Supabase logo

Supabase

Community
alinaqi
supabase

Core Supabase CLI, migrations, RLS, Edge Functions

Overview

Publisheralinaqi
Repositorymaggy
Skill namesupabase
Stars
707
Forks
57
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Supabase 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/alinaqi/maggy/tree/main/skills/supabase
  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/alinaqi/maggy.git /tmp/maggy
mkdir -p .claude/skills
cp -r /tmp/maggy/skills/supabase .claude/skills/supabase
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Supabase 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 Supabase 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 Supabase 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.

Supabase Core Skill

Core concepts, CLI workflow, and patterns common to all Supabase projects.

Sources: Supabase Docs | Supabase CLI


Core Principle

Local-first, migrations in version control, never touch production directly.

Develop locally with the Supabase CLI, capture all changes as migrations, and deploy through CI/CD.


Supabase Stack

ServicePurpose
DatabasePostgreSQL with extensions
AuthUser authentication, OAuth providers
StorageFile storage with RLS
Edge FunctionsServerless Deno functions
RealtimeWebSocket subscriptions
VectorAI embeddings (pgvector)

CLI Setup

Install & Login

bash
# macOS
brew install supabase/tap/supabase

# npm (alternative)
npm install -g supabase

# Login
supabase login

Initialize Project

bash
# In your project directory
supabase init

# Creates:
# supabase/
# ├── config.toml      # Local config
# ├── seed.sql         # Seed data
# └── migrations/      # SQL migrations

Link to Remote

bash
# Get project ref from dashboard URL: https://supabase.com/dashboard/project/<ref>
supabase link --project-ref <project-id>

# Pull existing schema
supabase db pull

Start Local Stack

bash
supabase start

# Output:
# API URL: http://localhost:54321
# GraphQL URL: http://localhost:54321/graphql/v1
# DB URL: postgresql://postgres:postgres@localhost:54322/postgres
# Studio URL: http://localhost:54323
# Anon key: eyJ...
# Service role key: eyJ...

Migration Workflow

Option 1: Dashboard + Diff (Quick Prototyping)

bash
# 1. Make changes in local Studio (localhost:54323)
# 2. Generate migration from diff
supabase db diff -f <migration_name>

# 3. Review generated SQL
cat supabase/migrations/*_<migration_name>.sql

# 4. Reset to test
supabase db reset

Option 2: Write Migrations Directly (Recommended)

bash
# 1. Create empty migration
supabase migration new create_users_table

# 2. Edit the migration file
# supabase/migrations/<timestamp>_create_users_table.sql

# 3. Apply locally
supabase db reset

Option 3: ORM Migrations (Best DX)

Use Drizzle (TypeScript) or SQLAlchemy (Python) - see framework-specific skills.

Deploy Migrations

bash
# Push to remote (staging/production)
supabase db push

# Check migration status
supabase migration list

Database Patterns

Enable RLS on All Tables

sql
-- Always enable RLS
ALTER TABLE public.profiles ENABLE ROW LEVEL SECURITY;

-- Default deny - must create policies
CREATE POLICY "Users can view own profile"
  ON public.profiles
  FOR SELECT
  USING (auth.uid() = id);

Common RLS Policies

sql
-- Public read
CREATE POLICY "Public read access"
  ON public.posts FOR SELECT
  USING (true);

-- Authenticated users only
CREATE POLICY "Authenticated users can insert"
  ON public.posts FOR INSERT
  WITH CHECK (auth.role() = 'authenticated');

-- Owner access
CREATE POLICY "Users can update own records"
  ON public.posts FOR UPDATE
  USING (auth.uid() = user_id);

-- Admin access (using custom claim)
CREATE POLICY "Admins have full access"
  ON public.posts FOR ALL
  USING (auth.jwt() ->> 'role' = 'admin');

Link to auth.users

sql
-- Profile table linked to auth
CREATE TABLE public.profiles (
  id UUID PRIMARY KEY REFERENCES auth.users(id) ON DELETE CASCADE,
  username TEXT UNIQUE NOT NULL,
  avatar_url TEXT,
  created_at TIMESTAMPTZ DEFAULT NOW()
);

-- Auto-create profile on signup
CREATE OR REPLACE FUNCTION public.handle_new_user()
RETURNS TRIGGER AS $$
BEGIN
  INSERT INTO public.profiles (id, username)
  VALUES (NEW.id, NEW.email);
  RETURN NEW;
END;
$$ LANGUAGE plpgsql SECURITY DEFINER;

CREATE TRIGGER on_auth_user_created
  AFTER INSERT ON auth.users
  FOR EACH ROW EXECUTE FUNCTION public.handle_new_user();

Seed Data

supabase/seed.sql

sql
-- Runs on `supabase db reset`
-- Use ON CONFLICT for idempotency

INSERT INTO public.profiles (id, username, avatar_url)
VALUES
  ('d0e1f2a3-b4c5-6d7e-8f9a-0b1c2d3e4f5a', 'testuser', null),
  ('a1b2c3d4-e5f6-7a8b-9c0d-1e2f3a4b5c6d', 'admin', null)
ON CONFLICT (id) DO NOTHING;

Environment Variables

Required Variables

bash
# Public (safe for client-side)
SUPABASE_URL=https://xxxxx.supabase.co
SUPABASE_ANON_KEY=eyJ...

