Testdriver:Options logo

Testdriver:Options

Organization
testdriverai
testdriver:options

Every option you can pass to the TestDriver client, with defaults and examples

Overview

Publishertestdriverai
Repositorytestdriverai
Skill nametestdriver:options
Stars
465
Forks
39
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Testdriver:Options 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/testdriverai/testdriverai/tree/main/ai/skills/testdriver-options
  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/testdriverai/testdriverai.git /tmp/testdriverai
mkdir -p .claude/skills
cp -r /tmp/testdriverai/ai/skills/testdriver-options .claude/skills/testdriverai-testdriver-options
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Testdriver:Options 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 Testdriver:Options 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 Testdriver:Options 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.

Overview

You configure the SDK with an options object. You can pass the object in three places:

javascript
// 1. Vitest hook (most common)
const testdriver = TestDriver(context, { os: "windows" });

// 2. Constructor
const testdriver = new TestDriver(apiKey, { os: "windows" });

// 3. Global plugin options in vitest.config.mjs
testdriver({ os: "windows" })

The hook merges the options in this order. A later source replaces an earlier source:

  1. Default values
  2. Environment variables (TD_OS, TD_API_ROOT, TD_E2B_TEMPLATE_ID)
  3. Global plugin options
  4. Options that you pass to the hook or the constructor

Options that you pass to connect() replace the constructor values for that connection only.

Sandbox

These options control the virtual machine that runs your test.

When reconnect is true, the SDK skips provision methods (chrome, vscode, installer, and others). The application is already running. The previous sandbox must still be alive. See keepAlive and the Run guide.

Example

javascript
const testdriver = TestDriver(context, {
  os: "windows",
  resolution: "1920x1080",
  keepAlive: 300000,
  debugOnFailure: true,
});

Preview and recording

These options control what you see while the test runs.

  • "browser" opens the debugger in your default browser.
  • "ide" opens the preview in the IDE panel. This mode needs the TestDriver extension for VS Code or Cursor.
  • "none" runs without a visual preview. Use this in CI.

The file name format is <seq>-<action>-<phase>-L<line>-<description>.png. Example: 001-click-before-L42-submit-button.png. See Debugging with screenshots.

Example

javascript
const testdriver = TestDriver(context, {
  preview: process.env.CI ? "none" : "browser",
  autoScreenshots: true,
});

AI and element location

These options control how the AI locates elements and checks assertions.

You can replace this value for one call with find(description, { verify: true }). See find.

<ParamField path="top" type="object">
  Nucleus and top-k sampling parameters.

  <Expandable title="properties">
    <ParamField path="p" type="number">
      Top-P (nucleus sampling). Limits token choices to the smallest set whose total probability is more than P. Lower values give more focused responses. Range: 0 to 1.
    </ParamField>

    <ParamField path="k" type="number">
      Top-K sampling. Limits token choices to the K most likely tokens. `1` always picks the most likely token. `0` disables the limit.
    </ParamField>
  </Expandable>
</ParamField>

Example

javascript
const testdriver = TestDriver(context, {
  verify: true,
  ai: { temperature: 0, top: { p: 0.9, k: 40 } },
});

Caching

These options control the element cache. The cache stores the position of an element after the first find(). Later runs reuse the position when the screen has not changed. See Caching.

<ParamField path="thresholds" type="object">
  Fine-tune the cache matching.

  <Expandable title="properties">
    <ParamField path="find" type="object">
      Thresholds for `find()` operations.

      <Expandable title="properties">
        <ParamField path="screen" type="number" default="0.05">
          The pixel diff threshold for the screen comparison (0 to 1). `0.05` allows a 5% difference.
        </ParamField>

        <ParamField path="element" type="number" default="0.8">
          The OpenCV template match threshold for the element (0 to 1). `0.8` requires an 80% correlation.
        </ParamField>
      </Expandable>
    </ParamField>

    <ParamField path="assert" type="number" default="0.05">
      The pixel diff threshold for `assert()` operations (0 to 1). `0.05` allows a 5% difference.
    </ParamField>
  </Expandable>
</ParamField>

Example

javascript
const testdriver = TestDriver(context, {
  cache: {
    enabled: true,
    thresholds: {
      find: { screen: 0.05, element: 0.8 },
      assert: 0.05,
    },
  },
  cacheKey: "login-test",
});

Redraw detection

These options control how the SDK waits for the screen to settle after an action. See Redraw.

<ParamField path="thresholds" type="object">
  Threshold configuration.

  <Expandable title="properties">
    <ParamField path="screen" type="number | false" default="0.05">
      The pixel diff threshold (0 to 1). Set to `false` to disable screen redraw detection.
    </ParamField>

    <ParamField path="network" type="boolean" default="false">
      Wait for network activity to stop.
    </ParamField>
  </Expandable>
</ParamField>

Example

javascript
const testdriver = TestDriver(context, {
  redraw: {
    thresholds: { screen: 0.1, network: true },
  },
});

Self-hosted and infrastructure

Most users do not need these options. Use them for self-hosted or custom deployments.

Quick reference

OptionTypeDefault
os'linux' | 'windows''linux'
resolutionstring'1366x768'
newSandboxbooleantrue
reconnectbooleanfalse
sandboxIdstring—
keepAlivenumber60000
debugOnFailurebooleanfalse
environmentobject—
preview'browser' | 'ide' | 'none''browser'
dashcambooleantrue
autoScreenshotsbooleanfalse
loggingbooleantrue
analyticsbooleantrue
verifybooleanfalse
aiobject—
cacheboolean | objecttrue
cacheKeystring—
redrawboolean | objecttrue
apiRootstringchannel default
ipstring—
sandboxAmistring—
sandboxInstancestring—
e2bTemplateIdstring—

Frequently asked questions

What does the Testdriver:Options AI skill do?

Every option you can pass to the TestDriver client, with defaults and examples

Why use Testdriver:Options on TypingMind?

Because you install it once and use it with any model. Testdriver:Options 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 Testdriver:Options in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/testdriverai/testdriverai/tree/main/ai/skills/testdriver-options. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Testdriver:Options?

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 Testdriver:Options?

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

Is the Testdriver:Options AI skill free?

It is published on GitHub by testdriverai. Check the repository for licensing terms. 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 👇