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.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

86%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 compact, well-structured instruction skill with concrete Gradle commands, clear Always/Ask-first/Never constraints, and a sequenced daily workflow with validation. Minor gaps: the Use Case example is partial and the test-failure feedback loop is implicit rather than spelled out.

Suggestions

Add a brief explicit feedback loop in the VERIFY step for when tests or ktfmtFormat fail (e.g., 'If formatting or tests fail, fix and re-run before proceeding to PRESENT').

Expand the DISTILL step's Use Case example into a small complete, copy-paste-ready snippet showing the `operator fun invoke()` body returning a predictable result, so the core extraction pattern is fully executable.

Optionally add a one-line pointer in Examples to a reference file for larger multi-Repository extractions, in case the skill later grows beyond the single-file scope.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's Kotlin/Android competence — it never explains what ViewModels, Repositories, or Use Cases are; sections are compact lists and one-line philosophy bullets with no padding.	5 / 5
Actionability	Provides concrete, executable commands (`./gradlew ktfmtFormat`, `lintDebug`, `testDebugUnitTest`) and specific patterns (`operator fun invoke()`, `class ValidatePasswordUseCase @Inject constructor()`, `ref:` commit format), but the Use Case implementation example is partial rather than fully copy-paste ready.	4 / 5
Workflow Clarity	The Daily Process is a clearly sequenced SCAN→SELECT→DISTILL→VERIFY→PRESENT flow with an explicit VERIFY checkpoint (run ktfmtFormat, run tests, confirm originals pass, require 100% coverage), but the error-recovery feedback loop (what to do when tests fail) is implicit rather than stated.	4 / 5
Progressive Disclosure	At ~44 lines with no external bundle files and well-organized sections (Goal, Constraints, Instructions, Examples), this single-file skill qualifies for the under-50-lines exception; the only referenced file (`.jules/distiller.md`) is a journal, not a nested skill reference.	5 / 5
	Total	18 / 20 Passed

Description

88%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 tightly written, third-person description that concretely states both what the skill does and when to use it, with strong domain-specific trigger language. The only gaps are a few commonly-used synonyms and a slight overlap risk with broader refactoring skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Extracts duplicated or tangled business logic ... into pure, highly testable Kotlin Use Cases', plus 'decouple Android dependencies', 'create domain-layer interactors', 'reduce ViewModel bloat' — comprehensive and specific rather than abstract.	5 / 5
Completeness	Explicitly answers both what ('Extracts duplicated or tangled business logic ... into ... Kotlin Use Cases') and when via a concrete trigger clause ('Use this skill to decouple Android dependencies from business rules, create domain-layer interactors, or reduce ViewModel bloat').	5 / 5
Trigger Term Quality	Strong natural terms ('ViewModel bloat', 'domain-layer interactors', 'Android dependencies') with synonyms (Use Cases/Interactors), but a few common phrases a user might say ('refactor', 'Clean Architecture', 'separation of concerns') are absent, so it sits just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	A clear, narrow niche (Kotlin/Android domain-layer extraction) with distinct triggers, but minor overlap risk with a general Kotlin refactoring or clean-architecture skill keeps it just below the minimal-conflict anchor.	4 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: nekomangaorg/Neko
Path: .agents/skills/distiller/SKILL.md
Commit: 9f8d94d

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

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.