AI Skill StudioAI Skill Studio
Skills
Presets:

Target Standard & File Format

AI Agent Rules & Skills
Context Shields & Privacy (Ignore Files)
Integrations & Machine Documentation
AI Governance & Multi-Agent Planning Suite

Identity & Activation Rules

3 chips
Scoped domain keywords evaluated in real time
api-routescode-auditsrefactoring
Suggested Chips:

Technology Stack Context

Engineering Philosophy

Flexible & Adaptable

Architectural & Code Quality Conventions

Less rigid & configurable

Agent Behavioral Guardrails

Select active rules
Security & Trust Boundaries
Always included
  • Untrusted Content Is Data
  • Encoded Payloads
  • Least-Privilege File Access
  • Confirm Irreversible Actions
  • Secret Handling
  • Validation Failures
  • Conflicting Requests

Step-by-Step Workflow Procedures

Flutter 3 & Riverpod / Dart Gemini System Prompt

Generate Google AI Studio and Gemini SDK system instructions for Flutter 3 & Riverpod / Dart. Google AI Studio and Gemini SDK system instructions steer Gemini models with explicit Flutter 3 & Riverpod / Dart roles, input constraints, and output formats, maximizing reasoning reliability and code fidelity.

Target Path
prompts/gemini-system-instructions.json
Execution Scope
Sent per request
Specification Format
JSON system instruction
AI Tool Support
Gemini API and Google AI Studio
02 / WHY IT HELPS

What this file changes for Flutter 3 & Riverpod / Dart

Without it

Google AI Studio and Gemini SDK system instructions steer Gemini models with explicit Flutter 3 & Riverpod / Dart roles, input constraints, and output formats, maximizing reasoning reliability and code fidelity.

What the file tells the agent
Always add const constructors wherever possible to maximize Flutter element rebuild caching.
Use Riverpod 2 with code generation (@riverpod / NotifierProvider) or BLoC; ban raw mutable setState() in business logic.
Leverage Dart 3 pattern matching and sealed classes for exhaustive state and error representation.
Enforce sound null safety: avoid force-unwrapping with ! unless proven non-null by a preceding guard clause.
Separate presentation UI widgets from asynchronous repository and API service layers.
03 / CODE PATTERNS

Flutter 3 & Riverpod / Dart: code to avoid and code to write instead

Avoid
// Discouraged: Mutable setState with force-unwrap and missing const
class BadProfile extends StatefulWidget {
  @override
  _BadProfileState createState() => _BadProfileState();
}
class _BadProfileState extends State<BadProfile> {
  var user;
  void load() async {
    user = await fetchUser();
    setState(() {});
  }
  @override
  Widget build(BuildContext context) {
    return Container(child: Text(user!.name)); // Runtime crash if null!
  }
}
Write instead
import 'package:flutter/material.dart';
import 'package:flutter_riverpod/flutter_riverpod.dart';

@immutable
sealed class ViewState<T> {
  const ViewState();
}
class Loading<T> extends ViewState<T> { const Loading(); }
class Success<T> extends ViewState<T> { final T data; const Success(this.data); }
class Failure<T> extends ViewState<T> { final String message; const Failure(this.message); }

class ProfileView extends ConsumerWidget {
  const ProfileView({super.key});

  @override
  Widget build(BuildContext context, WidgetRef ref) {
    final state = ref.watch(profileProvider);
    return Scaffold(
      appBar: AppBar(title: const Text('Profile')),
      body: switch (state) {
        Loading() => const Center(child: CircularProgressIndicator.adaptive()),
        Success(:final data) => Center(child: Text('Welcome, ${data.name}')),
        Failure(:final message) => Center(child: Text('Error: $message')),
      },
    );
  }
}
04 / REPOSITORY PLACEMENT & 3-STEP TERMINAL INSTALLATION

How to Install Flutter 3 & Riverpod / Dart Gemini System Instructions via Terminal

1

Step 1: Open Project Directory & Verify Target Placement

Open your terminal and navigate to your project root folder where the prompts/gemini-system-instructions.json file will reside. Ensure the file is placed at the exact path below relative to your project root so the AI engine automatically loads it:

prompts/gemini-system-instructions.json
2

Step 2: Fetch Rule File via Terminal Command

Run curl, PowerShell, or wget to stream the rule directly from the DevScratchpad raw API endpoint and write it to prompts/gemini-system-instructions.json:

Terminal One-Liner Install

Run directly in your project root to stream and write this rule file with one command.

Raw API Stream
$mkdir -p "prompts" && curl -fsSL "https://www.devscratchpad.tech/api/raw/gemini-prompts/flutter-dart" -o "prompts/gemini-system-instructions.json"
3

Step 3: Check that Gemini API and Google AI Studio uses it

Nothing loads this file automatically. Pass it as the system instruction in your Gemini API call, or paste it into Google AI Studio.

05 / ROUTE DIRECTORY & CROSS-TOOLING
Format Pillar Hub

Gemini system instructions generator for the Gemini API

Gemini System Instructions: how it works, where the file goes, and every Gemini preset.

/gemini-prompts Directory
06 / RELATED DEVELOPER TOOLS

Tools for Flutter 3 & Riverpod / Dart work

Browser-based utilities to test, format and inspect the code your AI tool writes. Nothing you paste is uploaded.

View all 28 tools

Live Repository & Schema Ingestion

Inspect any public or private GitHub repository, or paste SQL DDL and Prisma models directly in AI Skill Studio to auto-generate authentic rules. Zero server transmission.

Launch AI Skill Studio

Migrating from Legacy .cursorrules or CLAUDE.md?

Use the free, in-browser converter to turn one long rules file into Cursor .mdc, Claude SKILL.md or Windsurf rules.

Convert Rules Free
07 / FREQUENTLY ASKED QUESTIONS

Technical FAQ: Flutter 3 & Riverpod / Dart AI Rulebooks

How do I use this prompt in Google AI Studio?

Paste the text parts into the System instructions field in Google AI Studio, or load the JSON in code and pass it as the system instruction (system_instruction in REST, config.systemInstruction in the Google Gen AI SDK).

Which Gemini models support these instructions?

Current Gemini models in the Gemini API and Google AI Studio accept a system instruction. Check Google's model list for the one you use.