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.

56

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/supabase-automation/SKILL.md

The canonical home for this skill is supabase-automation in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

61%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is well-structured and richly actionable with concrete tool sequences, parameters, and pitfalls, but it repeats pitfalls across sections and lacks explicit post-write verification loops for destructive SQL operations. Splitting the parameter reference and adding a validate step would raise the weaker dimensions.

Suggestions

Add an explicit validation step to destructive workflows: after INSERT/UPDATE/DELETE via RUN_SQL_QUERY, re-query (e.g. SELECT with read_only: true) to verify the change, and on error fix-and-retry — this uncaps workflow_clarity.

Remove the duplicate 'Known Pitfalls' section or collapse it into cross-references to the per-workflow Pitfalls to eliminate the redundancy dragging conciseness.

Include one fully worked example tool call with all arguments populated (e.g. a SELECT_FROM_TABLE with project_ref, table, filters, order, limit) to push actionability to 5.

DimensionReasoningScore

Conciseness

The body is dense with genuinely useful operational detail and avoids explaining concepts Claude already knows, but the standalone 'Known Pitfalls' section largely re-states pitfalls already given per workflow (20-letter ref format, array syntax, case-sensitive quoting, ERROR 42P01/42883), creating noticeable redundancy.

3 / 5

Actionability

Concrete tool slugs, exact parameter formats (e.g. '^[a-z]{20}$'), filter operator lists, and error codes give mostly executable guidance; the gap is the absence of any fully worked example call showing all arguments filled in.

4 / 5

Workflow Clarity

Workflows are clearly sequenced with [Prerequisite]/[Required]/[Optional] tags and connection-status validation in setup, but the destructive SQL-write paths (INSERT/UPDATE/DELETE via RUN_SQL_QUERY) lack an explicit verify-then-retry feedback loop, so workflow clarity is capped at 3 per the destructive-operations guideline.

3 / 5

Progressive Disclosure

The single file is well organized into Prerequisites, Setup, Core Workflows, Common Patterns, Known Pitfalls, and a Quick Reference table with no nested references; the main gap is that the detailed per-tool parameter reference could be split into a separate file to slim the overview.

4 / 5

Total

14

/

20

Passed

Description

66%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description clearly conveys the skill's domain and breadth of capabilities and names a distinctive niche, but it omits any explicit 'Use when' trigger guidance and is light on natural-language synonyms. Adding a trigger clause would lift completeness and distinctiveness.

Suggestions

Append a 'Use when...' clause naming concrete trigger phrases, e.g. 'Use when the user wants to query or manage a Supabase database, run SQL, inspect schemas, manage projects/orgs, edge functions, or storage buckets.'

Add natural synonyms such as 'Postgres' alongside 'Supabase' and 'SQL' so the description matches more varied user phrasings.

Tighten 'table management' and 'project administration' into more concrete actions (e.g. 'list and inspect tables', 'list projects and organizations') to push specificity toward 5.

DimensionReasoningScore

Specificity

Lists several concrete action areas — 'database queries, table management, project administration, storage, edge functions, and SQL execution' — giving broad coverage, though the actions are stated at domain level rather than as discrete concrete operations.

4 / 5

Completeness

It clearly states what the skill does, but there is no 'Use when...' clause or equivalent explicit trigger guidance — the second sentence ('Always search tools first for current schemas') is an instruction, not a when-trigger, so completeness is capped at 3 per the guidelines.

3 / 5

Trigger Term Quality

Names the core trigger 'Supabase' plus capability keywords users would say (queries, SQL, edge functions, storage), but omits common synonyms such as 'Postgres' and lacks file-extension cues.

4 / 5

Distinctiveness Conflict Risk

The 'Supabase ... via Rube MCP (Composio)' framing carves a distinct niche with low conflict risk, but the absence of explicit trigger phrases leaves minor overlap ambiguity with generic database skills.

4 / 5

Total

15

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
Reviewed

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.