Agent skill · software engineering · sundial-org
supabase
Connect to Supabase for database operations, vector search, and storage. Use for storing data, running SQL queries, similarity search with pgvector, and managing tables. Triggers on requests involving databases, vector stores, embeddings, or Supabase specifically.
Why this skill is useful
Adds executable scripts for database operations and vector search that provide capabilities beyond standard SQL commands.
What it needs
Requires supabase installed locally. Requires supabase account access. About 3k tokens when loaded. Last updated 2026-03-07. 639 stars on the source repository.
What this skill does
Supabase CLI Interact with Supabase projects: queries, CRUD, vector search, and table management. Setup Quick Commands Commands Reference query - Run raw SQL select - Query table with filters insert - Insert row(s) update - Update rows upsert - Insert or update delete - Delete rows vector-search - Similarity search with pgvector tables - List all tables describe - Show table schema rpc - Call stored procedure Vector Search Setup 1. Enable pgvector extension 2. Create table with embedding column 3. Create similarity search function 4. Create index for performance Environment Variables Variable Required Description ---------- ---------- ------------- SUPABASEURL Yes Project URL (https://xxx.supabase.co) SUPABASESERVICEKEY Yes Service role key (full access) SUPABASEANONKEY No Anon key (restricted access) SUPABASEACCESSTOKEN No Management API token OPENAIAPIKEY No For generating embeddings Notes Service role key bypasses RLS (Row Level Security) Use anon key for client-side/restricted access Vector search requires pgvector extension Embeddings default to OpenAI text-embedding-ada-002 (1536 dimensions)
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills sundial-org/supabase