This is a high-quality skill that provides a clear, phased workflow for optimizing RLS policies with concrete SQL examples at every step. It respects Claude's intelligence by avoiding unnecessary explanations of Postgres concepts while providing specific, actionable patterns. The verification report phase with EXPLAIN ANALYZE checks ensures correctness validation.

Dimension	Reasoning	Score
Conciseness	The content is lean and efficient. Every section serves a purpose, there's no explanation of what RLS is or how Postgres policies work—it assumes Claude knows these concepts. The SQL examples are minimal but complete.	3 / 3
Actionability	Fully executable SQL examples are provided for each phase: audit queries, before/after policy rewrites, index creation with naming conventions, and SECURITY DEFINER function templates. Commands like `supabase db push` are specific and copy-paste ready.	3 / 3
Workflow Clarity	The 5-phase workflow is clearly sequenced (Audit → Wrap → Index → Encapsulate → Migrate) with explicit validation in Phase 5 ('HALT if any statement fails') and a comprehensive verification report phase that includes EXPLAIN ANALYZE checks and confirmation of zero bare auth.* calls. The feedback loop is present: re-query, verify index scans, confirm no inline JOINs.	3 / 3
Progressive Disclosure	Content is well-structured with clear phases as sections. The SECURITY DEFINER template is appropriately placed in a collapsible `<details>` block. References to external tiles (supabase-mcp-verification.md, tenant-isolation-rls.md) are one level deep and clearly signaled in pre-conditions.	3 / 3
	Total	12 / 12 Passed

Description

100%

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

This is an excellent skill description that clearly articulates specific technical actions, provides explicit trigger conditions via a 'Use when...' clause, and occupies a highly distinctive niche. It uses proper third-person voice and avoids vague language, making it easy for Claude to select this skill precisely when needed.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: enforcing SELECT-wrapped auth.uid() calls, mandatory B-Tree/GIN indexes on policy-referenced columns, and SECURITY DEFINER encapsulation of deep JOINs. These are highly specific, actionable techniques.	3 / 3
Completeness	Clearly answers both 'what' (optimizes RLS policies via three specific techniques) and 'when' with an explicit 'Use when...' clause listing four trigger scenarios: optimizing RLS performance, fixing policy full table scans, wrapping auth.uid in SELECT, or indexing columns used in RLS policies.	3 / 3
Trigger Term Quality	Includes strong natural keywords users would say: 'RLS', 'RLS policies', 'auth.uid', 'full table scans', 'indexing', 'RLS performance', 'SELECT', 'B-Tree', 'GIN indexes', 'SECURITY DEFINER'. These cover the domain well and match how developers would describe these problems.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive niche focused specifically on RLS policy performance optimization in what appears to be a Supabase/PostgreSQL context. The combination of auth.uid(), RLS policies, and specific index types makes it very unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Reviewed

2 months ago

Table of Contents

Discovery Implementation Validation