django-project-setup
Set up a new Django 6.0 project with modern tooling (uv, direnv, HTMX, OAuth, DRF, testing). Use when the user wants to create a Django project from scratch with production-ready configuration.
What this skill does
# Django 6.0 Project Setup
Automated setup for production-ready Django 6.0 projects with modern tooling.
## What This Skill Does
Creates a complete Django 6.0 project with:
### Modern Stack (2026)
- ✅ **uv** - Fast package manager (no pip/venv needed)
- ✅ **Django 6.0** - Latest version with Python 3.12+ support
- ✅ **PostgreSQL** - Docker Compose + Supabase support
- ✅ **Custom User Model** - UUID primary keys from day 1
- ✅ **direnv** - Automatic environment management
- ✅ **HTMX** - Modern frontend interactivity
- ✅ **OAuth** - Authentication ready (django-oauth-toolkit)
- ✅ **DRF + Pydantic** - Type-safe API schemas
- ✅ **pytest + factory_boy** - Modern testing infrastructure
- ✅ **mypy + ruff** - Type checking and linting
- ✅ **Docker Compose** - Local PostgreSQL container
- ✅ **Makefile** - Common development commands
- ✅ **Full Type Annotations** - AI tooling optimized (Copilot, Cursor, Cody)
## AI Tooling Compatibility
This project template is optimized for AI coding assistants:
- ✅ **Full Type Coverage**: All generated code has comprehensive type annotations
- ✅ **Strict mypy**: `disallow_untyped_defs = true` enforced from day 1
- ✅ **Better Completions**: AI tools understand code context and relationships
- ✅ **Fewer Errors**: Type checking catches issues before runtime
- ✅ **Improved Refactoring**: AI can suggest safer, type-aware refactorings
- ✅ **Self-Documenting**: Type hints serve as inline documentation
Compatible with: GitHub Copilot, Cursor, Cody, Continue, Tabnine, and other AI coding assistants.
### Why This Matters
When you provide full type annotations:
- AI assistants give more accurate code completions
- Auto-import suggestions are more precise
- Refactoring suggestions are type-safe
- Error detection happens as you type
- Generated documentation is more comprehensive
### Directory Structure
```
{project_name}/
├── config/ # Settings and core config
│ ├── settings/
│ │ ├── __init__.py
│ │ ├── base.py # Core settings
│ │ ├── dev.py # Development
│ │ └── prod.py # Production
│ ├── urls.py
│ ├── asgi.py
│ └── wsgi.py
├── apps/ # Django apps
│ ├── __init__.py
│ └── core/ # Shared utilities
│ ├── models.py # UUIDModel base class
│ └── ...
├── templates/ # Global templates
├── static/ # Global static files
├── pyproject.toml # uv dependencies
├── pytest.ini # Test configuration
├── conftest.py # Test fixtures
├── docker-compose.yml # PostgreSQL container
├── Makefile # Development commands
├── .envrc # Environment config
├── .env.example # Environment template
├── manage.py
└── CLAUDE.md # Project instructions
```
## Usage
```bash
# With Docker PostgreSQL (default)
/django-project-setup myproject
# With Supabase
/django-project-setup myproject --with-supabase
```
The skill will:
1. Parse arguments (project name and optional --with-supabase flag)
2. Ask for first app name (e.g., 'accounts', 'blog', 'api')
3. Create project structure with uv
4. Set up database (Docker Compose or Supabase instructions)
5. Configure direnv environment
6. Install all dependencies
7. Create custom User model with UUID
8. Run initial migrations (or show Supabase setup instructions)
9. Set up testing infrastructure
10. Configure HTMX, OAuth, and DRF
11. Create CLAUDE.md with project patterns
## Requirements
- **Python 3.12+** (Django 6.0 requirement - automatically installed by uv if missing)
- **uv** (will be installed if missing - handles Python version management)
- **direnv** (recommended, will prompt if missing)
- **Docker** (for local PostgreSQL)
## After Setup
### With Docker PostgreSQL (default)
```bash
# Start PostgreSQL
/usr/bin/make start-docker
# Run migrations
/usr/bin/make migrate
# Create superuser (set password in .envrc.local first)
/usr/bin/make createsuperuser
# Start development server
/usr/bin/make runserver
# Run tests
/usr/bin/make test
# Type checking
/usr/bin/make typecheck
# Linting
/usr/bin/make lint
```
Visit http://localhost:8000/admin/ to verify setup.
