presentation

A Flutter presentation-layer generator for screens and UI state. The presentation layer is the part of an app that displays data and responds to user actions without knowing how data is stored or fetched.

In plain words
What is it for?
Use it after repositories are implemented to create screens, reusable widgets, and state handling with Freezed and Riverpod.
Why use it?
It keeps screens separate from database and network details, making the UI structure easier to reason about and change.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/launch52-ai/flutter-template/presentation
Any agent
npx skills add launch52-ai/flutter-template --skill presentation
Clone the repo
git clone --depth 1 https://github.com/launch52-ai/flutter-template

Made for: Claude Code, Codex.

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,641 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00044 $0.01641
Opus 5 $0.00022 $0.00821
Sonnet 5 $0.00009 $0.00328
Haiku 4.5 $0.00004 $0.00164

Measured yesterday against content hash c0a4824c5579, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

presentation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/presentation/SKILL.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Presentation - Presentation Layer Generator

Generate presentation layer components that handle UI state and render screens using domain entities.

Philosophy

The presentation layer is domain-aware, data-blind:

  • Imports domain entities and repository interfaces
  • Never imports data layer (models, repository implementations)
  • Uses Freezed sealed states for exhaustive pattern matching
  • Uses Riverpod AsyncNotifier with disposal safety

This keeps the UI decoupled from data sources and serialization details.

When to Use This Skill

  • After /data has implemented repositories
  • When creating screens from spec requirements
  • When adding new screens or actions to existing features
  • User asks to "create screen", "implement UI", "add presentation layer"

What This Skill Creates

lib/features/{feature}/presentation/
├── providers/
│   ├── {feature}_state.dart         # Freezed sealed state
│   └── {feature}_notifier.dart      # AsyncNotifier with safe state
├── screens/
│   └── {feature}_screen.dart        # ConsumerWidget with pattern matching
└── widgets/
    └── {feature}_item.dart          # Extracted reusable widgets

Workflow

Step 1: Locate Requirements

Check for:

lib/features/{feature}/.spec.md           # Feature specification
lib/features/{feature}/domain/            # Domain entities
lib/features/{feature}/data/              # Repository implementation

If domain/data layers don't exist, ask user to run /domain and /data first.

Step 2: Analyze UI Requirements

From the spec, identify:

  • Screens - Section 4.1 (list, detail, form, etc.)
  • State Fields - What data each screen needs
  • Actions - User interactions (refresh, create, delete, submit)
  • Navigation - How screens connect

Step 3: Generate Code

Use reference files in reference/ directory as templates:

Component Reference File
List state reference/providers/list_state.dart
Detail state reference/providers/detail_state.dart
Form state reference/providers/form_state.dart
Basic notifier reference/providers/basic_notifier.dart
CRUD notifier reference/providers/crud_notifier.dart
Form notifier reference/providers/form_notifier.dart
List screen reference/screens/list_screen.dart
Detail screen reference/screens/detail_screen.dart
Form screen reference/screens/form_screen.dart
List item widget reference/widgets/list_item.dart
Form field widget reference/widgets/form_field.dart

Read the full file on GitHub · 197 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 197 lines · 44 tokens per session scan A c0a4824c5579

Subscribe to this mod's changes

presentation is a skill published in the GitHub repository launch52-ai/flutter-template (2 stars, last pushed 6mo ago), licensed MIT. It adds 44 tokens to every session and 1,641 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories