Conciseness

At 509 lines the body extensively covers concepts Claude already knows — index type definitions ('B-Tree: Default, good for equality and range queries'), 'Avoid SELECT *', batch INSERT VALUES syntax, and basic EXPLAIN semantics — with several padded bad/good/better triplets for the same idea. Not 1 because the material is organized and mostly relevant rather than introductory filler; not 3 because large sections are pure restatement of standard database knowledge.

Actionability

Concrete, mostly copy-paste-ready SQL throughout — 'EXPLAIN (ANALYZE, BUFFERS, VERBOSE)', 'CREATE INDEX idx_users_cursor ON users(created_at DESC, id DESC)', the pg_stat_statements monitoring queries. Not 5 because of minor gaps: the Python batch example uses 'WHERE user_id IN (?)' with a list (not executable as written) and 'WHERE id IN (1, 2, 3, 4, 5, ...)' contains a literal ellipsis.

Workflow Clarity

The body is a topic catalog (concepts → patterns → advanced → pitfalls), not a sequenced optimization process; there is no 'identify via pg_stat_statements → EXPLAIN ANALYZE → apply fix → re-verify' loop, and validation is absent despite this being a database-operation skill, which caps the score at 3 and the missing sequence pulls it to 2. Not 1 because the section ordering does loosely imply an approach (monitoring queries appear, EXPLAIN is introduced first).

Progressive Disclosure

The Resources section lists seven bundle paths ('references/postgres-optimization-guide.md', 'assets/index-strategy-checklist.md', 'scripts/analyze-slow-queries.sql', etc.), but none of these files exist in the bundle — every reference is dead. Combined with ~500 lines of reference-grade detail inlined in SKILL.md (material the missing files were meant to hold), navigation fails. Not 3 because the references are clearly signaled yet point to nothing, which is worse than unclear signaling; not 1 because the section structure itself is well organized.

Specificity

Quotes 'Master SQL query optimization, indexing strategies, and EXPLAIN analysis' and 'eliminate slow queries' — several concrete, specific actions with only minor coverage gaps (no database-specific triggers). Not 5 because 'dramatically improve database performance' is promotional padding rather than a concrete capability; not 3 because it names more than 1-2 concrete actions.

Completeness

Explicitly answers both: what ('SQL query optimization, indexing strategies, and EXPLAIN analysis... eliminate slow queries') and when (a concrete 'Use when' clause with three trigger scenarios). Matches the anchor-5 example structure; not 4 because the when-clause is already explicit and specific.

Trigger Term Quality

'Use when debugging slow queries, designing database schemas, or optimizing application performance' contains natural phrases users would say. Not 5 because common variations are missing — users would also say 'add an index', 'N+1 queries', 'query plan', 'slow query log'; not 3 because the included terms are natural rather than jargon-only.

Distinctiveness Conflict Risk

The SQL performance niche with triggers like 'debugging slow queries' and 'EXPLAIN analysis' is mostly distinct. Not 5 because 'designing database schemas' is broad and overlaps with general schema-design or database-modeling skills; not 3 because the core triggers are clearly database-performance-specific.