███████╗██╗     ██╗   ██╗████████╗████████╗███████╗██████╗
██╔════╝██║     ██║   ██║╚══██╔══╝╚══██╔══╝██╔════╝██╔══██╗
█████╗  ██║     ██║   ██║   ██║      ██║   █████╗  ██████╔╝
██╔══╝  ██║     ██║   ██║   ██║      ██║   ██╔══╝  ██╔══██╗
██║     ███████╗╚██████╔╝   ██║      ██║   ███████╗██║  ██║
╚═╝     ╚══════╝ ╚═════╝    ╚═╝      ╚═╝   ╚══════╝╚═╝  ╚═╝
██████╗ ███████╗██╗   ██╗███████╗██╗      ██████╗ ██████╗ ███████╗██████╗
██╔══██╗██╔════╝██║   ██║██╔════╝██║     ██╔═══██╗██╔══██╗██╔════╝██╔══██╗
██║  ██║█████╗  ██║   ██║█████╗  ██║     ██║   ██║██████╔╝█████╗  ██████╔╝
██║  ██║██╔══╝  ╚██╗ ██╔╝██╔══╝  ██║     ██║   ██║██╔═══╝ ██╔══╝  ██╔══██╗
██████╔╝███████╗ ╚████╔╝ ███████╗███████╗╚██████╔╝██║     ███████╗██║  ██║
╚═════╝ ╚══════╝  ╚═══╝  ╚══════╝╚══════╝ ╚═════╝ ╚═╝     ╚══════╝╚═╝  ╚═╝

⚡ Flutter Developer

Agent skills that help developers write, structure, research and maintain Dart and Flutter code to the official guidance.

imageValidate skills imageLicense: MIT imageAgent skills imageFormat imageTooling

Table of contents:

• Skills
• How they fit together
• Install
• Usage
• Validate
• Layout
• Status and limits

Important

Principle: follow the official Dart and Flutter guidance, verify against the real code before changing it, and make the smallest correct change.

These skills turn the Dart team's Effective Dart guide, the Flutter team's architecture and theming guidance, the Django REST Framework and Simple JWT documentation, and the GNU Make manual into short, reasoned rules an agent can apply. Each rule carries its reason, so it still works when a situation is not named. They follow the open Agent Skills format and work in Claude Code, Codex, Cursor, Copilot, OpenCode or any SKILL.md-compatible agent.

🧩 Skills

🗺️ How they fit together

flowchart TD
    R["⚡ flutter-developer<br/>routes work and enforces shared guardrails"]
    R --> A["🧹 dart-code-standards<br/>Effective Dart style, usage and API design"]
    R --> B["🏗️ flutter-architecture<br/>layers, MVVM, repositories, testing"]
    R --> W["🧱 flutter-widget-fundamentals<br/>widgets, state, keys, layout, forms"]
    R --> C["🔍 flutter-task-research<br/>research-only investigation"]
    R --> D["📋 flutter-tech-debt-plan<br/>scored remediation plans"]
    R --> F["🔌 flutter-django-integration<br/>Django REST API client, auth, errors, pagination"]
    R --> G["🎨 flutter-design-system<br/>themes, design tokens, accessibility"]
    R --> E["🛠️ make-automation<br/>Makefiles for build and test commands"]
    R --> H["⬆️ flutter-migration<br/>SDK upgrades and breaking-change fixes"]

Most work starts at the router. Research comes before a change that needs understanding, and standards and architecture apply while the change is written.

📦 Install

Tip

Install the router skill plus every sibling skill it links to; routers reference siblings by relative path.

Claude Code plugin (installs the skills together):

/plugin marketplace add KinwiseNZ-DevOps/flutter-developer
/plugin install flutter-developer@flutter-developer-marketplace

ChatGPT desktop plugin (local, skills and bundled hooks):

This repo has a portable plugin.json manifest and a repo marketplace at .agents/plugins/marketplace.json. Open this repo as a trusted project and restart ChatGPT desktop, then install Flutter Developer from the Plugins Directory. Review and trust bundled hook scripts before they run.

For best results also install the optional companions flutter-optimiser (performance) and django-api-architect (Django server code). The integration skill names the exact companion skill to use for each concern.

