flutter-init
Use when user wants to create a new Flutter project (Todo/Habit/Note/Expense/Custom domain) with Clean Architecture, Riverpod 3.0, Drift, and modern Flutter stack
68
59%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/flutter-init/SKILL.mdQuality
Discovery
72%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description has strong trigger terms and distinctiveness due to its specific tech stack (Riverpod 3.0, Drift, Clean Architecture), making it easy to identify when this skill should be selected. However, it lacks specificity about what concrete actions the skill performs beyond 'create a new Flutter project' - it should describe outputs like scaffolding folder structure, generating boilerplate, or configuring dependencies.
Suggestions
Add specific actions the skill performs, e.g., 'Scaffolds folder structure, generates repository/usecase boilerplate, configures Drift database, sets up Riverpod providers'
Expand the 'what' portion to describe deliverables: 'Creates production-ready Flutter project with layered architecture, pre-configured state management, and local database setup'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Flutter project creation) and lists technologies (Clean Architecture, Riverpod 3.0, Drift), but doesn't describe concrete actions like 'scaffolds folder structure', 'generates boilerplate code', or 'configures dependencies'. | 2 / 3 |
Completeness | Has a 'Use when' clause addressing when to trigger, but the 'what' is weak - it only says 'create a new Flutter project' without explaining what the skill actually does (generates files, scaffolds structure, etc.). | 2 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'Flutter project', 'Todo', 'Habit', 'Note', 'Expense', 'Clean Architecture', 'Riverpod', 'Drift'. Good coverage of both project types and technical stack terms. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche: Flutter + Clean Architecture + Riverpod 3.0 + Drift combination. Unlikely to conflict with generic Flutter skills or other architecture patterns due to the specific tech stack mentioned. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
47%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill has excellent workflow clarity with proper validation checkpoints and error recovery loops, but severely violates conciseness principles by being ~6x longer than recommended. The verbose domain descriptions and dialogue scripts explain concepts Claude already understands, wasting significant token budget. The content would benefit from aggressive trimming and moving detailed domain specifications to reference files.
Suggestions
Reduce the main skill to ~50-100 lines by moving domain field definitions and preset details to references/domains.md and references/presets.md
Remove explanatory text about what each domain type is (Todo, Habit, etc.) - Claude understands these concepts
Condense the dialogue script to a simple list of required inputs rather than full conversational templates
Add 1-2 concrete Dart code examples showing what generated files look like (e.g., a sample Freezed entity or Riverpod provider)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~300 lines with extensive explanations of domain options, step-by-step dialogue scripts, and repeated information. The skill explains concepts Claude already knows (what Todo/Habit apps are, what CRUD means) and includes lengthy preset descriptions that could be condensed significantly. | 1 / 3 |
Actionability | Provides concrete bash commands and clear step sequences, but lacks executable code examples for the actual generated files. The guidance is procedural rather than showing actual Dart code snippets that would be generated, making it harder to verify correctness. | 2 / 3 |
Workflow Clarity | Clear multi-step workflow with explicit validation checkpoints (flutter analyze), success/failure criteria, and a feedback loop for error correction. Step 3.8 explicitly requires fixing errors until analyze passes before proceeding. | 3 / 3 |
Progressive Disclosure | References setup-guide.md for detailed documentation, but the main file itself is a monolithic wall of text (~300 lines) that should be split. The comment at the bottom acknowledges it should be ~50 lines but the content violates this guideline significantly. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- bear2u/my-skills
- Commit
1be5394
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.