The 60-Prompt Starter Pack for Everyday Coding
by Laura Mbeki
Three hundred review prompts, sorted by language, code smell and how risky the change is.
LM Created by Laura Mbeki
Every bullet below is something you will have built, shipped or be able to explain by the time you finish the last lesson.
4 modules · 5 lessons · 35m of material
1 lesson running 8m 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.
1 lesson running 9m 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 12m 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.
1 lesson running 6m 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.
4 modules · 5 lessons
35m total length
Short list, and deliberately so. If you meet these you can start today.
Code review is where most teams quietly lose hours, and it is exactly the kind of work a model can carry if you ask precisely. This pack contains three hundred prompts arranged in a grid you can navigate in seconds: down one axis the language, across the other the smell you are chasing, from long parameter lists and primitive obsession to leaking abstractions and untested error paths.
Every prompt is graded by risk. Green prompts suggest changes that are safe to apply in one pass. Amber prompts ask the model to propose a change and the test that would catch it going wrong. Red prompts refuse to rewrite anything and instead produce a written argument for and against, because some refactors are decisions, not edits.
The download ships as Markdown, a Notion import, a JSON file keyed by smell for anyone wiring prompts into their own tooling, and a one-page printable cheat sheet. Five recorded lessons walk through a genuine review of a messy TypeScript service, showing which prompts fire in which order and where the model gets confidently wrong.
Access arrives by email as a link into the WisdomCharms library the moment your payment clears, and every future revision of the grid appears behind that same link at no extra cost.
Still unsure about something? Write to misteryjj100@gmail.com and a human answers, usually the same working day.
Reviews are written by people who bought this course. We publish the critical ones too.
4.0
Rated 4.0 out of 5Course rating · 4 reviews
Oskar Pettersson
Tech lead
I now run the amber set over anything that touches persistence, and it has caught two missing transactions this quarter. The rule that an amber change ships with a guarding test alongside it is the discipline I did not have before.
Fatima Zahra El Amrani
Senior developer
Three hundred prompts as a flat list would be useless. Grading them by how much damage a wrong answer does is what makes the thing usable, because I know before I paste whether I am going to accept the output or argue with it.
Chiara Lombardi
Backend engineer
The smell grid is a genuinely original way to organise material like this and the writing is strong throughout. But it ships as a PDF plus a folder of markdown, so finding the right one of three hundred means grep. A tagged index would have made this five stars without changing a word of the content.
Nikolai Petrov
Systems programmer
It is sold as sorted by language and technically it is, but a large share of the entries repeat across those sections with only the language name changed. The C++ set in particular reads as the JavaScript set with different keywords, and you can tell from what comes back: not one prompt asks about ownership or object lifetime, which is where reviews of C++ actually go wrong. The grid was a good idea. The three hundred is not three hundred.
Prompt engineer and AI workflow designer
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.
One-time payment · lifetime access