### With Supabase
```bash
# 1. Complete Supabase setup (see SUPABASE_SETUP.md)
# 2. Add DATABASE_URL to .env.local
# 3. Allow direnv
direnv allow
# Run migrations
uv run python manage.py migrate
# Create superuser
uv run python manage.py createsuperuser
# Start development server
uv run python manage.py runserver
# Run tests
uv run pytest
# Type checking
uv run mypy .
# Linting
uv run ruff check .
```
Visit http://localhost:8000/admin/ to verify setup.
## Execution Instructions
When this skill is invoked with a project name (e.g., `/django-project-setup myproject` or `/django-project-setup myproject --with-supabase`), follow these steps:
### Prerequisites Check
1. **Parse Arguments**:
```bash
# Extract project name (first non-flag argument)
# Check if --with-supabase flag is present
# Set use_supabase=true if flag found, false otherwise
```
2. Check if uv is installed, install if missing:
```bash
which uv || curl -LsSf https://astral.sh/uv/install.sh | sh
```
3. Check if Python 3.12+ is available, install via uv if missing:
```bash
# Check current Python version
python3 --version 2>/dev/null | grep -q "Python 3.1[2-9]" || \
# If not found, use uv to install Python 3.12
uv python install 3.12
```
4. Verify current directory or use /tmp if not specified
### Execution Steps
**Step 1: Ask for First App Name**
Use AskUserQuestion to ask:
```
Question: "What should be the first Django app to create?"
Options:
- "blog" (description: "Blog/content management app")
- "accounts" (description: "User accounts and profiles")
- "api" (description: "API endpoints")
- "core" (description: "Core functionality only")
Header: "First App"
```
**Step 2: Initialize uv Project**
```bash
# Initialize project with Python 3.12+
uv init --python 3.12 {project_name}
builtin cd {project_name}
# Verify .python-version file was created
[ -f .python-version ] && echo "✅ Python version pinned" || echo "3.12" > .python-version
```
**Step 3: Add Core Dependencies**
```bash
uv add django psycopg[binary] django-environ
uv add djangorestframework django-oauth-toolkit django-htmx pydantic
uv add --group dev pytest pytest-django pytest-cov pytest-asyncio
uv add --group dev factory-boy pytest-factoryboy
uv add --group dev mypy django-stubs types-requests
uv add --group dev ruff django-extensions ipython
```
**Step 4: Create Django Project Structure**
```bash
uv run django-admin startproject config .
```
**Step 5: Create Directory Structure**
```bash
mkdir -p apps/core/{migrations,tests}
mkdir -p apps/{first_app_name}/{migrations,tests}
mkdir -p templates/partials
mkdir -p static
mkdir -p config/settings
```
**Step 6: Create Configuration Files**
Use the templates in `templates/` directory to create:
1. `Makefile` - Use Makefile.template (conditionally add Docker targets if use_supabase == false)
2. `.envrc` - Use .envrc.template, configure DATABASE_URL based on use_supabase
3. `.env` - Use .env.template, configure database variables based on use_supabase
4. `.env.example` - Use .env.example.template, configure based on use_supabase
5. `.envrc.local` - Use .envrc.local.template
6. `.gitignore` - Use .gitignore.template
7. `pytest.ini` - Use pytest.ini.template
8. `conftest.py` - Use conftest.py.template
9. `CLAUDE.md` - Use CLAUDE.md.template, replace {project_name} and add database-specific notes
**If use_supabase == false (Docker):**
- Create `docker-compose.yml` - Use docker-compose.yml.template, replace {project_name}
**If use_supabase == true:**
- Create `SUPABASE_SETUP.md` with instructions for Supabase project creation
- Display message: "⚠️ Supabase setup required - see SUPABASE_SETUP.md for instructions"
**Step 7: Split Settings Files**
1. Delete `config/settings.py`
2. Create `config/settings/__init__.py` (Related in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.