The 60-Prompt Starter Pack for Everyday Coding
by Laura Mbeki
Prompts that turn commits, diffs and tickets into documentation people will actually read.
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.
5 modules · 19 lessons · 2h 30m of material
3 lessons running 22m 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 lessons running 32m 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 lessons running 34m 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 lessons running 32m 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 lessons running 30m 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 · 19 lessons
2h 30m total length
Short list, and deliberately so. If you meet these you can start today.
Documentation is the work everyone agrees is important and nobody schedules. A model will not make you care, but it will remove the blank page, and this vault is built to make that first draft close enough to keep.
Inside are prompt sets for the documents developers are actually asked for: a README that explains what the project is in the first two lines, an architecture overview written from a directory listing and a few key files, API reference entries generated from route definitions, a getting-started guide tested against a genuinely empty machine, runbooks for on-call, changelogs grouped by user impact rather than commit order, release notes in three different tones, migration guides that spell out breaking changes, and the deprecation notice nobody wants to write.
The vault also handles the reverse direction: prompts that read existing documentation and find what is now false, what contradicts the code, and what assumes knowledge the reader does not have. Those are the ones teams end up using every quarter.
Nineteen recorded lessons apply the vault to a real open-source style repository across a full release cycle. The pack ships as Markdown, Notion, plain text and a set of document templates, delivered by an access link emailed after checkout.
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.
4.5
Rated 4.5 out of 5Course rating · 2 reviews
Hendrik Vos
Developer advocate
Grouping changes by who is affected and what they have to do about it, rather than listing merged pull requests in order, is such an improvement that our support team commented on it unprompted. The prompts do most of the sorting for you.
Simone Neri
Technical writer
The drifted-documentation audit expects a README and the code it describes pasted in together, which for anything real means splitting it up and losing exactly the cross-references you were checking. Lovely idea, awkward in practice. The changelog and runbook prompts are strong enough on their own to hold this at four.
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