sql-best-practices

Use this skill when writing SQL queries — selects, joins, aggregations, window functions, or schema modifications. Apply whenever SQL is needed to ensure correctness, safety, and performance.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%Weight 40%Scale 1-3

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

A lean, well-organized best-practices reference that respects the token budget and groups guidance clearly, but it stops at directives and SQL fragments rather than complete executable examples, leaving a couple of key patterns (notably parameterized queries and transaction wrapping) without a copy-pasteable illustration.

Suggestions

Add one complete worked example for the weakest guidance — e.g. a full parameterized query in application code (with the placeholder binding) so the 'never string interpolation' directive is copy-paste ready.

Illustrate the CTE and EXPLAIN patterns with a short runnable query block (e.g. 'WITH ... SELECT ... ' followed by 'EXPLAIN ANALYZE ...') instead of only naming the constructs.

Add a brief validate→fix loop for slow queries: run EXPLAIN ANALYZE, inspect the plan, refactor if a full scan appears, then re-check — this also strengthens feedback for database operations.

Dimension	Reasoning	Score
Conciseness	Lean bullet list with no re-explanation of what SQL is or how libraries work; every line is actionable guidance and assumes Claude's competence, matching the 'lean and efficient; every token earns its place' anchor.	3 / 3
Actionability	Gives concrete SQL fragments ('SELECT col1, col2', 'EXPLAIN ANALYZE', CTEs via 'WITH') but no complete worked examples, and the parameterized-query and transaction directives lack copy-pasteable illustration — fitting 'some concrete guidance but incomplete; missing key details' rather than the fully copy-paste-ready anchor at 3.	2 / 3
Workflow Clarity	A simple, single-purpose, under-50-line reference organized into clear Query quality / Safety / Naming sections; per the simple-skills note workflow clarity scores 3 when the single action is unambiguous and well-organized.	3 / 3
Progressive Disclosure	Self-contained under 50 lines with no bundle files and no need for external references, organized into well-labeled sections; the under-50-lines note allows a score of 3 on well-organized sections alone.	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 that concisely states what the skill covers (specific SQL operations) and when to invoke it via explicit trigger clauses, with natural keywords and a distinct SQL niche. It mirrors the rubric's good examples closely.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete SQL actions — 'selects, joins, aggregations, window functions, or schema modifications' — matching the 'lists multiple specific concrete actions' anchor rather than the partial-coverage anchor at 2.	3 / 3
Completeness	Explicit 'what' (the five SQL operation types) and explicit 'when' triggers ('Use this skill when writing SQL queries', 'Apply whenever SQL is needed'), so it is not capped at 2 for a missing trigger clause.	3 / 3
Trigger Term Quality	Natural terms a user would say ('SQL queries', 'selects, joins, aggregations', 'schema modifications', 'whenever SQL is needed') give good coverage, matching the score-3 anchor; it is not jargon-only like the score-1 example.	3 / 3
Distinctiveness Conflict Risk	SQL is a clear, well-scoped niche with distinct SQL-specific triggers, unlikely to fire for non-SQL skills; matches the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	12 / 12 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: aiming-lab/MetaClaw
Path: memory_data/skills/sql-best-practices/SKILL.md
Commit: 922caf3

Reviewed: 9 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.