Uloop Run Tests logo

Uloop Run Tests

Community
hatayama
uloop-run-tests

Run Unity Test Runner and report detailed results. Use for EditMode/PlayMode tests, change verification, or failure diagnosis.

Overview

Publisherhatayama
Repositoryunity-cli-loop
Skill nameuloop-run-tests
Stars
578
Forks
49
Bundled files
2
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by hatayama on GitHub. Read the source before you install it.

Installation

Install the Uloop Run Tests AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/hatayama/unity-cli-loop/tree/main/.agents/skills/uloop-run-tests
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/hatayama/unity-cli-loop.git /tmp/unity-cli-loop
mkdir -p .claude/skills
cp -r /tmp/unity-cli-loop/.agents/skills/uloop-run-tests .claude/skills/uloop-run-tests
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Uloop Run Tests in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Uloop Run Tests on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Uloop Run Tests is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

uloop run-tests

Execute Unity Test Runner. When a test or suite fails or a test ends inconclusive, NUnit XML results with failure messages, stack traces, and inconclusive reasons are automatically saved. Read the XML file at XmlPath for detailed diagnosis.

uloop run-tests automatically compiles pending script changes before running tests. Pass --skip-compile only while validating active hot-reload patches, because the compile clears those patches; otherwise let the default compile surface errors and run against current scripts. --skip-compile skips only the CLI-side compile: script edits saved since the last compile can still be imported during the run; such an import reloads the domain as soon as the run releases its assembly lock, discarding active patches and ending the request. While hot reload holds Auto Refresh (the state an apply leaves), a verified run kept the patches live. Check uloop hot-reload --status after the run instead of assuming either outcome.

Before executing tests, uloop run-tests handles unsaved loaded Scene and Prefab Stage changes according to --unsaved-changes (default save): save writes them first, fail stops if any remain, and discard reloads disk state so tests run against saved files. Untitled scenes cannot be discarded and fail. If the chosen mode cannot proceed, it returns Success: false, keeps TestCount at 0, lists the items in Message, and does not start the Unity Test Runner.

Active pause points are automatically cleared (the underlying code patches are removed as well) before test execution begins. Cleared IDs are reported in the response's ClearedPausePointIds field.

A test run can end by discarding active hot-reload changes: script edits imported during the run are compiled when the test runner releases its assembly-reload lock, and that deferred domain reload wipes the patches even though the tests themselves ran patched. The response's Warning field appears whenever changes were live when the run started and does not say whether they survived; check 'uloop hot-reload --status', then re-apply 'uloop hot-reload' or bake the edits in with 'uloop compile' before the next Play or test run.

NoTestsFound means zero tests matched — not a test failure. Check NoTestsFoundExplanation and Message for asmdef hints. When an unfiltered run finds no tests and the project has no test assembly for the TestMode, ProposedTestAsmdef carries a ready-to-write .asmdef: save Content at AssetPath, move the test scripts under that folder, then compile and rerun.

Status: Inconclusive means no test failed but at least one could not meet an Assume; Success is false, as Unity's batchmode test run also fails for it. InconclusiveTests names them with the assumption's message. A test that cannot run in this environment should call Assert.Ignore so it reports as skipped.

Usage

bash
uloop run-tests [options]

Parameters

ParameterTypeDefaultDescription
--test-modestringEditModeTest mode: EditMode, PlayMode
--filter-typestringallFilter type: all, exact, regex, assembly, class
--filter-valuestring-Filter value (test name, pattern, assembly, or class name)
--unsaved-changesstringsavesave writes unsaved Scene/Prefab Stage changes; fail stops if any remain; discard reloads disk state (Untitled scenes fail)
--skip-compileflag-Skip the CLI-side compile before running tests; use only while validating active hot-reload patches. Script edits saved since the last compile can still be imported during the run.
--timeout-secondsinteger600Maximum seconds to wait for RunFinished before canceling the await (max 1500). Increase for long suites; on timeout the Test Runner may still be running until stop handling lands
--respect-enter-play-mode-settingsflag-PlayMode only: keep the project's Enter Play Mode settings instead of forcing Domain Reload off. A Domain Reload during the run is survived; the result is recovered after the reload. Use for projects whose libraries require a Domain Reload on Play entry.
--rerun-failedflag-Rerun only the tests that failed or were inconclusive in the most recent completed run of the same --test-mode (whole fixtures for a failed OneTimeSetUp/OneTimeTearDown). Cannot be combined with --filter-type or --filter-value

By default PlayMode still forces Domain Reload off. With --respect-enter-play-mode-settings, a Domain Reload may run and the command takes longer; pause-point and hot-reload notes are omitted from a result recovered after reload. Canceling the CLI (Ctrl-C) does not stop the Unity-side run on this path.

exact matches the full test name (Namespace.Class.Method). class runs every test of one class by bare or namespace-qualified name, e.g. --filter-type class --filter-value PlayerTests; the name is matched literally and whole, so PlayerTests does not run EnemyPlayerTests. regex matches a .NET regex against full test names, e.g. --filter-type regex --filter-value '^MyGame.Tests.'

--rerun-failed reads the record that every completed run writes for its test mode, so it reruns the failures of the most recent completed run, filtered or not. A run that timed out or was cancelled leaves no record. With nothing recorded as failed it returns Status: NothingToRerun without running; to tell a flaky test from a real failure, run --rerun-failed again after a failure.

Output

Returns JSON. Success, Status, Message, FailedTests (up to 10), and XmlPath (set when a test or suite failed or was inconclusive) are usually enough; every field is described in references/response-fields.md, and the XML file in references/xml-results.md.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Uloop Run Tests AI skill do?

Run Unity Test Runner and report detailed results. Use for EditMode/PlayMode tests, change verification, or failure diagnosis.

Why use Uloop Run Tests on TypingMind?

Because you install it once and use it with any model. Uloop Run Tests is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Uloop Run Tests in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/hatayama/unity-cli-loop/tree/main/.agents/skills/uloop-run-tests. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Uloop Run Tests?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Uloop Run Tests?

As many as you like. As long as a model supports skills, you can use Uloop Run Tests with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Uloop Run Tests AI skill free?

Yes. It is published on GitHub by hatayama under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