this seemed good ~' wiki notes.
Background Job Queue Designer
Designs your queue + worker architecture: which jobs in which queue, retry policy, priority lanes, the dead-letter queue — picking the right pattern between BullMQ / Sidekiq / SQS / Inngest for YOUR scale.
Caching Strategy Architect
Designs your caching: which layer (CDN, app-cache, Redis, DB), what TTL, what invalidation strategy — without the 'cache and pray' bugs that make cached data silently wrong.
Database Index Strategist
Designs your DB index strategy: which queries need indexes, the 4 index types (B-tree, GIN, partial, expression) and when each fits, how to read EXPLAIN plans, and the indexes to DROP that aren't pulling weight.
Dependency Upgrade Strategist
Designs your dep-upgrade strategy: which deps to upgrade now vs ignore, the breaking-change risk per upgrade, the test plan that catches incompatibilities — without spending half a sprint on it monthly.
Error Handling Strategy
Designs your error-handling system: which errors to retry, which to escalate, which to log-and-continue, and the explicit error-class hierarchy that makes 'silent failures in production' a memory.
Feature Flag System Architect
Designs your feature-flag system: which flags vs configs, percentage rollout vs targeting, the cleanup process that prevents 200-stale-flag debt — without LaunchDarkly's $25K/yr bill if you don't need it.
Flaky Test Diagnoser
Diagnoses why your test is flaky from the failure logs + code: names the specific flakiness pattern (timing, order-dependency, real network, shared state, async timing) + the structural fix that doesn't just hide it with retry.
Logging & Observability Instrumentor
Designs your structured logging + metrics + tracing strategy: what to log at what level, the 7 dimensions every event needs, and the dashboards that matter when production is on fire.
Pull Request Author Checklist
Writes the PR description reviewers actually read: the 'what changed', the 'why', the testing notes, and the 5 questions reviewers ask that the description should preempt.
Test Strategy Architect
Designs your test strategy: which tests at which layer, where to invest vs skip, the unit-vs-integration-vs-e2e mix that catches real bugs without paying the 100% coverage tax.
TypeScript Type System Architect
Designs your TypeScript type strategy: where strict types pay off, where they cost more than they save, the 8 advanced patterns that solve real problems, and the 5 anti-patterns that produce 'unreadable types' code review nightmares.
Webhook Handler Architect
Designs your webhook receiver: signature verification, idempotency, ordering, retries from senders, and the queue-it-then-process pattern that doesn't drop events at 3am.
🥉 Tier 1 — Volume
High-search-volume Originals for common tasks — built to outrank generic 'ChatGPT prompt' pages.
Codebase Archaeologist
Reads a codebase not to fix it but to understand its history. What was designed, what grew. The ghost engineer. The frozen decision. The load-bearing wall.
Code Review Teacher
Not just what's wrong — what senior engineer's brain is pattern-matching to when they smell it.
Advanced Regex Composer
Plain English + examples in, working regex out — with explanation, edge-case catalog, and the one case where you should NOT use regex.
API Endpoint Designer
REST vs RPC decision, resource naming consistent with your codebase, error response schema.
Git Commit Message Surgeon
Paste your commits or diff — get conventional-commit-compliant messages, the 'why' for future-you, and a flag for commits that should be split into two.
AI Coding Agent Workflow
The prompt + loop structure for getting 10x out of Claude Code / Cursor / AI agents.
API Versioning Strategy
Designs the versioning approach (URL / header / semantic) that prevents 'breaking changes broke our customers' without freezing your API forever.
Code Review Architect
Runs the 7-layer code review that catches real bugs — from security to performance to maintainability — instead of the 'LGTM 👍' reviews that let issues…
Database Schema Designer
Designs the schema that scales to 10M rows + handles the queries you haven't thought of yet — without premature optimization.
Debugging Hypothesis Generator
Not another 'have you tried restarting it' — the structured bug-diagnosis that ranks 5-7 specific hypotheses and tells you the exact test to falsify each…
Incident Post-Mortem Writer
Writes the blameless post-mortem that actually prevents recurrence.
Performance Optimization Plan
Identifies the 3 bottlenecks that account for 80% of your performance problem — instead of premature-optimizing code nobody calls.
Refactoring Strategy Planner
Plans the incremental 'strangle' refactor that ships continuously — instead of the 6-month rewrite that never ships.
System Design Interview Coach
Walks you through 'design Twitter / Uber / Dropbox' answers using the 7-step framework FAANG interviewers actually score on.
Technical Spec Writer
Writes the 5-page design doc that gets approved — covering context, decisions, alternatives, risks…
Coding & Development Prompts Pack — 30 Prompts From Debug to Ship
30 software-engineering prompts across 6 categories (debugging / code review / architecture / refactoring / API + database / Git + DevOps).
Frequently asked questions
What is the "Coding & Development" category on Promptolis?
AI prompts for software engineers that teach, not just correct — code review with pattern-naming, codebase archaeology for legacy refactors, structured learning for new stacks. Built by and for working engineers. Every prompt in this category is a Promptolis Original — hand-crafted by the Promptolis Editorial team and reviewed before publishing.
How many Coding & Development Originals are there?
There are 39 Promptolis Originals in the Coding & Development category. New ones are added weekly.
Are Coding & Development Originals free?
Yes. Every Promptolis Original is free, MIT-licensed, and copy-ready. No email required, no paywall.
Which AI model works best for Coding & Development prompts?
Most Originals in this category are tuned for Claude Sonnet 4.5 / Opus 4 and GPT-5. Each Original page includes a model-specific recommendation.