database

Connect to Supabase for database operations, vector search, and storage. Use for storing data, running SQL queries, similarity search with pgvector, and mana...

Security Scan

The skill's files implement a Supabase CLI and require high‑privilege Supabase credentials and an external embedding API, but the registry metadata omits those requirements and misses required binaries — the capability/requirements don't fully align.

Purpose & Capability

The skill's stated purpose (Supabase DB operations, vector search) matches the script's behavior, but the registry's declared required env vars list only SKILLBOSS_API_KEY while the script actually requires SUPABASE_URL and SUPABASE_SERVICE_KEY (a Supabase service role key with full access). That omission is an incoherence: a database tool legitimately needs Supabase credentials, so the registry metadata should declare them.

Instruction Scope

SKILL.md and scripts instruct the agent to run scripts that: call Supabase REST/RPC endpoints using the service role key, run raw SQL via an exec_sql RPC, and call an external embedding service (https://api.heybossai.com/v1/pilot). The instructions reference and expect command-line tools (curl, jq) but the skill metadata did not declare these runtime dependencies. The script will transmit user query text to a third‑party embedding API — expected for vector search but worth noting.

Install Mechanism

There is no installer or external download; the skill is instruction-plus-included-script (scripts/supabase.sh). No network-based installer or archive extraction is present, which reduces install-time risk. The script itself will be installed as a file in the skill bundle.

Credentials

The script requires SUPABASE_SERVICE_KEY (service role key — full DB access) and SUPABASE_URL in addition to SKILLBOSS_API_KEY. The registry only lists SKILLBOSS_API_KEY. Requesting a Supabase service role key is high privilege for a skill; the credentials requested are broader than what the registry declares. Additionally, the script expects jq and curl but the declared required binaries are none.

Persistence & Privilege

always is false (good). The skill allows autonomous invocation (disable-model-invocation: false), which is the platform default. Combined with a Supabase service role key, autonomous invocation increases blast radius (an agent could run arbitrary queries in the DB). This is not a configuration error by itself, but users should be aware of the risk of giving an agent a full‑privilege DB key.

What to consider before installing

This skill implements a Supabase CLI and will need: SUPABASE_URL and a SUPABASE_SERVICE_KEY (service role key) plus SKILLBOSS_API_KEY for embeddings, and command-line tools like curl and jq. The registry metadata only declared SKILLBOSS_API_KEY, which is inconsistent — confirm the required environment variables before installing. Because the script uses a Supabase service role key (full access), only install if you trust the skill and are willing to grant full DB access; prefer creating a least-privilege API key or using row-level security and limited roles. Also verify you are comfortable sending text to the external embedding endpoint (api.heybossai.com). If you can't provide a limited key or audit the skill fully, treat this as high-risk and avoid granting service-role credentials or allowing autonomous invocation.

Supabase CLI

Interact with Supabase projects: queries, CRUD, vector search, and table management.

Setup

# Required
export SUPABASE_URL="https://yourproject.supabase.co"
export SUPABASE_SERVICE_KEY="eyJhbGciOiJIUzI1NiIs..."

# Required: SkillBoss API Hub key (for vector embeddings via /v1/pilot)
export SKILLBOSS_API_KEY="your-skillboss-api-key"

# Optional: for management API
export SUPABASE_ACCESS_TOKEN="sbp_xxxxx"

Quick Commands

# SQL query
{baseDir}/scripts/supabase.sh query "SELECT * FROM users LIMIT 5"

# Insert data
{baseDir}/scripts/supabase.sh insert users '{"name": "John", "email": "[e-mail]"}'

# Select with filters
{baseDir}/scripts/supabase.sh select users --eq "status:active" --limit 10

# Update
{baseDir}/scripts/supabase.sh update users '{"status": "inactive"}' --eq "id:123"

# Delete
{baseDir}/scripts/supabase.sh delete users --eq "id:123"

# Vector similarity search
{baseDir}/scripts/supabase.sh vector-search documents "search query" --match-fn match_documents --limit 5

# List tables
{baseDir}/scripts/supabase.sh tables

# Describe table
{baseDir}/scripts/supabase.sh describe users

Commands Reference

query - Run raw SQL

{baseDir}/scripts/supabase.sh query "<SQL>"

# Examples
{baseDir}/scripts/supabase.sh query "SELECT COUNT(*) FROM users"
{baseDir}/scripts/supabase.sh query "CREATE TABLE items (id serial primary key, name text)"
{baseDir}/scripts/supabase.sh query "SELECT * FROM users WHERE created_at > '2024-01-01'"

select - Query table with filters

{baseDir}/scripts/supabase.sh select <table> [options]

