flutter-ai-rules
Flutter AI Skills and Rules for Claude, Codex, Cursor, and Other AI-Powered IDEs
Install / Use
npx skills add evanca/flutter-ai-rulesInstalls into whichever agent you are using.
.cursorrules
Cursor IDE rules (legacy)
Quality Score
Category
AI & Machine LearningSupported Platforms
Tags
Our assessment of flutter-ai-rules
flutter-ai-rules scores 88/100 on our quality scale, 443rd of 965 AI & Machine Learning skills we index (top 46%).
Its .cursorrules is 11 KB long, well organised into 19 sections with 4 code examples: a thorough specification that gives an agent plenty to work with.
It has 669 GitHub stars, a meaningful sign that others use it.
Maintenance, license and trust
- The repository was last updated today, so flutter-ai-rules is actively maintained.
- Our last check on 2026-10-21 found the source still online.
- It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
- Its trust signals score 95/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.
AI review by kimi-k2.7-code on 2026-09-24. Automated pattern scan on 2026-09-24. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
flutter-ai-rules compared with similar skills
All 4 of these similar skills score higher than flutter-ai-rules; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| flutter-ai-rules (this skill)by evanca | 88 | 669 | today | .cursorrules |
| claude-memby thedotmack | 100 | 113.5k | today | CLAUDE.md |
| Understand-Anythingby Egonex-AI | 100 | 90.9k | 10d ago | CLAUDE.md |
| headroomby headroomlabs-ai | 100 | 78.9k | today | CLAUDE.md |
| CowAgentby zhayujie | 100 | 47.8k | today | CLAUDE.md |
Frequently asked questions
- How do I install flutter-ai-rules?
- Run
npx skills add evanca/flutter-ai-rules. The install tabs above show the steps for each supported agent. - Which AI agents does flutter-ai-rules work with?
- It is written for Cursor, Windsurf and OpenAI Codex, as a .cursorrules file. Other agents that read the same format can often use it too.
- Is flutter-ai-rules safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 95/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is flutter-ai-rules still maintained?
- The repository was last updated today, so flutter-ai-rules is actively maintained.
Skill content
View source on GitHubFlutter AI Skills and Rules for Cursor, Claude, Codex, Antigravity, and Other AI-Powered IDEs
<img src="media/flutter_ai_rules.png" width="500" alt="Flutter Rules for Windsurf, Cursor">⚡ TLDR
Primary method: Copy skill folders from skills/ into your IDE's skills directory (e.g., .cursor/skills/, .windsurf/skills/). The agent will automatically use relevant skills based on your tasks.
For traditional rules: If you want to use .cursor/rules or .windsurfrules, just copy the contents of the rule set of your choice (e.g., combined/flutter_dart__under_6K.md) into your IDE's global or local rules.
For maximum control, you can also copy the /rules folder into your project and reference rules as needed (e.g., "Read @rules/effective_dart.md and follow its conventions."). For tool- and package-specific guidance (Firebase, Bloc, Riverpod, Mockito, etc.), use the matching skill in skills/.
🚀 Introduction
This repository provides a comprehensive, (almost) non-opinionated collection of Flutter-related rules tailored for use with Windsurf, Cursor, and other AI-powered IDEs. These rules are designed to improve your development workflow, ensure consistency, and help you get the most out of your AI coding assistant.
📁 Repository Structure
-
skills/
NEW! Skills are an open standard for extending agent capabilities. A skill is a folder containing aSKILL.mdfile with instructions that the agent can follow when working on specific tasks. They are essentially what “dynamic rules” used to be — applied automatically when the agent determines they are relevant based on the description.Copy or symlink any skill folder into
.cursor/skills/,.agent/skills/, or another supported location. -
rules/
Contains individual rule files covering broad Flutter/Dart foundations (e.g.,effective_dart.md,flutter_app_architecture.md,flutter_errors.md,testing.md). Tool- and package-specific guidance (Bloc, Riverpod, Provider, Mockito, Firebase, etc.) now lives inskills/. These files are:- Based only on official documentation from Flutter, Dart, or relevant package websites.
- Categorized by subject to make them easy to mix, match, and reference.
- Meant to be refined, adjusted, or extracted based on your project needs.
-
combined/
Contains pre-made, curated sets of rules that combine commonly used topics (e.g., Flutter + Riverpod + Mockito).
These files:- Are kept under 6,000 characters to comply with Windsurf's limit.
- Can be used as-is by copying them into your global or local rules configuration.
✅ How To Use
Option 1: Skills - Agent Will Decide What to Use
Install skills interactively with the Skills CLI:
npx skills add evanca/flutter-ai-rules
To inspect the available skills without installing them:
npx skills add evanca/flutter-ai-rules --list
To install a specific skill:
npx skills add evanca/flutter-ai-rules --skill flutter-best-practices
The CLI discovers the packages under skills/ and installs them for supported agents. Alternatively, browse the folder and copy or symlink individual skill folders into your IDE's skills directory (e.g., .cursor/skills/, .windsurf/skills/). The agent will then activate relevant skills contextually based on your tasks.
Option 2: Use Pre-Made Combined Rules
If you want a quick setup with traditional rules:
- Browse the
combined/folder. - Copy a file that suits your project.
- Paste it into your IDE's global or local rules config.
- You're ready to go.
