CtrlK
BlogDocsLog inGet started
Tessl Logo

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

62

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/flutter-init/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

62%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with an excellent validation-driven workflow, but it is noticeably verbose and over-inlined relative to its own progressive-disclosure budget, pushing material that belongs in setup-guide.md into the main file.

Suggestions

Move the full interactive questionnaire (Step 1 dialog) and the per-preset feature checklists into references/setup-guide.md, leaving SKILL.md with a compact prompt skeleton.

Trim the body toward its stated ~150-line ceiling by relocating the error-fix catalog (Step 3.9b) and Android desugaring snippet to the reference, keeping only a one-line pointer.

De-duplicate the preset/feature lists, which currently appear in both Step 1 and the Notes section.

DimensionReasoningScore

Conciseness

At ~308 lines the body is roughly double its own stated ~150-line max, inlining a full Korean questionnaire and preset checklists that duplicate the Notes section and clearly belong in references/setup-guide.md.

2 / 5

Actionability

Provides concrete, mostly copy-paste-ready commands (flutter create, build_runner, flutter analyze) and a real Gradle desugaring snippet plus specific error fixes (sealed class, CardThemeData, package: imports), with minor gaps where domain code generation is described rather than shown.

4 / 5

Workflow Clarity

Steps 1-4 are clearly sequenced with an explicit validation feedback loop ('flutter analyze' -> fix errors -> re-run until 0-1 issues), CRITICAL checkpoints, and a checklist of common fixes for a batch generation operation.

5 / 5

Progressive Disclosure

The single reference (references/setup-guide.md) is clearly signaled and one level deep, but far too much detail (the interactive dialog, full preset tables, error-fix catalog) is inlined in SKILL.md rather than moved to the reference, violating its own disclosure guideline.

3 / 5

Total

14

/

20

Passed

Description

82%Weight 40%Scale 1-5

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 is explicit, third-person, and clearly answers both what and when with concrete trigger terms and a distinct niche. Its only weakness is that the action set is essentially a single verb ('create') rather than multiple concrete operations.

DimensionReasoningScore

Specificity

Names the domain ('create a new Flutter project') and concrete stack details (Clean Architecture, Riverpod 3.0, Drift) but the only real action verb is 'create'; coverage is not comprehensive enough for a 4.

3 / 5

Completeness

Explicitly states both what ('create a new Flutter project ... with Clean Architecture, Riverpod 3.0, Drift') and when ('Use when user wants to create a new Flutter project') with concrete trigger phrasing.

5 / 5

Trigger Term Quality

'create a new Flutter project' is a natural phrase users say, with 'Flutter' and the domain list (Todo/Habit/Note/Expense) giving good keyword coverage, though minor variations like 'Flutter app' are absent.

4 / 5

Distinctiveness Conflict Risk

A clear niche (Flutter scaffolding with specific domains and stack) with distinct triggers and minimal overlap risk against other skills.

5 / 5

Total

17

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
bear2u/my-skills
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.