Trademarks of their respective owners. KissMySkills is not affiliated with or endorsed by them.
How it works
Ask it something hard.
📎 ai-django-tutor.txtLOADED ✓
I finished the polls tutorial. I want to build a booking app for a small gym. Where do I start?
CLAUDE · WITH THIS SKILLYou get: three questions about what the gym actually books and who logs in -> a level call of knows the basics, because you can run the server but have not designed a model -> a short explanation of why the model comes before the view -> a worked example modelling a library loan, deliberately not a gym -> your task, sketch Member, Class and Booking with the fields and the relations -> your answer, which puts the class time on Booking -> the question of what happens when twenty people book the same session, which is how you find the duplicated field -> ForeignKey and the difference from ManyToMany named once you have moved it -> next lesson: makemigrations, migrate, and reading the generated file.
Questions before you buy? A person answers, usually the same day: hello@kissmyskills.com
// the file itself
Read it before you buy it.
The first lines of the file your AI will read, exactly as delivered. Nothing rewritten for the page.
Use the name Once the file is loaded, talk to it by name: “Serge, check this page.” That is what the name is for. It also keeps several skills apart in one chat.
// the skill your AI runs on
You are a Socratic Django tutor, and the learner runs every command themselves. You have been activated to give the concept, a worked example on a different model, one task, then the check on what the shell returned.
KissMySkills.com | Install: paste this whole file into Claude Projects (Project instructions), a custom GPT (Instructions), a Gemini Gem, or your AI's system prompt. Then tell it what you want to learn. You are a Socratic Django tutor. Your job is to make the learner able to take a Django project from an empty folder to something deployed and working, alone. Assume they have Python, a virtualenv and a terminal open, and that they run every command themselves. Be short, plain and exact. The rule you never break: you do not build the app the learner is building. You give the concept, a worked example on a different model, a task, then a check. · The order that works: project against app, URLs, views, templates, then models, the ORM, forms, auth, deployment. Models first sounds tidy but learners need a page on screen early. · Models and migrations: field types, null against blank, ForeignKey, ManyToManyField, on_delete, related_name, and reading the generated migration file instead of trusting it. · The ORM is where most of the learning is: filter, exclude, get and the DoesNotExist it raises, Q objects, annotate, select_related against prefetch_related, and lazy querysets. · The N+1 query is the defining Django performance bug. Django Debug Toolbar makes it visible. A template loop that touches a related object is the usual cause. · Views: function views with the request and response cycle first, then class based views once the repetition is felt. ListView and DetailView are not a starting point. · Templates: inheritance with extends and block, context, why a template variable is not a Python expression, and why logic belongs in the view. · Forms: Form against ModelForm, cleaned_data, clean methods, CSRF, and the POST then redirect pattern. · Auth: the User model, login_required, permissions and groups, and why a custom user model is decided on day one or regretted later. · The admin: register, list_display, search_fields, inlines. A staff tool, not a product feature. · Deployment: environment variables, DEBUG, ALLOWED_HOSTS, collectstatic, a real database, and gunicorn behind nginx or a platform host. · Classic errors: circular imports, forgetting migrate, editing a migration by hand, TemplateDoesNotExist, NoReverseMatch from a wrong url name. · Employable means tests with the Django test client, no queries in templates, migrations that apply cleanly on an empty database, and settings that differ by environment.
92 lines · .txt · instant download
// what's inside
What's inside this skill
Models and migrations taught until makemigrations stops being scary
The N+1 query found by reading the Django Debug Toolbar, not by guessing
Function views first, class based views only once you feel the repetition
Settings, static files and DEBUG=False handled before you deploy
Python developers moving to the web, bootcamp students past the polls tutorial, and analysts who need an internal tool with a login and an admin.
// two ways to get it
Use it inside your AI, or download it once.
Library plan
This skill and 2,500+ others, inside your chat
$9/mocancel anytime, or $59 a year
All 2,500+ skills, prompt packs and agents, loaded the moment you ask
Nothing to download or paste: connect once in Claude, ChatGPT, Claude Code or Cursor
New skills every week and 10 catalog files a month to download
Trademarks of their respective owners. KissMySkills is not affiliated with or endorsed by them.
// ask your assistant
Or let your AI set up this skill for you.
Go to kissmyskills.com/pages/connector and set up the "AI Django Tutor" skill (handle: ai-django-tutor) for me
Paste it into Claude, ChatGPT, Claude Code, Cursor or Codex. Your AI walks you through connecting KissMySkills (about 3 minutes, 7-day free trial) and loads the skill. What your AI will read →
What you're actually buying
This AI Django tutor is for the day you followed the polls tutorial to the end, then opened a blank project and had no idea what to type first. This file turns Claude, ChatGPT or Gemini into a Django tutor that has you build an app of your own, one layer at a time, and explain what each file is doing there.
It asks what you have shipped, sets your level, then works through the arc that matters: project against app, models and migrations, the ORM and the N+1 query, views from function to class based, templates and static files, forms and ModelForm, the admin, users and permissions, then settings and deployment. Every lesson is a short explanation, a worked example on a different model, then a task you write yourself. When your queryset returns nothing it asks what the filter is comparing, not what to paste.
Same file, same behaviour in Claude, ChatGPT and Gemini. Pay once, install in about a minute, nothing renewing in the background.
// how to install
Under 2 minutes
Four steps. Any AI chat.
01
Download the file
After checkout, the download link lands in your inbox. Save the .txt file anywhere on your device.
02
Open your AI chat
Any AI chat you already use: Claude, ChatGPT, Gemini, Grok, Copilot or another.
03
Paste the prompt
Open the .txt file, copy the prompt section and paste it into Claude or ChatGPT - or add it to a Project so it is always there.
04
Start working
Your AI is now configured as a specialist. Ask it anything inside its domain.
No technical knowledge required.
With Library there is nothing to download. Connect your AI once, then ask for any skill by name.
Paste it into a Claude Project, a custom GPT or a Gemini Gem, then say what you have built in Python and Django so far. It sets a level, picks a small project with you and gives you lesson one. You write the code in your own virtualenv and paste back what happened, including the traceback. It ends each session with a progress block you paste back next time.
Does it build the app for me?+
No. It writes short examples on a different model to show a pattern, then hands you the task and waits. If you paste a broken view it asks what the URL resolved to and what the queryset returned before it says anything else. The app you end up with is one you wrote, which is the only version you will be able to change later.
Do I need to know Python first?+
You need functions, classes, dictionaries and imports. If you have those, the tutor starts at Django itself. If you do not, it says so in the first exchange and spends a lesson on the Python that Django leans on: decorators, list comprehensions and how a class attribute differs from an instance attribute. It will not pretend you are ready when you are not.
Ready to give your AI a specialist?
This one and 2,500+ others, inside Claude, ChatGPT, Claude Code, Codex or Cursor. Cancel anytime.