# Private (server-side only - NEVER expose)
SUPABASE_SERVICE_ROLE_KEY=eyJ...
DATABASE_URL=postgresql://postgres.[ref]:[password]@aws-0-region.pooler.supabase.com:6543/postgres

Local vs Production

bash
# .env.local (local development)
SUPABASE_URL=http://localhost:54321
SUPABASE_ANON_KEY=<from supabase start>
DATABASE_URL=postgresql://postgres:postgres@localhost:54322/postgres

# .env.production (remote)
SUPABASE_URL=https://xxxxx.supabase.co
SUPABASE_ANON_KEY=<from dashboard>
DATABASE_URL=<connection pooler URL>

Connection Pooling

bash
# Transaction mode (recommended for serverless)
# Add ?pgbouncer=true to URL
DATABASE_URL=postgresql://...@pooler.supabase.com:6543/postgres?pgbouncer=true

# Session mode (for migrations, long transactions)
DATABASE_URL=postgresql://...@pooler.supabase.com:5432/postgres

Edge Functions

Create Function

bash
supabase functions new hello-world

Basic Structure

typescript
// supabase/functions/hello-world/index.ts
import { serve } from 'https://deno.land/std@0.168.0/http/server.ts';

serve(async (req) => {
  const { name } = await req.json();

  return new Response(
    JSON.stringify({ message: `Hello ${name}!` }),
    { headers: { 'Content-Type': 'application/json' } }
  );
});

With Auth Context

typescript
import { serve } from 'https://deno.land/std@0.168.0/http/server.ts';
import { createClient } from 'https://esm.sh/@supabase/supabase-js@2';

serve(async (req) => {
  const supabase = createClient(
    Deno.env.get('SUPABASE_URL') ?? '',
    Deno.env.get('SUPABASE_ANON_KEY') ?? '',
    {
      global: {
        headers: { Authorization: req.headers.get('Authorization')! },
      },
    }
  );

  const { data: { user } } = await supabase.auth.getUser();

  if (!user) {
    return new Response('Unauthorized', { status: 401 });
  }

  return new Response(JSON.stringify({ user_id: user.id }));
});

Deploy

bash
# Serve locally
supabase functions serve

# Deploy single function
supabase functions deploy hello-world

# Deploy all
supabase functions deploy

Storage

Create Bucket (in migration)

sql
INSERT INTO storage.buckets (id, name, public)
VALUES ('avatars', 'avatars', true);

-- Storage policies
CREATE POLICY "Avatar images are publicly accessible"
  ON storage.objects FOR SELECT
  USING (bucket_id = 'avatars');

CREATE POLICY "Users can upload own avatar"
  ON storage.objects FOR INSERT
  WITH CHECK (
    bucket_id = 'avatars' AND
    auth.uid()::text = (storage.foldername(name))[1]
  );

CLI Quick Reference

bash
# Lifecycle
supabase start                   # Start local stack
supabase stop                    # Stop local stack
supabase status                  # Show status & credentials

# Database
supabase db reset                # Reset + migrations + seed
supabase db push                 # Push to remote
supabase db pull                 # Pull remote schema
supabase db diff -f <name>       # Generate migration from diff
supabase db lint                 # Check for issues

# Migrations
supabase migration new <name>    # Create migration
supabase migration list          # List migrations
supabase migration up            # Apply pending (remote)

# Functions
supabase functions new <name>    # Create function
supabase functions serve         # Local dev
supabase functions deploy        # Deploy all

# Types
supabase gen types typescript --local > types/database.ts

# Project
supabase link --project-ref <id> # Link to remote
supabase projects list           # List projects

CI/CD Template

yaml
# .github/workflows/supabase.yml
name: Supabase CI/CD

on:
  push:
    branches: [main]
  pull_request:

env:
  SUPABASE_ACCESS_TOKEN: ${{ secrets.SUPABASE_ACCESS_TOKEN }}
  SUPABASE_DB_PASSWORD: ${{ secrets.SUPABASE_DB_PASSWORD }}
  SUPABASE_PROJECT_ID: ${{ secrets.SUPABASE_PROJECT_ID }}

jobs:
  test:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: supabase/setup-cli@v1

      - name: Start Supabase
        run: supabase start

      - name: Run migrations
        run: supabase db reset

      - name: Lint database
        run: supabase db lint

  deploy:
    needs: test
    if: github.ref == 'refs/heads/main'
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: supabase/setup-cli@v1

      - name: Link project
        run: supabase link --project-ref $SUPABASE_PROJECT_ID

      - name: Push migrations
        run: supabase db push

      - name: Deploy functions
        run: supabase functions deploy

Anti-Patterns

  • Direct production changes - Always use migrations
  • Disabled RLS - Enable on all user-data tables
  • Service key in client - Never expose service role key
  • No connection pooling - Use pooler for serverless
  • Committing .env - Add to .gitignore
  • Skipping migration review - Always check generated SQL
  • No seed data - Use seed.sql for consistent local dev

Frequently asked questions

What does the Supabase AI skill do?

Core Supabase CLI, migrations, RLS, Edge Functions

Why use Supabase on TypingMind?

Because you install it once and use it with any model. Supabase 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 Supabase in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/alinaqi/maggy/tree/main/skills/supabase. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Supabase?

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 Supabase?

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

Is the Supabase AI skill free?

Yes. It is published on GitHub by alinaqi 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 👇