sql-insight

Translate natural language to SQL, optimize query performance, and interpret EXPLAIN plans for SQLite and PostgreSQL. Triggered when users ask to convert questions into SQL, improve slow queries, tune indexes, analyze execution plans, or mention keywords like NL2SQL, query tuning, or full table scan.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%

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

A highly actionable, well-structured CLI tool skill with concrete commands and a clear workflow, slightly held back by inline redundancy and content that could be split into references for better progressive disclosure.

Suggestions

Trim the opening line and Capabilities table, which restate the description, and merge overlapping Quick Start and Detailed Usage command listings to reduce redundancy.

Move the 13 optimization rules, EXPLAIN interpretation items, and output examples into a reference file (e.g. references/optimization_rules.md) linked from a short overview section to improve progressive disclosure.

Add an explicit feedback note to the NL→SQL workflow (e.g. "if optimize reports issues, revise the SQL and re-run optimize") to make the verification loop explicit.

Dimension	Reasoning	Score
Conciseness	Mostly efficient tables and commands that assume Claude's competence, but the intro line and Capabilities table restate the description, and Quick Start overlaps with Detailed Usage so it could be tightened.	2 / 3
Actionability	Fully executable, copy-paste-ready commands with concrete arguments and realistic output examples for every subcommand.	3 / 3
Workflow Clarity	The NL→SQL workflow is an explicit numbered sequence (schema → translate → optimize → explain) where the optimize and explain steps act as verification checkpoints; operations are read-only so no destructive-validation cap applies.	3 / 3
Progressive Disclosure	Well-organized sections with a single referenced script, but everything lives inline in one ~210-line file — the 13-rule table, EXPLAIN items, and output examples could be progressively disclosed to reference files.	2 / 3
	Total	10 / 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.

A strong, third-person description that names specific capabilities, an explicit trigger clause, and natural user keywords, well-scoped to a distinct SQL-assistant niche.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Translate natural language to SQL, optimize query performance, and interpret EXPLAIN plans" — and scopes them to SQLite and PostgreSQL.	3 / 3
Completeness	Clearly states what it does and includes an explicit "Triggered when..." clause answering when to use it.	3 / 3
Trigger Term Quality	Covers natural phrases a user would say ("convert questions into SQL", "improve slow queries", "tune indexes", "analyze execution plans") plus keywords (NL2SQL, query tuning, full table scan).	3 / 3
Distinctiveness Conflict Risk	Niche is narrow (SQL translation/optimization/EXPLAIN for SQLite and PostgreSQL) with distinct triggers, unlikely to collide with unrelated 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: zebbern/claude-code-guide
Path: skills/sql-insight/SKILL.md
Commit: af7d491

Reviewed: about 7 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.