Skip to content
TakoAPI
Back to skills

supabase

by stopmoclay

Data & Analytics
—Not yet rated
Your rating

Brief

Connect to Supabase for database operations, vector search, and storage.

Description

What This Skill Does

Connects to a Supabase project to run SQL queries, perform CRUD operations on tables, and execute vector similarity search using pgvector. The service role key grants full database access; an anon key can be used for restricted access.

Handles raw SQL, CRUD, and vector similarity search through one CLI without needing separate database clients or a custom embedding pipeline.

When to Use It

  • Query user records filtered by status or date range
  • Insert rows collected from a form or API response
  • Find semantically similar documents using pgvector embeddings
  • Inspect table schemas before writing migration SQL
  • Delete expired session rows matching a condition

Example Workflow

INPUT

User asks: Find the top 5 documents related to 'setting up authentication'

AGENT
  1. 1

    Calls vector-search on the documents table with the query string

  2. 2

    Generates an embedding for the query using OpenAI text-embedding-ada-002

  3. 3

    Passes the embedding to the match_documents RPC function in Supabase

  4. 4

    Retrieves rows ranked by cosine similarity above the configured threshold

  5. 5

    Returns the top 5 matching records with content and similarity scores

OUTPUT

A ranked list of 5 document records with content fields and similarity scores

Requirements

  • SUPABASE_URL environment variable
  • SUPABASE_SERVICE_KEY environment variable
  • Supabase account and project
  • OPENAI_API_KEY environment variable (required for vector search embeddings)

Installation

clawhub install stopmoclay/supabase

Run the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.

Links