Read information from the screen using AI and return it as a string
npx skills add https://github.com/testdriverai/testdriverai --skill testdriver:extract
<!-- Generated from extract.mdx. DO NOT EDIT. -->
Extract information from the current screen using AI and return it as a string. Describe what you want in natural language, and the AI reads the screen and returns the matching value — text, numbers, labels, status messages, or any other on-screen content.
Unlike assert(), which returns a boolean verdict, extract() returns the actual value so you can store it, compare it, or feed it into later steps and framework assertions.
const value = await testdriver.extract(description)
const value = await testdriver.extract({ description })
<ParamField path="description" type="string" required>
Natural language description of the information to read from the screen.
</ParamField>
<Info>
extract() also accepts an options object — extract({ description }) — which is equivalent to the positional form. The bare string form is the most common.
</Info>
Promise<string> — The information read from the screen. Returns the extracted value as text; parse or cast it yourself if you need a number or other type.
// 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');
// 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);
<Check>
Be specific about what to read
Precise descriptions produce cleaner values:
// ❌ 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');
</Check>
<Check>
Ask for the format you want
Steer the output by describing the desired shape in the prompt:
// 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');
</Check>
<Check>
Extract for detailed assertions
Use extract() when a boolean assert() isn't enough and you need the actual value to inspect:
const confirmation = await testdriver.extract('the confirmation number');
expect(confirmation).toMatch(/^ORD-\d{6}$/);
</Check>
<AccordionGroup>
<Accordion title="Capturing Confirmation Details">
const submitBtn = await testdriver.find('place order button');
await submitBtn.click();
// 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}`);
</Accordion>
<Accordion title="Reading Tooltip and Hover Content">
const icon = await testdriver.find('info icon next to the price');
await icon.hover();
const tooltipText = await testdriver.extract('the tooltip text');
expect(tooltipText).toContain('tax included');
</Accordion>
<Accordion title="Verifying Dynamic Values">
// Read a value before an action
const before = await testdriver.extract('the account balance');
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, ''))
);
</Accordion>
<Accordion title="Passing Data Between Steps">
// Read a generated code on one screen...
const resetCode = await testdriver.extract('the password reset code');
// ...and type it into the next
const codeField = await testdriver.find('reset code input');
await codeField.click();
await testdriver.type(resetCode);
</Accordion>
</AccordionGroup>
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);
});
});
<Note>
Like assertions, extract() reads the screen fresh on every call — it is not cached — so it always reflects the current state of the app.
</Note>
assert() - Verify screen state with a boolean AI judgmentfind() - Locate elements to interact withparse() - Detect all UI elements on screenIntegration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.
Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances
Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.
Build and distribute Expo development clients locally or via TestFlight
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.
Take testdriverai/testdriver:extract from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.