Enferno Dev logo

Enferno Dev

Community
level09
enferno-dev

Development skill for the Enferno Flask framework. Use when implementing features, fixing bugs, or writing code in Enferno-based applications: blueprints, SQLAlchemy models and migrations, admin JSON APIs, Vue 3 + Vuetify pages without a build step, Flask-Security auth, Celery tasks, and dependency upgrades.

Overview

Publisherlevel09
Repositoryenferno
Skill nameenferno-dev
Stars
568
Forks
79
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by level09 on GitHub. Read the source before you install it.

Installation

Install the Enferno Dev AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/level09/enferno/tree/master/.agents/skills/enferno-dev
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/level09/enferno.git /tmp/enferno
mkdir -p .claude/skills
cp -r /tmp/enferno/.agents/skills/enferno-dev .claude/skills/enferno-dev
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Enferno Dev in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Enferno Dev on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Enferno Dev is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Enferno Development

Flask 3 + SQLAlchemy 2.x + Vue 3 + Vuetify 3. No frontend build step. uv for everything.

Quick Reference

bash
uv run flask run --port 5001                      # Dev server (5001 on macOS)
uv run flask create-db                            # Create tables and stamp migrations
uv run flask install                              # Create admin user
uv run flask db migrate -m "msg"                  # Draft migration, review before upgrade
uv run flask db upgrade                           # Apply migrations
uv run python checks.py                           # Boot, DB, routes, login/logout smoke checks
uv run ruff check . && uv run ruff format .       # Lint + format

Blueprint Structure

enferno/
├── feature_name/
│   ├── views.py      # Page routes and /api/ endpoints
│   ├── models.py     # SQLAlchemy models
│   └── forms.py      # WTForms (if needed)
└── templates/feature_name/

Register in register_blueprints() in enferno/app.py:

python
from enferno.feature_name.views import bp as feature_bp

app.register_blueprint(feature_bp)

Models

Use BaseMixin (save()/delete()) and implement to_dict()/from_dict(). After changing models, run flask db migrate and review the generated revision.

python
from enferno.extensions import db
from enferno.utils.base import BaseMixin


class Product(db.Model, BaseMixin):
    __tablename__ = "products"

    id = db.Column(db.Integer, primary_key=True)
    name = db.Column(db.String(255), nullable=False)
    price = db.Column(db.Numeric(10, 2))
    active = db.Column(db.Boolean, default=True)

    def to_dict(self):
        return {"id": self.id, "name": self.name, "price": float(self.price or 0), "active": self.active}

    def from_dict(self, data):
        self.name = data.get("name", self.name)
        self.price = data.get("price", self.price)
        self.active = data.get("active", self.active)
        return self

API Endpoints

Protect the whole blueprint in before_request. Payloads are {"item": {...}}; lists return items, total, perPage. Log admin actions with Activity.register.

python
from flask import Blueprint, render_template, request
from flask_security import auth_required, current_user, roles_required

from enferno.extensions import db
from enferno.user.models import Activity

bp = Blueprint("products", __name__)


@bp.before_request
@auth_required("session")
@roles_required("admin")
def before_request():
    pass


@bp.get("/products/")
def products_page():
    return render_template("products/index.html")


@bp.get("/api/products")
def list_products():
    page = request.args.get("page", 1, type=int)
    per_page = request.args.get("per_page", 25, type=int)
    pagination = db.paginate(db.select(Product), page=page, per_page=per_page)
    return {"items": [p.to_dict() for p in pagination.items], "total": pagination.total, "perPage": pagination.per_page}


@bp.post("/api/product/")
def create_product():
    product = Product().from_dict(request.json.get("item", {}))
    db.session.add(product)
    db.session.commit()
    Activity.register(current_user.id, "Product Create", product.to_dict())
    return {"item": product.to_dict()}


@bp.post("/api/product/<int:id>")
def update_product(id):
    product = db.get_or_404(Product, id)
    old = product.to_dict()
    product.from_dict(request.json.get("item", {}))
    db.session.commit()
    Activity.register(current_user.id, "Product Update", {"old": old, "new": product.to_dict()})
    return {"item": product.to_dict()}


