run-tests

Run a Gradle project's tests by test type or module — unit, integration, or all. Use this skill whenever the user wants to run, re-run, or check the project's tests (e.g. "run the unit tests", "run all tests", "run the integration tests for the vet module", "did the tests pass?").

Quality

90%

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.

The content is an efficient, well-structured overview that defers detail to real one-level-deep references and gives concrete task names plus a decision workflow. It could be tightened on actionability (full run steps live in references) and workflow clarity (no explicit failure-recovery loop in the body).

Suggestions

Add a short explicit error-recovery note in the body (e.g. 'if a path's reference reports failures, re-run the failing type/module or surface the failure to the user') to push workflow_clarity toward 5.

Inline one minimal concrete run command per path (e.g. a sample `:web:test` invocation) so the body is executable without opening a reference, improving actionability.

Dimension	Reasoning	Score
Conciseness	The body is lean: it never explains what Gradle or tests are, uses a compact table for task mapping, and every line (probe-first, IDE vs console branch, Haiku subagent collection) earns its place, matching the 5-anchor.	5 / 5
Actionability	Concrete guidance is present — specific Gradle tasks ('test', 'testIntgr', 'integrationTest', ':web:test') and a concrete tool call ('steroid_list_projects' via ToolSearch) — but the full execution steps are deferred to references, leaving minor gaps versus copy-paste-ready 5-anchor code.	4 / 5
Workflow Clarity	There is a clear sequenced workflow (probe → pick IDE/console path → run → collect report in a Haiku subagent → act on it) with a fallback branch, but the body lacks an explicit test-failure/error-recovery loop, so it sits at 4 rather than 5.	4 / 5
Progressive Disclosure	The body is a clear overview with well-signaled one-level-deep references ('references/ide.md', 'references/gradle.md', 'references/report.md'), each tied to a specific condition, and all referenced files exist in the bundle, matching the 5-anchor.	5 / 5
	Total	18 / 20 Passed

Description

95%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 well-crafted: it states a clear niche, gives concrete example trigger phrases a user would naturally say, and explicitly covers both what and when. The only minor gap is that the action verbs (run/re-run/check) are generic rather than enumerating many distinct concrete operations.

Dimension	Reasoning	Score
Specificity	Quotes 'Run a Gradle project's tests by test type or module — unit, integration, or all' and 'run, re-run, or check the project's tests' name the domain plus several concrete actions (run/re-run/check by type and module), but the verbs stay generic compared to the comprehensive multi-action 5-anchor example.	4 / 5
Completeness	Explicitly answers 'what' ('Run a Gradle project's tests by test type or module') and 'when' ('Use this skill whenever the user wants to run, re-run, or check the project's tests') with concrete trigger phrases, matching the 5-anchor.	5 / 5
Trigger Term Quality	Quotes natural user phrases like 'run the unit tests', 'run all tests', 'run the integration tests for the vet module', and 'did the tests pass?' give comprehensive coverage of how users actually phrase the request, matching the 5-anchor.	5 / 5
Distinctiveness Conflict Risk	The Gradle-specific, test-type/module framing carves a clear niche with distinct triggers and minimal overlap risk with general build or run-app skills, matching the 5-anchor.	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: Amplicode/spring-skills
Path: skills/run-tests/SKILL.md
Commit: bf19b3c

Reviewed: 5 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.