CtrlK
BlogDocsLog inGet started
Tessl Logo

domain-distiller

Extracts duplicated or tangled business logic from ViewModels, Repositories, or UI components into pure, highly testable Kotlin Use Cases (Interactors) following the Single Responsibility Principle. Use this skill to decouple Android dependencies from business rules, create domain-layer interactors, or reduce ViewModel bloat.

71

Quality

86%

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%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.

A well-structured, actionable refactoring skill with a clear validated workflow and good token efficiency. Could improve by including one complete executable Use Case example and trimming the persona flourishes.

Suggestions

Add one complete, copy-paste-ready Use Case example (class + operator fun invoke + a matching unit test) to lift actionability from 4 to 5.

Trim the 'The Distiller ⚗️' persona framing and redundant Philosophy bullets to tighten conciseness.

Optionally split the worked example and DI-binding details into a reference file to make progressive disclosure explicit rather than implicit.

DimensionReasoningScore

Conciseness

Mostly lean and assumes Claude's competence (no basic-concept explanations), with minor non-essential flair ('The Distiller ⚗️' persona and philosophy bullets) that could be trimmed.

4 / 5

Actionability

Provides concrete commands and patterns ('./gradlew ktfmtFormat', 'class ValidatePasswordUseCase @Inject constructor()', 'operator fun invoke()', 'ref: ...') but lacks a complete copy-paste example covering a common case end-to-end.

4 / 5

Workflow Clarity

Clear 5-step sequence (SCAN, SELECT & PROPOSE, DISTILL, VERIFY, PRESENT) with explicit validation checkpoints (ktfmtFormat, lint, tests) and an approval gate plus fix-and-retry feedback loop for this code-modifying skill.

5 / 5

Progressive Disclosure

Single-purpose, ~45-line skill with well-organized sections and no need for bundle files; the one external reference ('.jules/distiller.md') is a one-level-deep, clearly signaled pointer.

5 / 5

Total

18

/

20

Passed

Description

87%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.

A strong, specific description that clearly answers both 'what' and 'when' with concrete Android-domain trigger phrases. Minor room to broaden trigger-term synonyms and enumerate more discrete concrete actions.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ('Extracts duplicated or tangled business logic', 'decouple Android dependencies', 'create domain-layer interactors', 'reduce ViewModel bloat'), with only minor coverage gaps versus the comprehensive multi-action anchor.

4 / 5

Completeness

Clearly states what it does (extracts logic into pure Kotlin Use Cases) and explicitly when to use it ('Use this skill to decouple... create... or reduce ViewModel bloat') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural phrases an Android developer would say ('ViewModel bloat', 'domain-layer interactors', 'Use Cases', 'decouple Android dependencies'), though slightly jargon-heavy and missing a few common synonyms.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (Kotlin Use Case / domain-layer extraction) with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

18

/

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
nekomangaorg/Neko
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.