Вход на сайт

Просмотр новости

Найдите то, что Вас интересует

Django Seedkit

Дата публикации: 03-08-2026 20:00:19

Scaffold a Django project the way you need it. Seedkit is a skill for Claude Code, Cursor, and other coding agents. Tell it what you must build, it asks a few questions, then writes the Django project — authentication, APIs, background jobs, deploy. A cookiecutter gives one fixed set of packages and you delete the parts you do not need; Seedkit knows more than 50 Django packages and writes only the code for what you select.

Основное содержимое страницы с новостью.

Current Django knowledge and best practices for coding agents

Scaffold a Django project
the way you need it.

Seedkit is a skill for Claude Code, Cursor, and other coding agents. Tell it what you must build. It asks you a few questions, then writes the project.

/django-seedkit SaaS landing + waitlist, GDPR-friendly stack (mail, analytics, errors), VPS deploy

/django-seedkit add proper auth — magic link, lockout on brute force, optional 2FA

/django-seedkit look at our repo and tell us what's worth adding next

Measured result

Sonnet with the skill scores above Fable and Opus without it.

The generated projects pass more production checks. To measure that, the same nine projects were generated more than once. Sonnet ran with the skill and without it. Fable and Opus ran without it. A second model then ran the same eight security and configuration checks on every result. With the skill, all nine projects passed all eight — 72 of 72. Without it, a quarter of the checks failed.

Control arms: Fable 54 of 72 on all nine projects, Sonnet 33 of 48 on six, Opus 29 of 32 on four. One run for each project and model, Claude models only. The numbers show that a difference exists. They do not rank the models. Full method →


Comparison

A cookiecutter alternative for coding agents

A cookiecutter gives you one fixed set of packages, and you delete the parts that you do not need. Seedkit knows more than 50 Django packages, and most topics offer more than one option. It asks what you must build, then writes only the code for the options that you select.

You select the packages

Background jobs on Celery, RQ, or the database. Static files on S3 or WhiteNoise. A deploy to a VPS, to Fly.io, or over SSH. You receive the code for your answers, and no other code.

The project is yours

Seedkit writes a normal Django project once. It adds no wrapper library, and your project has no dependency at run time.

The version pins are current

Seedkit resolves each version when it writes the project. A template gives you the versions from its own release date.

Add features to a project you have

Give the command add [feature] in your repository. Seedkit adds the dependency, the settings, the .env example, and the CI step.

See it run An agent reads the prompt, asks a few questions, and writes a Django project that starts. The first prompt above produced 07-vps-sqlite-saas. It has a Docker and Caddy deploy, Sentry, Litestream backups, and CI.

What it adds

One reference file for each topic

Each file has the packages, the settings, and the templates for one topic. Together they cover every step, from an empty directory to a deploy. They also cover the small items, such as robots.txt and the sitemap. Seedkit writes only the files that your answers select.

Authentication
Setup & config
APIs
Billing
Async & caching
Storage & email
Frontend & SEO
Security
Code quality
Dev experience
Ops & CI/CD

Install

Two commands, then one prompt

In Claude Code:

claude plugin marketplace add viewflow/seedkit
claude plugin install seedkit@viewflow

In Cursor, Codex, OpenCode, or Gemini CLI, use the skills CLI:

npx skills add viewflow/seedkit

Then, in an empty directory:


Why a skill and not a prompt

A prompt cannot add what the model does not know

The model writes Django from memory, and that memory is one or two years old. So it writes an authentication setting that Django deprecated, or last year's Stripe webhook. Or it opens the database port to the local network. You can correct all that in your prompt — if you already know the answers. Seedkit already knows them, and it is that prompt, written and tested.

A reference file keeps only the part of the package documentation that the model does not know. Today's setting names, today's package names. One file for each topic: authentication, payments, storage, deploy.

You do not have to know what to ask for. Which package locks an account after failed logins? Which settings does a production deploy need? The files have the answer, and the skill offers it to you.

More than 100 hours of tests found what the model gets wrong. Each file goes into a generated project. We start it, read the result, then correct or drop what failed. What stays in the file is the part the model does not know. You skip the search.

FAQ

Questions
Is Django Seedkit a cookiecutter alternative?

Yes. A cookiecutter gives you one fixed set of packages, and you delete the parts that you do not need. Seedkit asks what you must build, then writes only the code for the options that you select.

Does it work with agents other than Claude Code?

Yes. Install it into Cursor, Codex, OpenCode, Gemini CLI, or any agent that the skills CLI supports. Use the command npx skills add viewflow/seedkit.

Does my project depend on Seedkit when it runs?

No. Seedkit writes a normal Django project once. It adds no wrapper library, no dependency at run time, and nothing more to upgrade later.

Which model must I use?

Any model can run the skill. The knowledge is in the reference files, so the model does not supply it. Sonnet with the skill scored 72 of 72, so a mid-tier model is enough. Keep the expensive models for the code that only you can write. Our tests run on Sonnet, so other models have less coverage. Report a problem in the GitHub issue tracker.

Схожие новости

#Наименование новостиТональностьИнформативностьДата публикации
1django-crawl - An in-process site crawler using Django’s test client028.1828-07-2026
2Django - 5.2.17028.1804-08-2026
3Django - 6.1028.1805-08-2026
4Django-согласия и cookies под 152-ФЗ: версии документов, аудит и экспорт вместо одного чекбокса011.622-06-2026
5Django - 6.0.8028.1804-08-2026
6heise-Angebot: Claude Code in der Praxis – eigenen KI-Chat-Agenten in fünf Sessions entwickeln017.8626-07-2026
7Сервисы — место, где живет бизнес-логика010.3902-01-2026
8 The New Agency Stack: How Dev Shops Use Claude, Cursor, and Copilot in Production 08.4624-07-2026
9GitHub's former CEO launches a distributed Git network built for the agentic coding age0508-07-2026
10Spawn — фреймворк для разработки AIDD методологий09.7115-06-2026

Классификация: Пресс-релизы. Схожих патентов: 0. Схожих новостей: 10. Тональность: 0. Информативность: 5.3. Источник: pythondigest.ru.