All Formats
StarPillar Specification & Hub Directory

OpenAI Custom Instructions & System Prompts

Targeted system instructions for ChatGPT, GPT-4o, and o-series reasoning models.

Open Blank Studio Editor
Target: prompts/openai-custom-instructions.md
01 / SPECIFICATION & RUNTIME BEHAVIOR

How OpenAI Custom Instructions Operates in Production

OpenAI system instructions set the foundation for model behavior, response formatting, and technical boundaries. Crafting concise, role-anchored instructions with negative constraints produces higher-fidelity code and prevents verbose boilerplate.

System Persona & GuardrailsSpec Syntax

Set the engineer role, technical boundaries, and brevity requirements to avoid chatty responses.

You are a Senior TypeScript Architect.
Philosophy: Strict type-safety, zero-any policy.
Provide concise code diffs without boilerplate fluff.
02 / REPOSITORY PLACEMENT
prompts/openai-custom-instructions.mdChatGPT Custom Instructions / Custom GPTs / Playground

System instruction blueprint for personal ChatGPT profiles or team Custom GPT knowledge bases.

03 / PRESET SPOKE MATRIX

Available Tech Stack Presets (27)

Click any tech stack below to open the client-side editor preloaded with this verified configuration.

FrontendLaunch

Next.js 15 App Router

Generate OpenAI ChatGPT and Playground custom instructions for Next.js 15 App Router.

Enforced Invariant:

"Enforce React Server Components (RSC) by default; restrict 'use client' strictly to interactive leaf components."

FrontendLaunch

React 19 & Vite

Generate OpenAI ChatGPT and Playground custom instructions for React 19 & Vite.

Enforced Invariant:

"Use React 19 action hooks (useActionState, useOptimistic, useFormStatus) for async mutations."

BackendLaunch

Python FastAPI & Pydantic v2

Generate OpenAI ChatGPT and Playground custom instructions for Python FastAPI & Pydantic v2.

Enforced Invariant:

"Use strict Pydantic v2 BaseModels with Field validation for all input and output schemas."

Fullstack & DBLaunch

Supabase & PostgreSQL

Generate OpenAI ChatGPT and Playground custom instructions for Supabase & PostgreSQL.

Enforced Invariant:

"Always include `ENABLE ROW LEVEL SECURITY;` on every created table."

Fullstack & DBLaunch

Prisma ORM

Generate OpenAI ChatGPT and Playground custom instructions for Prisma ORM.

Enforced Invariant:

"Always use `select` to specify required fields; avoid raw `findMany()` fetching unused relations."

Fullstack & DBLaunch

Drizzle ORM

Generate OpenAI ChatGPT and Playground custom instructions for Drizzle ORM.

Enforced Invariant:

"Define schemas using pgTable/sqliteTable with explicit foreign keys and constraints."

BackendLaunch

Go (Golang) & Fiber

Generate OpenAI ChatGPT and Playground custom instructions for Go (Golang) & Fiber.

Enforced Invariant:

"Check every `if err != nil` explicitly; never swallow errors or ignore returned values."

BackendLaunch

Rust & Axum

Generate OpenAI ChatGPT and Playground custom instructions for Rust & Axum.

Enforced Invariant:

"Never call `.unwrap()` or `.expect()` in production route handlers; propagate errors via `Result<T, AppError>`."

FrontendLaunch

Tailwind CSS v4

Generate OpenAI ChatGPT and Playground custom instructions for Tailwind CSS v4.

Enforced Invariant:

"Configure themes directly in globals.css using `@theme` and `@import 'tailwindcss';`."

FrontendLaunch

Vue 3 & Nuxt 3

Generate OpenAI ChatGPT and Playground custom instructions for Vue 3 & Nuxt 3.

Enforced Invariant:

"Always use `<script setup lang='ts'>` and the Composition API; ban legacy Options API."

FrontendLaunch

SvelteKit 5 & Svelte 5

Generate OpenAI ChatGPT and Playground custom instructions for SvelteKit 5 & Svelte 5.

Enforced Invariant:

"Use Svelte 5 runes: `$state()`, `$derived()`, and `$props()`."

Specialist PersonaLaunch

Universal Cursor Pro

Generate OpenAI ChatGPT and Playground custom instructions for Universal Cursor Pro.

Enforced Invariant:

"Deliver surgical, targeted diffs; never replace entire files unnecessarily."

Specialist PersonaLaunch

Pragmatic Rapid Prototyping

Generate OpenAI ChatGPT and Playground custom instructions for Pragmatic Rapid Prototyping.

Enforced Invariant:

"Prioritize working software over complex design patterns or deep inheritance hierarchies."

