Agent Skills for developers using AI agents with Supabase — database, auth, storage, and edge functions.
What it does
Claude generates Supabase queries that miss RLS, auth patterns that use deprecated methods, storage policies that are either too permissive or incorrectly structured, and edge function patterns that don't match how Supabase's runtime actually works. This is Supabase's official agent skill — built and maintained by the Supabase engineering team — covering correct RLS policy syntax, typed query patterns, auth session management, storage bucket configuration, and edge function structure.
Use case
Any project using Supabase. The failure mode this prevents most often: Claude generates a table and forgets RLS entirely, or generates RLS that looks correct but has logic errors that expose data. Made by Supabase — these are the patterns their own engineers use.
"Add a posts table. Only the author can edit. Everyone can read published posts." "Write a query to fetch all orders with the customer's name and email." "Create a storage bucket for user avatars — authenticated users can upload their own." "Write an edge function that charges a Stripe payment when an order is submitted." "Generate a migration to add soft deletes to this table."
Install in your project. Claude applies correct Supabase patterns to all database, auth, and storage code it generates.
For RLS: describe the access rules in plain English. Claude generates the correct SQL, not a guess.
For typed queries: Claude generates properly typed Supabase client calls that match your schema.
Input
A description of the database operation, auth flow, or storage pattern you need — or existing Supabase code to review.
Output
Correct Supabase client code with proper TypeScript types, RLS policies that match the intended access rules, and migration SQL that follows Supabase conventions.
npx skillsadd supabase/agent-skills/supabase-postgres-best-practices
npx skillsadd supabase/skills/supabase-skills
Requires skills.sh CLI
Build Obsidian.md plugins following official API patterns, TypeScript best practices, and plugin review guidelines.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.