@bp.delete("/api/product/<int:id>")
def delete_product(id):
    product = db.get_or_404(Product, id)
    Activity.register(current_user.id, "Product Delete", product.to_dict())
    db.session.delete(product)
    db.session.commit()
    return {"deleted": True}

Pages (Vue 3 + Vuetify)

layout.html owns <v-app>, the nav and the #app mount point. A page fills {% block content %} and mounts its app in {% block js %} with layoutMixin and registerEnfernoComponents, or the nav breaks. Vue expressions use ${ }; {{ }} is Jinja.

html
{% extends "layout.html" %}
{% block content %}
<v-card class="ma-2 mt-12 w-100">
  <v-card-text>
    <v-data-table-server :headers="headers" :items="items" :items-length="total"
                         :loading="loading" @update:options="loadItems">
      <template v-slot:item.actions="{ item }">
        <v-btn icon="ti-pencil" variant="text" @click="editItem(item)"></v-btn>
      </template>
    </v-data-table-server>
  </v-card-text>
</v-card>
{% endblock %}

{% block js %}
<script type="application/json" id="categories-data">{{ categories|tojson|safe }}</script>
<script>
const { createApp } = Vue;
const vuetify = Vuetify.createVuetify(config.vuetifyConfig);

const app = createApp({
  mixins: [layoutMixin],
  delimiters: config.delimiters,
  data() {
    return {
      items: [], total: 0, loading: false,
      categories: JSON.parse(document.querySelector('#categories-data').textContent),
      headers: [
        { title: 'Name', key: 'name' },
        { title: 'Actions', key: 'actions', sortable: false },
      ],
    };
  },
  methods: {
    async loadItems({ page, itemsPerPage }) {
      this.loading = true;
      const res = await axios.get('/api/products', { params: { page, per_page: itemsPerPage } });
      this.items = res.data.items;
      this.total = res.data.total;
      this.loading = false;
    },
    editItem(item) { /* open dialog */ },
  },
});

registerEnfernoComponents(app);
app.use(vuetify).mount('#app');
</script>
{% endblock %}

Rules:

  • Icons are Tabler only: ti-* names (icon="ti-pencil", <i class="ti ti-user">). Never mdi-*; it renders blank.
  • Logout is POST-only: a form posting to /logout, never href="/logout".
  • CSRF is enforced on every POST/PUT/DELETE. Axios on layout.html pages already sends the X-CSRFToken header; plain HTML forms need <input type="hidden" name="csrf_token" value="{{ csrf_token() }}">.
  • Pass server data through a <script type="application/json"> tag and |tojson, never by interpolating into JS.
  • Never mutate reactive state inside a computed property. It loops forever on Vue 3.5.

Queries (SQLAlchemy 2.x)

python
users = db.session.execute(db.select(User).where(User.active == True)).scalars().all()
user = db.get_or_404(User, id)
pagination = db.paginate(db.select(User), page=1, per_page=25)
orders = db.session.execute(db.select(Order).join(User).where(User.id == user_id)).scalars().all()

Celery Tasks

Optional (uv sync --extra full). enferno.tasks.celery is None when Celery is not installed or configured.

python
from enferno.tasks import celery


@celery.task
def process_order(order_id):
    ...

Dependency Upgrades

uv lock --upgrade && uv sync --extra dev --extra full, then uv run --with pip-audit pip-audit and uv run python checks.py. Read the Flask-Security changelog for changed defaults, and load an admin page in a real browser: a Vue upgrade once froze admin pages while every Python check passed.

More Patterns

Relationships, forms, uploads, search/filtering, dialogs and error handling: references/patterns.md.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Enferno Dev AI skill do?

Development skill for the Enferno Flask framework. Use when implementing features, fixing bugs, or writing code in Enferno-based applications: blueprints, SQLAlchemy models and migrations, admin JSON APIs, Vue 3 + Vuetify pages without a build step, Flask-Security auth, Celery tasks, and dependency upgrades.

Why use Enferno Dev on TypingMind?

Because you install it once and use it with any model. Enferno Dev is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Enferno Dev in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/level09/enferno/tree/master/.agents/skills/enferno-dev. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Enferno Dev?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Enferno Dev?

As many as you like. As long as a model supports skills, you can use Enferno Dev with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Enferno Dev AI skill free?

Yes. It is published on GitHub by level09 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