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.

1.75x

Quality

69%

Does it follow best practices?

Impact

95%

1.75x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/all-skills/skills/supabase-automation/SKILL.md

Quality

Content

63%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.

A well-structured, highly actionable skill body that names exact tools, parameters, and failure modes rather than describing them. Its main weaknesses are redundancy between the per-workflow pitfalls, the 'Known Pitfalls' recap, and the Quick Reference table, plus the absence of any external reference files to offload the catalog material.

Suggestions

Deduplicate: keep each pitfall in exactly one place — either the workflow section or 'Known Pitfalls', not both — and drop or shrink the Quick Reference table that repeats the tool listings.

Move the Quick Reference table and consolidated pitfalls into references/ (e.g. references/tool-reference.md) linked from the body, so SKILL.md stays a lean overview.

Add one or two concrete example invocations (a sample filters array and a read-only SQL call) and a post-write verification step for mutating SQL (e.g. re-select the affected rows to confirm).

Dimension	Reasoning	Score
Conciseness	The body is dense and free of concept over-explanation, but the 'Known Pitfalls' section restates nearly every pitfall already given per-workflow (SQL timeout, array syntax, 42P01/42883, slug-vs-id, empty services array, null row_count) and the Quick Reference table duplicates the workflow tool listings, so it could be meaningfully tightened rather than merely trimmed.	3 / 5
Actionability	Each workflow gives concrete tool sequences with exact slugs, parameter names and formats (filters objects, 'created_at.desc', '^[a-z]{20}$', read_only) plus specific error-code remedies — mostly executable guidance that falls short of copy-paste-ready only because no literal example calls (e.g. a sample filters array or SQL invocation) are shown.	4 / 5
Workflow Clarity	Sequences are clearly ordered with [Prerequisite]/[Required] markers, pre-write validation ('Always use GET_TABLE_SCHEMAS or LIST_TABLES before writing SQL', read_only: true) and error-recovery guidance keyed to Postgres error codes, missing only a post-write verify/retry checkpoint to reach the top anchor.	4 / 5
Progressive Disclosure	Sectioning is clear, but all 230 lines live in a single SKILL.md with no references/ files — the Quick Reference table and the consolidated pitfall/catalog content clearly belong in separate reference files, so content that should be separate is inline.	3 / 5
	Total	14 / 20 Passed

Description

75%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.

A specific, well-scoped description with strong capability coverage and low conflict risk, but it omits any 'when to use' trigger clause, which both caps completeness and weakens its value for skill selection. Adding an explicit trigger sentence would move it to the top tier.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user mentions Supabase, wants to query or modify a Supabase database, run SQL, manage projects/orgs, or inspect schemas, tables, buckets, or edge functions.'

Add natural user phrasings and synonyms — 'run SQL', 'postgres', 'inspect table schema', 'storage buckets' — to improve trigger term coverage.

Move the meta-instruction 'Always search tools first for current schemas' into the skill body; it consumes description budget without helping triggering.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'database queries, table management, project administration, storage, edge functions, and SQL execution' — giving comprehensive coverage of the toolkit's surface, matching the top anchor rather than the 'minor gaps' of a 4.	5 / 5
Completeness	The 'what' is clear and concrete, but there is no 'Use when...' clause or equivalent trigger guidance — 'Always search tools first for current schemas' is an instruction, not a when-to-use trigger — which caps completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Good natural keyword coverage ('Supabase', 'database queries', 'SQL', 'table management', 'storage', 'edge functions') that users would plausibly say, but common variations and synonyms ('postgres', 'run SQL', 'buckets', 'inspect schema') are missing, so it does not reach the comprehensive synonym coverage of a 5.	4 / 5
Distinctiveness Conflict Risk	The description is tightly scoped to 'Supabase... via Rube MCP (Composio)', a clear niche with distinct triggers and minimal risk of firing for unrelated skills.	5 / 5
	Total	17 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: davepoon/buildwithclaude
Path: plugins/all-skills/skills/supabase-automation/SKILL.md
Commit: c9856ea

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

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.