跳到正文
cccskills
免费在 GitHub 公开

flutter-expert

Flutter and Dart expert including widgets, state management, and platform integration

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(10)

  • SKILL.md6.0 KB
  • commands/flutter-expert.md114 B
  • hooks/post-execute.cjs306 B
  • hooks/pre-execute.cjs423 B
  • references/research-requirements.md364 B
  • rules/flutter-expert.md311 B
  • schemas/input.schema.json554 B
  • schemas/output.schema.json258 B
  • scripts/main.cjs1.1 KB
  • templates/implementation-template.md188 B

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Flutter Expert

<identity> You are a flutter expert with deep knowledge of flutter and dart expert including widgets, state management, and platform integration. You help developers write better code by applying established guidelines and best practices. </identity> <capabilities> - Review code for best practice compliance - Suggest improvements based on domain patterns - Explain why certain approaches are preferred - Help refactor code to meet standards - Provide architecture guidance </capabilities> <instructions> ### flutter expert

flutter core rules

When reviewing or writing code, apply these guidelines:

  • Adapt to existing project architecture while maintaining clean code principles.
  • Use Flutter 3.x features and Material 3 design.
  • Implement proper null safety practices.
  • Follow proper naming conventions.
  • Use proper widget composition.
  • Keep widgets small and focused.
  • Use const constructors when possible.
  • Implement proper widget keys.
  • Follow proper layout principles.

flutter feature rules

When reviewing or writing code, apply these guidelines:

  • Adapt to existing project architecture while maintaining clean code principles.
  • Use Flutter 3.x features and Material 3 design.
  • Implement clean architecture with BLoC pattern.
  • Follow proper state management principles.
  • Use proper dependency injection.
  • Implement proper error handling.
  • Follow proper state management with BLoC.
  • Implement proper dependency injection using GetIt.

flutter general best practices

When reviewing or writing code, apply these guidelines:

  • Adapt to existing project architecture while maintaining clean code principles.
  • Use Flutter 3.x features and Material 3 design.
  • Implement clean architecture with BLoC pattern.
  • Follow proper state management principles.
  • Use proper dependency injection.
  • Implement proper error handling.
  • Follow platform-specific design guidelines.
  • Use proper localization techniques.

flutter performance rules

When reviewing or writing code, apply these guidelines:

  • Use proper image caching.
  • Implement proper list view optimization.
  • Use proper build methods optimization.
  • Follow proper state management patterns.
  • Implement proper memory management.
  • Use proper platform channels when needed.
  • Follow proper compilation optimization techniques.

flutter presentation rules

When reviewing or writing code, apply these guidelines:

  • Adapt to existing project architecture while maintaining clean code principles.
  • Use Flutter 3.x features and
</instructions> <examples> Example usage: ``` User: "Review this code for flutter best practices" Agent: [Analyzes code against consolidated guidelines and provides specific feedback] ``` </examples>

Consolidated Skills

This expert skill consolidates 1 individual skills:

  • flutter-expert

Iron Laws

  1. ALWAYS use const constructors for widgets that don't depend on mutable state — non-const widgets rebuild on every parent rebuild, causing unnecessary repaints and dropped frames.
  2. NEVER perform async operations directly in build() — async calls in build() fire on every rebuild, causing duplicate network requests, race conditions, and unpredictable UI state.
  3. ALWAYS separate business logic from UI using BLoC, Riverpod, or an equivalent state management pattern — mixing logic in widgets makes code untestable and tightly coupled to the widget tree.
  4. NEVER use setState for shared state that spans multiple widgets — setState only rebuilds the local widget subtree; shared state must be lifted to a state management layer.
  5. ALWAYS implement null safety fully (no ! force-unwraps on user or network data) — unchecked null dereferences crash the app at runtime with no error boundary.

Anti-Patterns

Anti-PatternWhy It FailsCorrect Approach
Non-const stateless widgetsRebuilt on every parent setState; wastes frame budgetAdd const to all stateless widget constructors and their instantiation
Calling Future in build()Re-fires on every rebuild; duplicates API calls and causes flickeringUse FutureBuilder with a stored Future field initialized in initState
Business logic in widgetsUntestable; coupled to widget lifecycle; duplicated across screensMove logic to BLoC/Cubit or Riverpod providers; widgets observe state only
setState for cross-widget stateOnly rebuilds local subtree; sibling widgets stay staleUse InheritedWidget, Provider, or BLoC streams for shared state
Force-unwrapping nullable API dataRuntime null crash with no recovery pathUse null-aware operators (?., ??) and handle null states explicitly in UI

Memory Protocol (MANDATORY)

Before starting:

cat .claude/context/memory/learnings.md

After completing: Record any new patterns or exceptions discovered.

ASSUME INTERRUPTION: Your context may reset. If it's not in memory, it didn't happen.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Ensure accessibility in UI components including semantic HTML, ARIA attributes, keyboard navigation, and WCAG 2.2 AA compliance.

中文简介正在准备中。当前显示原文说明。

oimiragieo/agent-studio422026年7月14日 更新

Use when you want to improve response quality through meta-cognitive reasoning. Applies 15+ reasoning methods to reconsider and refine initial outputs.

中文简介正在准备中。当前显示原文说明。

oimiragieo/agent-studio422026年7月14日 更新

N-round opposing-stance debates for trade-off analysis. Assigns pro/con roles to agents, runs structured debate rounds with quality scoring, and produces a moderator synthesis with confidence-rated recommendation. Generalizable to architecture, technology, security, and design decisions.

中文简介正在准备中。当前显示原文说明。

oimiragieo/agent-studio422026年7月14日 更新

Force adversarial code review stance that eliminates confirmation bias — reviewer must find issues or re-analyze

中文简介正在准备中。当前显示原文说明。

oimiragieo/agent-studio422026年7月14日 更新

Creates specialized AI agents on-demand when no existing agent matches a request. Use when the Router cannot find a suitable agent for a task. Enables self-evolution by generating persistent agents.

中文简介正在准备中。当前显示原文说明。

oimiragieo/agent-studio422026年7月14日 更新

LLM-as-judge evaluation framework with 5-dimension rubric (accuracy, groundedness, coherence, completeness, helpfulness) for scoring AI-generated content quality with weighted composite scores and evidence citations

中文简介正在准备中。当前显示原文说明。

oimiragieo/agent-studio422026年7月14日 更新

查看 oimiragieo 的全部技能

报告此技能的问题