quality-test-pilot

Writes high-quality unit tests for Kotlin Android codebases to increase meaningful test coverage. Use this skill to add tests for untested edge cases, ViewModel states, exception handling blocks, or UseCases using MockK, runTest, and the Given-When-Then pattern.

Quality

88%

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

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 instruction skill with a clear validated workflow and tidy sectioning. The main improvement opportunity is trimming the motivational philosophy bullets for token efficiency and adding one complete executable test example.

Suggestions

Remove or compress the 'Philosophy' bullets ('Untested code is broken code', etc.) — these restate testing principles Claude already knows and add tokens without actionable guidance.

Add one complete, copy-paste-ready MockK + runTest unit test example in the Examples section so BUILD is fully executable rather than pattern-described.

Consider collapsing the emoji-laden 'Always/Ask first/Never' headers into tighter bullet groups to reduce visual/token overhead while preserving the guardrails.

Dimension	Reasoning	Score
Conciseness	Mostly lean and well-organized, but the 'Philosophy' bullets ('Untested code is broken code', 'A failing test is a feature') are motivational padding Claude already knows and could be trimmed; not enough to drop to 3.	4 / 5
Actionability	Provides concrete commands (`./gradlew ktfmtFormat`, `./gradlew testDebugUnitTest --tests ...`), specific patterns (mockk(), runTest, given-when-then test naming, `test:` PR prefix); minor gap is the absence of a full copy-paste test example.	4 / 5
Workflow Clarity	SCAN/SELECT/BUILD/VERIFY/PRESENT is a clear sequence with an explicit validation checkpoint (VERIFY runs ktfmtFormat and the specific test, and applies a mutation-testing fail-then-pass check), plus Always/Ask first/Never guardrails.	5 / 5
Progressive Disclosure	Under 50 lines with no external references needed; content is cleanly partitioned into Goal, Constraints, Instructions, and Examples sections, satisfying the simple-skill exception for progressive disclosure.	5 / 5
	Total	18 / 20 Passed

Description

92%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 states capability and trigger conditions for Kotlin Android unit testing. Minor synonym coverage gaps in trigger terms keep it just short of a perfect profile.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions across distinct code targets ('untested edge cases, ViewModel states, exception handling blocks, or UseCases') plus specific tooling (MockK, runTest, Given-When-Then), giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers what ('Writes high-quality unit tests for Kotlin Android codebases to increase meaningful test coverage') and when ('Use this skill to add tests for untested edge cases, ViewModel states...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural terms like 'unit tests', 'Kotlin Android', 'edge cases', 'ViewModel', and 'test coverage' are present; a few common synonyms (e.g. 'test cases', 'mocking') are missing, so it is not quite fully comprehensive.	4 / 5
Distinctiveness Conflict Risk	The Kotlin/Android + MockK/runTest/Given-When-Then niche is narrow with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	19 / 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/test pilot/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.