CtrlK
BlogDocsLog inGet started
Tessl Logo

supabase-database

Supabase database operations including queries, CRUD operations, RLS policies, and PostgreSQL functions. Use when querying tables, managing data, implementing RLS, or writing database functions.

66

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is supabase-database in fernandezbaptiste/Skrillz

SKILL.md
Quality
Evals
Security

Quality

Content

76%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 body is a highly actionable, well-sectioned reference with executable code throughout and real, clearly labeled reference files for deeper material. Its main weaknesses are token duplication between the body and the reference files (filter operators, ordering, RLS patterns, plus the redundant Quick Reference table) and the complete absence of validation/error-handling feedback loops around destructive database operations, which caps workflow clarity at 3.

Suggestions

Add validation checkpoints around destructive and batch operations: show checking the `error` return after insert/update/delete and verifying the result with a follow-up `.select()` or `.single()`, with a fix-and-retry loop — this would lift the workflow_clarity cap.

Trim the Filters and Ordering & Pagination sections in SKILL.md to the few most common operators and point to references/query-operators.md for the full catalog; do the same for the RLS section vs references/rls-policies.md, keeping only one representative policy example inline.

Remove or slim the Quick Reference table, which duplicates the Basic Queries section almost entirely, or replace both with a single compact quick-start example.

DimensionReasoningScore

Conciseness

The body contains zero conceptual padding and assumes Claude's competence throughout — every section is code or a table. It falls short of anchor 5 because of real token redundancy: the Quick Reference table duplicates the Basic Queries section, and the ~90-line filter/operator catalog duplicates references/query-operators.md, so it could be tightened.

4 / 5

Actionability

All guidance is fully executable and copy-paste ready: complete JavaScript query chains, SQL policy definitions, a CREATE FUNCTION example, a gen-types command, and a typed client setup. The examples concretely cover the common cases (filters, joins, RLS CRUD policies, RPC, TypeScript types), matching the anchor 5 example.

5 / 5

Workflow Clarity

There is no multi-step workflow with validation checkpoints, and destructive/batch database operations (.delete(), UPDATE, bulk insert) are shown without any error-checking or verification guidance — the database-operations cap on workflow clarity applies. It stays at 3 rather than lower because the content is a per-operation reference where steps are coherent, but validation is entirely absent rather than a minor gap, so anchor 4 is not earned.

3 / 5

Progressive Disclosure

All three referenced files exist (references/rls-policies.md, query-operators.md, postgres-functions.md) and are clearly signaled with one-line descriptions in a References section, one level deep. It falls short of anchor 5 because the Filters/Ordering and RLS sections inline substantial content that is duplicated in those reference files — a moderate, more-than-minor organization gap.

4 / 5

Total

16

/

20

Passed

Description

83%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 strong description: it names the domain and multiple concrete capabilities, and provides an explicit 'Use when...' clause with natural trigger phrases that clearly answer both what and when. Its only weaknesses are minor — a few missing synonyms (SQL, row level security spelled out) and slight overlap risk with generic SQL/Postgres skills.

DimensionReasoningScore

Specificity

The description lists several concrete actions — "queries, CRUD operations, RLS policies, and PostgreSQL functions" — with only minor coverage gaps (e.g., migrations, triggers, indexes). It falls short of anchor 5 because coverage is not fully comprehensive, but goes beyond anchor 3's 1-2 actions.

4 / 5

Completeness

It explicitly answers both what ("Supabase database operations including queries, CRUD operations, RLS policies, and PostgreSQL functions") and when ("Use when querying tables, managing data, implementing RLS, or writing database functions") with concrete trigger phrases, matching the anchor 5 example pattern.

5 / 5

Trigger Term Quality

Natural user phrases like "querying tables", "managing data", "implementing RLS", and "writing database functions" are present. A few natural terms users would say are missing (e.g., "SQL", "row level security" spelled out, "select/insert/update"), so it sits at anchor 4 rather than 5.

4 / 5

Distinctiveness Conflict Risk

The "Supabase" qualifier carves out a clear niche with distinct triggers, though there is minor overlap risk with generic PostgreSQL/SQL skills. Not anchor 5 because database querying is a broadly shared trigger surface.

4 / 5

Total

17

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
fernandezbaptiste/Skrillz
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.