sql-database-assistant

Use when the user asks to write SQL queries, optimize database performance, generate migrations, explore database schemas, or work with ORMs like Prisma, Drizzle, TypeORM, or SQLAlchemy.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

82%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 dense, highly actionable SQL skill body with executable code, clear workflows, and well-signaled references. The main gaps are mild verbosity and inline content that could be offloaded to the existing reference files.

Suggestions

Move the per-ORM pattern sets and backup/restore command blocks into references (e.g., orm_patterns.md and a new backups reference) so SKILL.md stays a lean overview with signaled pointers.

Embed explicit "validate" checkpoints directly into the migration workflows (e.g., after each expand-contract step and after running migration_generator.py) rather than listing validation only in a separate strategies section.

Trim the Natural-Language-to-SQL "map nouns to tables / verbs to JOINs" heuristic, which restates a concept Claude can already derive, to tighten token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean, executable reference material (SQL templates, dialect tables, anti-pattern tables) assuming Claude's SQL knowledge, though the Natural-Language-to-SQL translation heuristic and some inline reference tables could be trimmed.	4 / 5
Actionability	Copy-paste-ready SQL examples, concrete introspection queries per dialect, and exact script invocations like `python scripts/query_optimizer.py --query "..." --dialect postgres` fully cover the common cases.	5 / 5
Workflow Clarity	The EXPLAIN workflow and expand-contract migration patterns are clearly sequenced, and validation guidance exists (pg_dump backups, validation queries, rollback, test restores), so the destructive-ops cap does not bind; but validation is not embedded as explicit checkpoints inside each destructive workflow.	4 / 5
Progressive Disclosure	Real, one-level-deep references are clearly signaled via blockquote "See references/..." markers and all referenced files (query_patterns.md, optimization_guide.md, orm_patterns.md) and scripts exist, but substantial inline content (4 ORM pattern sets, backup commands, dialect table) could be pushed into references.	4 / 5
	Total	17 / 20 Passed

Description

96%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, trigger-rich description that names concrete capabilities and specific ORM tools with an explicit Use-when clause. Slight overlap risk with sibling schema/migration skills keeps distinctiveness just below the top anchor.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "write SQL queries, optimize database performance, generate migrations, explore database schemas, or work with ORMs like Prisma, Drizzle, TypeORM, or SQLAlchemy" — with named tools, matching the comprehensive-coverage anchor.	5 / 5
Completeness	The explicit "Use when the user asks to..." clause states the triggers, and the enumerated actions double as the declarative "what", so both what and when are answered concretely; the Use-when cap does not apply.	5 / 5
Trigger Term Quality	Natural user phrases ("write SQL queries", "optimize database performance", "generate migrations", "explore database schemas") plus specific ORM names give comprehensive coverage including synonyms users actually say.	5 / 5
Distinctiveness Conflict Risk	The SQL/ORM operational niche is clear and distinct from pure schema design, but "generate migrations" and "explore database schemas" create minor overlap risk with the related database-designer / migration-architect skills.	4 / 5
	Total	19 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: alirezarezvani/claude-skills
Path: engineering/skills/sql-database-assistant/SKILL.md
Commit: 19392f7

Reviewed: ~5 hours 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.