A collection of agent skills for AI assistants working with Dart and Flutter projects, implemented in the Agent Skills format — an open standard for extending AI agents.
Each skill provides structured knowledge based on official documentation, ready-to-use code examples, and detailed reference materials that AI agents can leverage.
This repository contains a set of specialized skills for Dart and Flutter development, organized according to the open Agent Skills standard.
What are Agent Skills?
Agent Skills are an open format for providing AI agents with new capabilities and expertise. They are structured folders with instructions, scripts, and resources that agents can discover and use to complete tasks more accurately and efficiently.
Created by: Anthropic Status: Open standard Supported by: Leading AI development tools
Skill composition
Each skill includes:
SKILL.md — skill description with metadata and usage conditions
Reference documentation — detailed guides in references/
Code examples — ready-to-use templates and examples in assets/
Best practices — recommendations and guidelines
Scripts (optional) — helper utilities in scripts/
What Agent Skills enable
✨ Domain expertise — specialized knowledge in specific areas
🚀 New capabilities — new abilities for agents
🔄 Repeatable workflows — standardized, repeatable workflows
🔗 Interoperability — reuse across different AI tools
Skills 🛠️
AGENTS.md Generator
Directory:agents-md-generator/
Description: Create or update minimal AGENTS.md files in the repository root and nested module directories using progressive disclosure. Works across heterogeneous projects without assuming any fixed agent folder structure.
When to use:
AGENTS.md is missing, bloated, contradictory, or outdated
A new package/service/module appears
Repository structure changes (monorepo growth or split)
Teams want consistent agent context across diverse stacks
Description: An operational workflow for adding, fixing, migrating, and validating Drift persistence in Dart CLI, server-side, and non-Flutter desktop apps.
When to use:
Adding local SQLite storage with package:drift/native.dart
Connecting server-side apps to PostgreSQL with drift_postgres
Writing type-safe tables, queries, writes, and reactive streams
Implementing and validating database schema migrations
Fixing build_runner, drift_dev, or generated-code failures
Key capabilities:
Setup with sqlite3, drift_postgres, and package:postgres
Defining tables and constraints
SELECT, WHERE, JOIN, aggregations
INSERT, UPDATE, DELETE, transactions
Reactive stream queries
Database schema migrations and generated migration tests
Deterministic smoke validation via scripts/verify-examples.sh
References:
setup.md — SQLite & PostgreSQL setup
postgres.md — PostgreSQL-specific features
tables.md — Table definitions
queries.md — Database queries
writes.md — Write operations
streams.md — Reactive streams
migrations.md — Schema migrations
Flutter Adaptive UI
Directory:flutter-adaptive-ui/
Description: Building adaptive and responsive Flutter UIs that work great across platforms and screen sizes.
When to use:
Building apps for multiple platforms (mobile, tablet, desktop, web)
Adapting layouts for different screen sizes
Supporting different input devices (touch, mouse, keyboard)
Implementing responsive navigation patterns
Optimizing for large screens and foldables
Using Capability and Policy patterns for platform-specific behavior
Key concepts:
3-step approach: Abstract → Measure → Branch
Breakpoints: Compact (<600), Medium (600-840), Expanded (≥840)
Layout rule: Constraints go down. Sizes go up. Parent sets position.
Capability/Policy pattern for platform-specific behavior
References:
layout-constraints.md — Constraints system with 29 examples
This repository follows the open Agent Skills format — a standard for giving AI agents new capabilities and expertise. Agent Skills are folders with instructions, scripts, and resources that agents can discover and use to complete tasks more accurately and efficiently.
Compatibility
Skills from this repository can be used by any AI assistants that support the Agent Skills format, including:
Anthropic Claude (with Agent Skills support)
Cursor IDE
Other compatible development tools
Benefits of Agent Skills
For skill authors:
Create a skill once and use it across many AI tools
Version control with Git
Portability across projects and teams
For teams and organizations:
Capturing organizational knowledge in a structured format