Or copy or symlink the skills/ subfolders you want into your agent's skills directory:

Always on

In Claude Code, Flutter Developer loads a short ruleset into every session as soon as the plugin is installed (official Dart and Flutter guidance, smallest change, honest verification). It tells you its state at the start of each session and costs roughly 450 tokens.

• Say "stop flutter mode" to pause it for the current session, and "start flutter mode" to resume.
• Ask Claude to set the saved mode to on, off or auto. It writes that word into ~/.claude/.flutter-developer.mode. You can also edit that file yourself, and deleting it returns to the default (on).
• It needs Node on the machine, because the start-up hook runs a small Node script. Without Node the hook quietly does nothing.
• Other agents have no start-up hook here. Paste skills/flutter-developer/references/always-on-rules.md into that agent's instruction file instead.

Safety checks

The same hooks run a few checks while you work. Each one only asks, warns or adds a reminder; none changes your files on its own.

Switch any check with ~/.claude/.flutter-developer.features.json, for example {"packageGuard": false, "sessionLog": true}, or ask Claude to write it. The saved mode (on, off or auto) applies to every check. If several of these plugins are installed, each risky action is checked once, not once per plugin.

Privacy: packageGuard and licenseGuard send package names, and linkGuard sends the links it checks, to the public registry or site. Nothing else leaves your machine. Turn those checks off if that is a concern.

🚀 Usage

Tip

You never need to memorise skill names. Just describe the problem in plain words; the router picks the right skill automatically. But if you want short, reliable phrases that always work, use these:

The flow (this is all most people need):

1. "Research how this feature works"   → a verified research note, no code changes
2. "Make this change"                  → smallest correct change, then format, analyse and test
3. "Review this against Dart style"    → rule-by-rule findings with reasons

Short phrases that trigger each skill:

Note

Skills also trigger on their own when your request matches. In Claude Code you can also invoke one explicitly with /flutter-developer, but the plain phrases above are shorter and work across every agent.

✅ Validate

python scripts/skills_tool.py check

Checks: frontmatter, name/folder match, description length and trigger, body under 500 lines, every relative link resolves (including README.md and AGENTS.md), agent profile naming with no more than two profiles per host and exactly one -workflow main agent, agent skills: entries that exist and no skills/<name>/SKILL.md paths in agent bodies, plugin manifests (.claude-plugin/plugin.json and marketplace.json: required fields, licence matches LICENSE, agents lists every Claude Code profile, no top-level agents/ folder), at least 3 eval cases per skill, catalogue freshness, no project-specific terms from reference-content/strip-terms.txt, and no em or en dashes in file names or in any text outside reference-content/. After the starter skill is deleted it also rejects leftover placeholders and setup-only paths that are tracked by Git or not ignored. Stdlib only, no dependencies.

🗂️ Layout

Repository layout

skills/<name>/SKILL.md      one folder per skill (+ references/ where needed)
.claude-plugin/             plugin.json and marketplace.json (Claude Code plugin)
hooks/                      always-on rules and safety checks for Claude Code
evals/cases.jsonl           3+ behavioural cases per skill
resources/agents/           optional host profiles copied by installer
scripts/install_agents.py   copy optional agent profiles into a project
scripts/skills_tool.py      validate, regenerate catalogue (stdlib only)
.github/workflows/          CI runs `skills_tool.py check` (free on public repos)
AGENTS.md                   agent-facing rules for this repo

📌 Status and limits

Note

• Architecture advice keeps the Flutter team's priority labels (Strongly recommend, Recommend, Conditional) and is meant to be adapted, not applied blindly.
• The Django integration skill covers the Flutter client only; server code belongs to the backend. Advice not stated by an official page is marked as inference in the skill references.
• Performance profiling and optimisation are out of scope here. The skills hand off to the flutter-optimiser plugin (flutter-performance-specialist) and, for server code, to the django-api-architect plugin, when those are installed. Without them the skills still work and say the hand-off was skipped.
• No agent profiles are supplied yet; the skills run directly in any compatible agent.
• Licensed under MIT (see LICENSE).

⚡ Built on the Agent Skills open format · grounded in Effective Dart and the Flutter architecture guide