Skip to content
New this month 24 fresh C++, C#, F#, JavaScript, TypeScript and Lua courses just landed. Browse new releases Use code WELCOME10 for 10% off your first order · 14-day refund
WisdomCharms — home
Cart 0 items in cart
Prompt Packs & Templates Intermediate

The Test-Writing Prompt Library for Python and TypeScript

One hundred and twenty prompts that turn untested code into a suite you can trust.

Rated 4.5 out of 5 from 2 reviews 38 students

LM Created by Laura Mbeki

  • Last updated August 2026
  • English
  • 1h 10m of material
  • 9 lessons

What you will learn

7 concrete outcomes

Every bullet below is something you will have built, shipped or be able to explain by the time you finish the last lesson.

  • Make the model describe behaviour in words before it writes a single assertion
  • Generate case lists that include boundaries, errors and empty inputs
  • Test code that involves time, randomness or the network without brittle mocks
  • Turn a bug report into a regression test that fails for the right reason
  • Build fixtures that stay small instead of growing into a second application
  • Audit an inherited suite and find the tests that pass without proving anything
  • Ask for coverage of behaviour rather than coverage of lines

Course curriculum

5 modules · 9 lessons · 1h 10m of material

1 lesson running 7m in total. Each lesson ships with the finished source files and a short written recap, so you can follow along in your own editor and skim the module again later.

Lesson-by-lesson titles, code downloads and exercises live inside the course library you get access to straight after checkout.

2 lessons running 14m in total. Each lesson ships with the finished source files and a short written recap, so you can follow along in your own editor and skim the module again later.

Lesson-by-lesson titles, code downloads and exercises live inside the course library you get access to straight after checkout.

2 lessons running 16m in total. Each lesson ships with the finished source files and a short written recap, so you can follow along in your own editor and skim the module again later.

Lesson-by-lesson titles, code downloads and exercises live inside the course library you get access to straight after checkout.

2 lessons running 18m in total. Each lesson ships with the finished source files and a short written recap, so you can follow along in your own editor and skim the module again later.

Lesson-by-lesson titles, code downloads and exercises live inside the course library you get access to straight after checkout.

2 lessons running 15m in total. Each lesson ships with the finished source files and a short written recap, so you can follow along in your own editor and skim the module again later.

Lesson-by-lesson titles, code downloads and exercises live inside the course library you get access to straight after checkout.

5 modules · 9 lessons

1h 10m total length

Requirements

Short list, and deliberately so. If you meet these you can start today.

  • Working knowledge of Python or TypeScript
  • A test runner already installed, such as pytest or Vitest
  • A chat model account, free tier is sufficient

About this course

Models write tests eagerly and badly. Left alone they produce a wall of assertions that all pass, cover the happy path twice, and mock the very thing you needed to verify. This library exists to get useful tests out of them instead.

The one hundred and twenty prompts are organised by what you are trying to protect: pure functions, code with time or randomness in it, HTTP boundaries, database access, background jobs, and legacy code with no seams at all. For each situation there is a prompt that first asks the model to describe the behaviour in words, then to list the cases worth testing including the unpleasant ones, and only then to write code. That order is the whole trick.

Python examples use pytest, TypeScript examples use Vitest, and both sets include prompts for property-based thinking, fixtures that do not turn into a second application, and turning a real bug report into a regression test. There is also a set for the opposite job: reading a test suite you inherited and asking the model which tests are lying to you.

Nine recorded lessons apply the library to two small codebases. Everything is delivered by an emailed access link, in Markdown, Notion and plain text.

Topics covered

Frequently asked questions

Still unsure about something? Write to misteryjj100@gmail.com and a human answers, usually the same working day.

pytest for Python and Vitest for TypeScript, though the prompts name the framework in one replaceable line, so Jest, unittest or Mocha work with a single edit.

It assumes you have written a test before. If you have never run a test suite, start with a fundamentals course and come back to this pack afterwards.

Yes. A dedicated set helps you find invariants worth checking and translate them into Hypothesis or fast-check style tests.

Checkout is handled on our provider's secure payment page. The moment your payment clears we email your personal access link and access code to the address you used at checkout, and the same link appears in your account library. There is nothing to install and nothing to wait for.

Email misteryjj100@gmail.com within 14 days of your purchase, quote your order number, and we refund the full amount to your original payment method. No form to fill in and no questions about how much of the course you watched.

What students say

Reviews are written by people who bought this course. We publish the critical ones too.

4.5

Rated 4.5 out of 5

Course rating · 2 reviews

Rating distribution

  • 5 stars 50%
  • 4 stars 50%
  • 3 stars 0%
  • 2 stars 0%
  • 1 star 0%
  • JM

    Julia Marchetti

    Backend engineer

    Mar 2026
    Rated 5.0 out of 5

    Behaviour first, code last

    Ask a model to write tests for a file and you get assertions that mirror the implementation line for line. Make it enumerate behaviours, then cases, then code, and you get something that would genuinely fail if the logic broke. Same tool, completely different result, purely from the ordering.
  • KL

    Kasper Lindgren

    Full-stack developer

    Oct 2025
    Rated 4.0 out of 5

    Python half is stronger

    The Python side is excellent, especially the fixtures and the material on cutting a seam into legacy code. The TypeScript prompts read as though they were written second: nothing on typed mocks, and barely an acknowledgement that runners other than Jest exist.

Your instructor

LM

Laura Mbeki

Prompt engineer and AI workflow designer

  • 506 students taught
  • 16 courses published
  • 4.3 instructor rating
  • Prompt engineering
  • Prompt libraries
  • AI workflows
  • Prompt evaluation

Laura went independent after seven years of agency work and now designs the prompt libraries that sit behind other people's products. She treats prompting as engineering: versioned prompts, a held-out evaluation set, a regression run before anything ships, and a token budget you have to hit. Her packs are the ones she uses with her own clients — briefing, rewriting, summarising, review — rather than sanitised examples, and each comes with notes on where it fails. She keeps every pack working across ChatGPT, Claude and a small open model, so the technique outlives the model.

See every course by Laura Mbeki
$7 USD

One-time payment · lifetime access

The WisdomCharms dispatch

One useful email a week. No fluff, no spam.

New course releases, discount codes before anyone else, and a short, practical breakdown of one technique — a prompt pattern, a C++ idiom, a TypeScript trick — that you can use the same day.

  • Subscriber-only launch pricing
  • Unsubscribe in one click
  • We never sell your address

By subscribing you agree to our Privacy Policy. Questions? Write to misteryjj100@gmail.com.