Testdriver:Extract logo

Testdriver:Extract

Organization
testdriverai
testdriver:extract

Read information from the screen using AI and return it as a string

Overview

Publishertestdriverai
Repositorytestdriverai
Skill nametestdriver:extract
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:Extract 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-extract
  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-extract .claude/skills/testdriverai-testdriver-extract
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Testdriver:Extract 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:Extract 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:Extract 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

Get information from the screen with AI. TestDriver returns it as a string. Describe what you want in natural language. The AI reads the screen and returns the correct value: text, numbers, labels, status messages, or other content on the screen.

assert() returns a boolean result. But extract() returns the real value. Thus you can store it, compare it, or use it in later steps and in framework assertions.

Syntax

javascript
const value = await testdriver.extract(description)
const value = await testdriver.extract({ description })

Parameters

Returns

Promise<string> — The information from the screen. TestDriver returns the value as text. Parse it or cast it yourself if you need a number or another type.

Examples

Basic Extraction

javascript
// Read text content
const title = await testdriver.extract('the page title');
const heading = await testdriver.extract('the main heading text');

// Read numbers and prices
const price = await testdriver.extract('the total price shown in the cart');
const count = await testdriver.extract('the number of items in the list');

// Read status and confirmation values
const status = await testdriver.extract('the order status');
const orderNumber = await testdriver.extract('the order confirmation number');

Using the Extracted Value

javascript
// Store and reuse across steps
const orderNumber = await testdriver.extract('the order confirmation number');
console.log('Order:', orderNumber);

// Combine with framework assertions
import { expect } from 'vitest';

const message = await testdriver.extract('the success message text');
expect(message).toContain('successfully');

// Cast to a number when you need to compare
const totalText = await testdriver.extract('the cart total as a number without currency symbol');
expect(Number(totalText)).toBeGreaterThan(0);

Best Practices

Precise descriptions produce cleaner values:

javascript
// ❌ Too vague — may return extra surrounding text
const price = await testdriver.extract('price');

// ✅ Specific — targets a single value
const price = await testdriver.extract('the total price in the order summary, digits only');

Steer the output by describing the desired shape in the prompt:

javascript
// Strip currency symbols
const total = await testdriver.extract('the order total as a number without the dollar sign');

// Isolate a single field
const email = await testdriver.extract('the email address shown in the profile header');

Use extract() when a boolean assert() isn't enough and you need the actual value to inspect:

javascript
const confirmation = await testdriver.extract('the confirmation number');
expect(confirmation).toMatch(/^ORD-\d{6}$/);

Use Cases

// Read the confirmation the app generated
const orderNumber = await testdriver.extract('the order confirmation number');
const eta = await testdriver.extract('the estimated delivery date');

console.log(`Order ${orderNumber} arrives ${eta}`);
```
const tooltipText = await testdriver.extract('the tooltip text');
expect(tooltipText).toContain('tax included');
```
const addBtn = await testdriver.find('add funds button');
await addBtn.click();

// Read it again after and compare
const after = await testdriver.extract('the account balance');
expect(Number(after.replace(/[^0-9.]/g, ''))).toBeGreaterThan(
  Number(before.replace(/[^0-9.]/g, ''))
);
```
// ...and type it into the next
const codeField = await testdriver.find('reset code input');
await codeField.click();
await testdriver.type(resetCode);
```

Complete Example

javascript
import { beforeAll, afterAll, describe, it, expect } from 'vitest';
import TestDriver from 'testdriverai';

describe('Extraction', () => {
  let testdriver;

  beforeAll(async () => {
    testdriver = new TestDriver(process.env.TD_API_KEY);
    await testdriver.auth();
    await testdriver.connect();
  });

  afterAll(async () => {
    await testdriver.disconnect();
  });

  it('should capture the order confirmation', async () => {
    await testdriver.focusApplication('Google Chrome');

    // Complete a checkout
    const checkoutBtn = await testdriver.find('checkout button');
    await checkoutBtn.click();

    const placeOrderBtn = await testdriver.find('place order button');
    await placeOrderBtn.click();

    // Verify we reached confirmation
    await testdriver.assert('the order confirmation page is displayed');

    // Extract the details the app generated
    const orderNumber = await testdriver.extract('the order confirmation number');
    const total = await testdriver.extract('the order total as a number without currency symbol');

    // Assert on the extracted values
    expect(orderNumber).toBeTruthy();
    expect(Number(total)).toBeGreaterThan(0);
  });
});

How It Works

  1. TestDriver captures a screenshot of the current screen
  2. The image and your description are sent to the TestDriver API
  3. The AI reads the requested information from the screenshot
  4. The extracted value is returned as a string

Related Methods

  • assert() - Verify screen state with a boolean AI judgment
  • find() - Locate elements to interact with
  • parse() - Detect all UI elements on screen

Frequently asked questions

What does the Testdriver:Extract AI skill do?

Read information from the screen using AI and return it as a string

Why use Testdriver:Extract on TypingMind?

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

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

Which AI models can use Testdriver:Extract?

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:Extract?

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

Is the Testdriver:Extract 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 👇