Options:
  --columns <cols>    Comma-separated columns (default: *)
  --eq <col:val>      Equal filter (can use multiple)
  --neq <col:val>     Not equal filter
  --gt <col:val>      Greater than
  --lt <col:val>      Less than
  --like <col:val>    Pattern match (use % for wildcard)
  --limit <n>         Limit results
  --offset <n>        Offset results
  --order <col>       Order by column
  --desc              Descending order

# Examples
{baseDir}/scripts/supabase.sh select users --eq "status:active" --limit 10
{baseDir}/scripts/supabase.sh select posts --columns "id,title,created_at" --order created_at --desc
{baseDir}/scripts/supabase.sh select products --gt "price:100" --lt "price:500"

insert - Insert row(s)

{baseDir}/scripts/supabase.sh insert <table> '<json>'

# Single row
{baseDir}/scripts/supabase.sh insert users '{"name": "Alice", "email": "[e-mail]"}'

# Multiple rows
{baseDir}/scripts/supabase.sh insert users '[{"name": "Bob"}, {"name": "Carol"}]'

update - Update rows

{baseDir}/scripts/supabase.sh update <table> '<json>' --eq <col:val>

# Example
{baseDir}/scripts/supabase.sh update users '{"status": "inactive"}' --eq "id:123"
{baseDir}/scripts/supabase.sh update posts '{"published": true}' --eq "author_id:5"

upsert - Insert or update

{baseDir}/scripts/supabase.sh upsert <table> '<json>'

# Example (requires unique constraint)
{baseDir}/scripts/supabase.sh upsert users '{"id": 1, "name": "Updated Name"}'

delete - Delete rows

{baseDir}/scripts/supabase.sh delete <table> --eq <col:val>

# Example
{baseDir}/scripts/supabase.sh delete sessions --lt "expires_at:2024-01-01"

vector-search - Similarity search with pgvector

{baseDir}/scripts/supabase.sh vector-search <table> "<query>" [options]

Options:
  --match-fn <name>     RPC function name (default: match_<table>)
  --limit <n>           Number of results (default: 5)
  --threshold <n>       Similarity threshold 0-1 (default: 0.5)
  --embedding-model <m> Model for query embedding (default: uses SkillBoss API Hub)

# Example
{baseDir}/scripts/supabase.sh vector-search documents "How to set up authentication" --limit 10

# Requires a match function like:
# CREATE FUNCTION match_documents(query_embedding vector(1536), match_threshold float, match_count int)

tables - List all tables

{baseDir}/scripts/supabase.sh tables

describe - Show table schema

{baseDir}/scripts/supabase.sh describe <table>

rpc - Call stored procedure

{baseDir}/scripts/supabase.sh rpc <function_name> '<json_params>'

# Example
{baseDir}/scripts/supabase.sh rpc get_user_stats '{"user_id": 123}'

Vector Search Setup

1. Enable pgvector extension

CREATE EXTENSION IF NOT EXISTS vector;

2. Create table with embedding column

CREATE TABLE documents (
  id bigserial PRIMARY KEY,
  content text,
  metadata jsonb,
  embedding vector(1536)
);

3. Create similarity search function

CREATE OR REPLACE FUNCTION match_documents(
  query_embedding vector(1536),
  match_threshold float DEFAULT 0.5,
  match_count int DEFAULT 5
)
RETURNS TABLE (
  id bigint,
  content text,
  metadata jsonb,
  similarity float
)
LANGUAGE plpgsql
AS $$
BEGIN
  RETURN QUERY
  SELECT
    documents.id,
    documents.content,
    documents.metadata,
    1 - (documents.embedding <=> query_embedding) AS similarity
  FROM documents
  WHERE 1 - (documents.embedding <=> query_embedding) > match_threshold
  ORDER BY documents.embedding <=> query_embedding
  LIMIT match_count;
END;
$$;

4. Create index for performance

CREATE INDEX ON documents
USING ivfflat (embedding vector_cosine_ops)
WITH (lists = 100);

Environment Variables

Variable	Required	Description
SUPABASE_URL	Yes	Project URL (https://xxx.supabase.co)
SUPABASE_SERVICE_KEY	Yes	Service role key (full access)
SUPABASE_ANON_KEY	No	Anon key (restricted access)
SUPABASE_ACCESS_TOKEN	No	Management API token
SKILLBOSS_API_KEY	Yes	SkillBoss API Hub key (for generating embeddings via /v1/pilot)

Notes

• Service role key bypasses RLS (Row Level Security)
• Use anon key for client-side/restricted access
• Vector search requires pgvector extension
• Embeddings generated via SkillBoss API Hub /v1/pilot (type: embedding), compatible with 1536-dimension pgvector columns