Run Tests Skill

SkillWeb & browsing

Run tests headless and return only failing test output. Accepts optional test filter patterns like gradle (e.g. /test *RankingGameTest)

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Run Tests Skill skill

What this skill tells your AI

The instructions your AI receives, as published by jvm-skills/jvm-skills in .junie/skills/test-gradle/SKILL.md and read by ahel’s review.

Run tests and report results. Does NOT fix failures — fix them inline in the calling context.

Argument handling

CRITICAL: Only add --tests flags if the user explicitly passed filter patterns. /test with NO arguments MUST run ALL tests — do NOT infer filters from branch name, recent changes, or context.

Examples:

  • /test./scripts/run-tests.sh (ALL tests, no filters)
  • /test *RankingGameSetupTest./scripts/run-tests.sh --tests "*RankingGameSetupTest"
  • /test *SetupTest *LobbyTest./scripts/run-tests.sh --tests "*SetupTest" --tests "*LobbyTest"

If the argument already contains --tests, pass it through as-is.

Instructions

  1. Run the test script (Bash tool, timeout 600000):

    ./scripts/run-tests.sh [--tests "pattern"]...
    
  2. Report the output as-is:

    • If output says "All tests passed." → report success, done.
    • If output shows "## Failed Tests" → report the failures verbatim. Do NOT fix them. Do NOT launch subagents. Return the raw failure output to the caller.

Signals

GitHub stars
138
Forks
26
Last commit
Aug 2026
Advanced
Catalog kind
skill
Gateway key
test-gradle
Source
github.com/jvm-skills/jvm-skills