CtrlK
BlogDocsLog inGet started
Tessl Logo

supabase-automation

Automate Supabase database queries, table management, project administration, storage, edge functions, and SQL execution via Rube MCP (Composio). Always search tools first for current schemas.

Install with Tessl CLI

npx tessl i github:davepoon/buildwithclaude --skill supabase-automation
What are skills?

72

Does it follow best practices?

Validation for skill structure

SKILL.md
Review
Evals

Evaluation results

100%

55%

Customer Purchase History Export

Tool sequence and pagination for table reads

Criteria
Without context
With context

RUBE_SEARCH_TOOLS first

0%

100%

LIST_ALL_PROJECTS prerequisite

0%

100%

Schema inspection before query

50%

100%

SELECT_FROM_TABLE for reads

0%

100%

Case-sensitive table name quoted

100%

100%

PostgreSQL array syntax

100%

100%

Pagination with offset+limit

100%

100%

No use of RUN_SQL_QUERY for basic reads

0%

100%

Without context: $0.2085 · 1m 17s · 13 turns · 17 in / 4,057 out tokens

With context: $0.3889 · 1m 35s · 18 turns · 432 in / 4,578 out tokens

100%

32%

Supabase Organization Security Audit

Org audit: slug vs id, API key masking, service health

Criteria
Without context
With context

RUBE_SEARCH_TOOLS first

0%

100%

LIST_ALL_ORGANIZATIONS for slug

50%

100%

Slug used for member listing

0%

100%

Non-empty services array

100%

100%

API keys masked in output

100%

100%

API keys not logged

100%

100%

Graceful 401/403 handling

80%

100%

LIST_ALL_PROJECTS prerequisite

100%

100%

Without context: $0.4199 · 1m 57s · 24 turns · 164 in / 7,150 out tokens

With context: $0.3649 · 1m 24s · 18 turns · 686 in / 4,993 out tokens

85%

35%

Enterprise Customer Onboarding Data Import

SQL write operations: array syntax, identifier quoting, schema-first

Criteria
Without context
With context

RUBE_SEARCH_TOOLS first

0%

0%

GET_TABLE_SCHEMAS before inserts

41%

100%

BETA_RUN_SQL_QUERY for INSERT

25%

100%

PostgreSQL array syntax

100%

100%

Double-quoted mixed-case identifiers

0%

53%

Batched inserts

100%

100%

Project ref format noted

100%

100%

LIST_ALL_PROJECTS prerequisite

0%

100%

read_only false for writes

62%

100%

Without context: $0.2980 · 1m 46s · 15 turns · 82 in / 6,326 out tokens

With context: $0.4024 · 1m 46s · 17 turns · 428 in / 5,654 out tokens

Evaluated
Agent
Claude Code

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.