Specialist PersonaLaunch

Zero-Trust Security

Generate OpenAI ChatGPT and Playground custom instructions for Zero-Trust Security.

Enforced Invariant:

"Flag and prevent any dynamic SQL query string interpolation."

DevOps & ToolingLaunch

Docker & CI/CD

Generate OpenAI ChatGPT and Playground custom instructions for Docker & CI/CD.

Enforced Invariant:

"Always use multi-stage Docker builds to separate builder tools from the lean production image."

Specialist PersonaLaunch

Vitest & Playwright TDD

Generate OpenAI ChatGPT and Playground custom instructions for Vitest & Playwright TDD.

Enforced Invariant:

"Write unit tests covering happy paths and at least two edge/error cases for every new function."

Specialist PersonaLaunch

Automated Code Reviewer

Generate OpenAI ChatGPT and Playground custom instructions for Automated Code Reviewer.

Enforced Invariant:

"Scan repository manifests to map stack idioms before evaluating logic."

Specialist PersonaLaunch

Multi-Agent System Orchestration

Generate OpenAI ChatGPT and Playground custom instructions for Multi-Agent System Orchestration.

Enforced Invariant:

"Define subagent roles: Lead Architect, Frontend Engineer, Backend Specialist, Security Reviewer."

BackendLaunch

Django 5 & Ninja / DRF

Generate OpenAI ChatGPT and Playground custom instructions for Django 5 & Ninja / DRF.

Enforced Invariant:

"Use asynchronous ORM operations (aget(), acreate(), afirst()) inside async def view handlers."

BackendLaunch

Bun & Elysia / Hono

Generate OpenAI ChatGPT and Playground custom instructions for Bun & Elysia / Hono.

Enforced Invariant:

"Use Elysia's native t schema builder (powered by TypeBox) for request body, query, and parameter validation."

FrontendLaunch

React Native & Expo Router

Generate OpenAI ChatGPT and Playground custom instructions for React Native & Expo Router.

Enforced Invariant:

"Use Expo Router file-based filesystem routing (app/_layout.tsx, app/(tabs)/index.tsx); ban legacy React Navigation container boilerplate."

FrontendLaunch

Flutter 3 & Riverpod / Dart

Generate OpenAI ChatGPT and Playground custom instructions for Flutter 3 & Riverpod / Dart.

Enforced Invariant:

"Always add const constructors wherever possible to maximize Flutter element rebuild caching."

DevOps & ToolingLaunch

Kubernetes & Helm Charts

Generate OpenAI ChatGPT and Playground custom instructions for Kubernetes & Helm Charts.

Enforced Invariant:

"Always specify explicit resources.requests and resources.limits (both CPU and memory) on every container."

DevOps & ToolingLaunch

Terraform & OpenTofu IaC

Generate OpenAI ChatGPT and Playground custom instructions for Terraform & OpenTofu IaC.

Enforced Invariant:

"Pin explicit version constraints for all providers and required Terraform/OpenTofu core versions (required_providers)."

DevOps & ToolingLaunch

Playwright End-to-End Testing

Generate OpenAI ChatGPT and Playground custom instructions for Playwright End-to-End Testing.

Enforced Invariant:

"Strictly ban hardcoded delays (page.waitForTimeout()); rely exclusively on Playwright web-first auto-waiting assertions (expect(locator).toBeVisible())."

BackendLaunch

Spring Boot 3 & Java 21

Generate OpenAI ChatGPT and Playground custom instructions for Spring Boot 3 & Java 21.

Enforced Invariant:

"Use jakarta.* packages for persistence, validation, and servlets; ban legacy javax.* imports."

BackendLaunch

.NET 8 & C# 12 Minimal APIs

Generate OpenAI ChatGPT and Playground custom instructions for .NET 8 & C# 12 Minimal APIs.

Enforced Invariant:

"Use modern C# 12 features: primary constructors, collection expressions, file-scoped namespaces, and nullable reference types (#nullable enable)."

04 / BEST PRACTICES
Place negative constraints ('Never do X') near the top of the system prompt for maximum compliance.
Explicitly instruct the model to provide minimal diffs preserving existing comments.
Save instructions in version control under `prompts/` to keep team prompts aligned.
Other Format DirectoriesHub Network
05 / FREQUENTLY ASKED QUESTIONS

How do I use this in ChatGPT?

Open ChatGPT Settings > Personalization > Custom Instructions, and paste the generated text into 'How would you like ChatGPT to respond?'.

Can I use this in the OpenAI API?

Yes, pass the generated content as the `developer` or `system` message in Chat Completion requests.