TerminaI examples

Not sure where to get started with TerminaI? This document covers examples on how to use TerminaI for a variety of tasks.

Note: Results are examples intended to showcase potential use cases. Your results may vary.

Rename your photographs based on content

Scenario: You have a folder containing the following files:

Terminal window

photos/photo1.pngphotos/photo2.pngphotos/photo3.png

Give Gemini the following prompt:

Rename the photos in my "photos" directory based on their contents.

Result: Gemini will ask for permission to rename your files.

Select Allow once and your files will be renamed:

Terminal window

photos/yellow_flowers.pngphotos/antique_dresser.pngphotos/green_android_robot.png

Explain a repository by reading its code

Scenario: You want to understand how a popular open-source utility works by inspecting its code, not just its README.

Give TerminaI the following prompt:

Clone the 'chalk' repository from https://github.com/chalk/chalk, read its key source files, and explain how it works.

Result: Gemini will perform a sequence of actions to answer your request.

First, it will ask for permission to run git clone to download the repository.
Next, it will find the important source files and ask for permission to read them.
Finally, after analyzing the code, it will provide a summary.

TerminaI will return an explanation based on the actual source code:

The `chalk` library is a popular npm package for styling terminal output withcolors. After analyzing the source code, here's how it works:
- **Core functionality:** The main file sets up a chainable API. Each color or  modifier (like `bold` or `italic`) is a getter that appends the corresponding  ANSI escape code to an internal stack.
- **Chainable API:** When you call `chalk.red.bold('Hello')`, you are accessing  getters. The `red` getter adds the red color code, and the `bold` getter adds  the bold code.
- **Output generation:** When the chain is treated as a string (e.g., in  `console.log`), a final `toString()` method is called. This method joins all  the stored ANSI codes, wraps them around the input string ('Hello'), and adds  a reset code at the end. This produces the final, styled string that the  terminal can render.

Combine two spreadsheets into one spreadsheet

Scenario: You have two .csv files: Revenue - 2023.csv and Revenue - 2024.csv. Each file contains monthly revenue figures, like so:

January,0February,0March,0April,900May,1000June,1000July,1200August,1800September,2000October,2400November,3400December,2100

You want to combine these two .csv files into a single .csv file.

Give TerminaI the following prompt:

Combine the two .csv files into a single .csv file, with each year a different column.

Result: TerminaI will read each file and then ask for permission to write a new file. Provide your permission and TerminaI will provide the following .csv:

Month,2023,2024January,0,1000February,0,1200March,0,2400April,900,500May,1000,800June,1000,900July,1200,1000August,1800,400September,2000,2000October,2400,3400November,3400,1800December,2100,9000

Run unit tests

Scenario: You’ve written a simple login page. You wish to write unit tests to ensure that your login page has code coverage.

Give TerminaI the following prompt:

Write unit tests for Login.js.

Result: TerminaI will ask for permission to write a new file and create a test for your login page

import React from 'react';import { render, fireEvent, waitFor } from '@testing-library/react';import Login from './Login';
// Mock the API call for loginjest.mock('./api', () => ({  login: jest.fn(),}));
describe('Login component', () => {  it('renders the login form correctly', () => {    const { getByLabelText, getByText } = render(<Login />);
    expect(getByLabelText('Username')).toBeInTheDocument();    expect(getByLabelText('Password')).toBeInTheDocument();    expect(getByText('Login')).toBeInTheDocument();  });
  it('shows an error message with invalid credentials', async () => {    const { getByLabelText, getByText, findByText } = render(<Login />);    const usernameInput = getByLabelText('Username');    const passwordInput = getByLabelText('Password');    const loginButton = getByText('Login');
    // Mock the API to return an error    require('./api').login.mockRejectedValue(new Error('Invalid credentials'));
    fireEvent.change(usernameInput, { target: { value: 'testuser' } });    fireEvent.change(passwordInput, { target: { value: 'wrongpassword' } });    fireEvent.click(loginButton);
    const errorMessage = await findByText('Invalid credentials');    expect(errorMessage).toBeInTheDocument();  });
  it('logs in successfully with valid credentials', async () => {    const onLoginSuccess = jest.fn();    const { getByLabelText, getByText } = render(      <Login onLoginSuccess={onLoginSuccess} />,    );    const usernameInput = getByLabelText('Username');    const passwordInput = getByLabelText('Password');    const loginButton = getByText('Login');
    // Mock the API to return a success message    require('./api').login.mockResolvedValue({ success: true });
    fireEvent.change(usernameInput, { target: { value: 'testuser' } });    fireEvent.change(passwordInput, { target: { value: 'correctpassword' } });    fireEvent.click(loginButton);
    await waitFor(() => {      expect(onLoginSuccess).toHaveBeenCalled();    });  });
  it('disables the submit button while submitting', async () => {    const { getByLabelText, getByText } = render(<Login />);    const usernameInput = getByLabelText('Username');    const passwordInput = getByLabelText('Password');    const loginButton = getByText('Login');
    // Mock the API to have a delay    require('./api').login.mockImplementation(      () =>        new Promise((resolve) =>          setTimeout(() => resolve({ success: true }), 1000),        ),    );
    fireEvent.change(usernameInput, { target: { value: 'testuser' } });    fireEvent.change(passwordInput, { target: { value: 'correctpassword' } });    fireEvent.click(loginButton);
    expect(loginButton).toBeDisabled();
    await waitFor(() => {      expect(loginButton).not.toBeDisabled();    });  });});

Installation

Voice & Speech