Option 3: Use Individual Rule Files
If you prefer more control:
- Browse the
rules/folder. - Pick files relevant to your project (e.g.,
effective_dart.md,testing.md, etc.). - You can:
- Include them directly in your IDE setup.
- Reference them in prompts to add context.
- Extract only the parts that are useful for your context.
- Include them partially or fully in a PRD (Product Requirements Document).
Everything is modular — use what works best for you.
Option 4: Download All Skills via CLI
You can fetch the latest skills directly into your project with a single command:
git clone --depth 1 https://github.com/evanca/flutter-ai-rules.git temp_repo && mkdir -p .skills && cp -r temp_repo/skills/* .skills && rm -rf temp_repo
This will copy all skills into a .skills folder in your project. After all skills are in the .skills folder, you can reference them individually based on your needs. For example:
"Read @.skills/bloc/SKILL.md and create test coverage for new methods."
Pro tip:
You can also configure your IDE to automatically load skills from this .skills folder, or reference them in prompts for specific guidance.
📏 No Opinions, Just Documentation
All rules are sourced from official documentation — no personal preferences or subjective interpretations. That’s intentional. You’re free to alter them to your taste, but this repo keeps things objective by sticking to the source.
Note: This might sometimes lead to contradictory rules (e.g., if one package suggests one folder architecture and another recommends a different one).
📌 Use Cases
- Install skills in your IDE for automatic, contextual assistance during development.
- Set up global rules for a Flutter project in your IDE.
- Configure project-specific constraints for popular state management packages.
- Provide clear expectations in a PRD when working with a team.
- Extract only what you need to avoid rule clutter.
- Reference individual skills or rules in prompts for specific guidance.
🛠️ Contributing
Contributions are welcome! If you'd like to suggest a new rule or improve an existing one, here’s how you can help:
- Fork this repository.
- Add or modify rules in the appropriate folder.
- Submit a pull request with a clear explanation of your changes.
Make sure to include an official documentation link for any rule set you’re adding or modifying to keep everything objective and reliable.
📚 References
Here are the official sources that have been used to build these rules:
Flutter
- Flutter App Architecture - Official Flutter architecture guidelines
- Flutter Common Errors - Common errors documentation
- Flutter ChangeNotifier State Management - Simple state management with ChangeNotifier
Dart
- Effective Dart - Official Dart style guidelines
- Dart 3 Updates - Documentation on Dart 3 features including:
State Management
- Bloc Library - Official Bloc library documentation
- Provider - Official Provider package documentation
- Riverpod - Official Riverpod documentation
Testing
Firebase
- Firebase for Flutter - Official Firebase Flutter documentation
- Code with Andrea - How to Setup Flutter & Firebase with Multiple Flavors using the FlutterFire CLI
📏 Recommended File Sizes by Tool
For each tool, the size guidance from its own official documentation for rule / instruction files and for SKILL.md skill files (accessed 2026-07-11).
| Tool | Rule file — recommended size | SKILL.md — recommended size |
|------|------------------------------|-------------------------------|
| Cursor | .mdc rule: under 500 lines (soft) | No numeric limit — "keep focused, move detail to separate files" |
| Windsurf | global_rules.md: 6,000 chars; .windsurf/rules/*.md: 12,000 chars/file (hard) | No numeric limit — "keeps your context window lean" |
| Claude Code | CLAUDE.md: under 200 lines (soft) | Under 500 lines (soft); description 1,536 chars (hard) |
| GitHub Copilot | copilot-instructions.md: ≤ 2 pages (soft, approx.) | Not supported — no repo-level SKILL.md |
| OpenAI Codex | AGENTS.md: no limit stated | Skill bundle: zip ≤ 50 MB, uncompressed file ≤ 25 MB, ≤ 500 files/version (no per-SKILL.md text limit) |
| Google Antigravity | rule file: 12,000 chars each (hard) | No numeric limit stated |
Notes:
- Hard = enforced/truncated at the limit; soft = a documented quality recommendation.
- Only Claude Code publishes a numeric
SKILL.mdlength recommendation (under 500 lines). Cursor, Windsurf, and Antigravity just say "keep it focused/lean" with no figure; OpenAI documents skill-bundle limits (50 MB zip / 25 MB per file / 500 files) rather than a text length; and GitHub Copilot has no repo-levelSKILL.md— it usescopilot-instructions.mdplus path-specific*.instructions.md(no size limit stated for the latter). - Claude Code loads
CLAUDE.mdin full regardless of length, but notes files over 200 lines "consume more context and reduce adherence"; its auto-memoryMEMORY.mdloads only the "first 200 lines or 25KB, whichever comes first." - Windsurf is still named Windsurf; its docs are served through Cognition (
docs.windsurf.com→docs.devin.ai) and reference.windsurf/rulesand.windsurf/skills. - This repo keeps the
combined/sets under 6,000 characters to satisfy the strictest hard limit above (Windsurfglobal_rules.md).
Official sources: Cursor — rules · skills | Windsurf — rules & skills | Claude Code — memory · skills | GitHub Copilot — instructions | OpenAI Codex — AGENTS.md · skills | Google Antigravity — rules · skills
Related Skills
claude-mem
113.5kPersistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Understand-Anything
90.9kGraphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
headroom
78.9kCompress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
CowAgent
47.8kOpen-source personal AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-agent, multi-model, multi-channel. Lightweight, extensible, one-line install.
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
