You're already using AI to write Flutter code. Now make it write code you trust. ACT is a structured workflow from spec to PR — where problems are caught early, not in the code review.
Early ACT users consistently mention more confidence, more control, and a workflow that catches problems before they become messy reviews.
Testimonial from Holger Matthies: I'm loving ACT. It's accelerating me and giving me more confidence, more control . Repeated review runs catch different critical findings, and that helps me turn a rough spec into something solid before implementation starts. The walkthrough reassured me that I'm using ACT as intended , and that alone made it worth the time. Thank you for ACT, it's truly making a difference .
Holger Matthies
Flutter developer
Testimonial from Zaya B: The installation process was easy and straightforward. The act:workflow pattern is excellent , and reading through the repository taught me a lot about setting up an AI coding environment. Overall I really liked this project. This really leveled up how I use AI .
Zaya B
Software Engineer
AI agents are great at following patterns and writing lots of code — when you give them the right structure. Without it, they infer missing requirements, make product decisions, and guess at your conventions, often going off-track. AI is a multiplier — of whatever process you give it. The speed is real. The confidence isn't.
AI follows local context. When conventions and decisions are not documented, patterns drift as features pile up.
The AI produces something, but you can't trust it without reading every line. That's not faster — it's just different work.
AI agents optimize for completion. They will chase green checks with brittle, shallow, or disabled tests that fail to protect real behavior.
Without a proper spec, the AI fills in the blanks with guesses. And you don't discover the wrong assumptions until the PR review.
AI agents write code that compiles. They don't write code that follows Flutter conventions — widget composition, proper state management, theme extensions, idiomatic patterns. You end up fighting the agents or rewriting by hand.
You solved this exact problem last week. But the context is gone and the AI has no memory of what worked. Without a way to capture and reuse insights, every session reinvents the wheel.
You describe what you want to build. The AI asks questions (rather than guessing) and writes a detailed specification, then a second pass tears it apart — finding gaps and wrong assumptions before a single line of code is written.
Then it builds phase by phase, committing as it goes. Tests lock in behavior and keep future runs aligned. And when you're done, you capture the insights so the next session starts smarter.
What if your AI agent actually worked this way?
Introducing the
Agentic Coding Toolkit (ACT) is a collection of commands, agents, skills, and a Flutter knowledge base that structures your AI-assisted development workflow — built to make spec-driven development practical, not theoretical.
ACT is fully open-source readable (markdown commands, skills, and knowledge files). It installs in two commands and works with any Flutter or Dart project — no modifications to your project structure.
Works with Claude Code and OpenCode — the two leading AI coding CLIs. You'll need one of these installed, along with your preferred LLM subscription or API key.
Watch ACT take a feature request through spec, plan, and execution, with each step committed along the way.
From spec to PR with guardrails at every step
You describe the feature. The AI asks clarifying questions and helps you iterate until all user flows, edge cases, and error scenarios are covered.
A second pass roasts the spec — looking for gaps, wrong assumptions, and misalignment with your existing codebase.
Turn the spec into a detailed multi-phase plan with actionable checklists, ready for implementation. Optional research agents gather Flutter patterns and inspect your codebase conventions.
The AI executes the plan phase by phase — making commits as it goes, running tests continuously, and creating a PR when done.
Capture reusable insights and decision patterns from the session. Next time, the knowledge is already there.
Six pillars that transform AI-assisted Flutter development from chaotic to predictable
AI works from detailed specs, not vague prompts. Each spec includes user flows, edge cases, and error scenarios — then gets adversarially reviewed for gaps before planning begins.
A repeatable cycle where each stage produces artifacts that feed the next. Spec to plan to implementation to knowledge capture — with guardrails at every step.
Tests are baked into implementation so behavior stays explicit and future agent runs stay on track. TDD-style guidance when it helps — without turning every task into ceremony.
Encode user journeys as robot-driven widget tests with stable selectors and deterministic test seams. Real user flows, not isolated unit checks.
10 principles. 15+ patterns. Breaking changes docs. Setup recipes. All loaded into every planning and implementation step — not as an afterthought, but as the foundation.
Conventional commits, automatic PR creation with smart descriptions, and full git worktree support for isolated parallel feature development.
Organized by the type of skill, plus supporting agents and the Flutter knowledge base.
| Skill | What it does |
|---|---|
/act-workflow-spec | Create detailed specifications with user flows, edge cases, and error scenarios |
/act-workflow-refine-spec | Adversarially review specs for gaps, wrong assumptions, and codebase misalignment |
/act-workflow-plan | Turn specs into phased implementation plans with codebase-aware context and TDD guidance |
/act-workflow-work | Execute plans phase-by-phase with auto commits, testing, and PR creation |
/act-workflow-compound | Capture reusable insights and decision patterns |
You're past tab-autocomplete. You've used Claude Code or OpenCode to build real features — and you've seen what happens when the AI works without guardrails. Architecture drifts. Tests pass for the wrong reasons. Every session starts from scratch.
You don't want to stop using AI. You want it to work your way — following your patterns, writing proper specs, and producing code you'd actually approve in a PR review.
Whether you're working solo or on a team, ACT gives you that structure.
This isn't for vibe coders. It's for engineers who care about what they ship.
Built for Flutter developers who want a structured, human-in-the-loop workflow with Claude Code or OpenCode. Early access pricing.
Best for AI coding on real projects that require testable and maintainable code.
Includes full toolkit access and updates while your subscription is active:
Best value if you want long-term updates with no renewals. One purchase, lifetime access.
Includes lifetime access to the full ACT toolkit and all future updates:
I've put a lot of care into making this toolkit genuinely useful and I'm confident you'll find it valuable.
But the only way to know if it's right for you is to try it. Get the toolkit, run the workflow on a real feature, and see the difference for yourself.
If you're not happy with it, for any reason, reach out via the contact page within 30 days and I'll issue a full refund within 24 hours.
About the Author
I'm a Flutter GDE and I've been writing code professionally for over 15 years. With my Flutter tutorials and courses, I've helped thousands of developers become better at building Flutter apps over at Code with Andrea.
The Agentic Coding Toolkit is the system I use daily to build Flutter apps with AI assistance — and now it's available to you.
Give your AI agent the guardrails, Flutter expertise, and structured workflow it needs to produce code you trust.