Skip to content
SkillModel-led1,003 tokens in use

SQL Pro

Optimizes SQL queries and schemas: reads execution plans, uses CTEs and window functions, adds covering indexes and ports across dialects.

12,471 stars on the repository MIT LicenseJeffallan/claude-skills · skills/sql-pro
/plugin install fullstack-dev-skills@fullstack-dev-skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing SQL Pro costs

114tokens idle
1,003tokens in use
13,871tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter15/15
  • Structure22/25
  • Examples15/15
  • Output15/15
  • Size15/15
  • Resources15/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity100
  • Maintenance100
  • Community60
  • Maturity36
  • Momentum40

SQL Pro gives the agent a workflow for slow queries and schema design: review the schema and query patterns, design set-based queries, analyze execution plans, add covering indexes and verify the result with EXPLAIN ANALYZE before documenting it.

The skill includes examples for a CTE with ROW_NUMBER, window function running totals, EXPLAIN ANALYZE interpretation and a before-and-after rewrite of a correlated subquery with a supporting covering index.

What You Get

  • A five-step workflow that ends with EXPLAIN ANALYZE verification
  • Examples for CTEs, window functions, EXPLAIN ANALYZE reading and a before-and-after optimization
  • Guidance on what to check in a plan: sequential scans, estimate gaps and buffer reads
  • A must-do list covering early filtering, EXISTS over COUNT, explicit NULL handling and covering indexes
  • An output layout with the optimized query, index rationale, plan analysis and before-and-after metrics
  • Reference files for query patterns, window functions, optimization, database design and dialect differences

Common Use Cases

  • Finding out why a query is slow and rewriting it
  • Writing ranking, running total and latest-row-per-group queries
  • Designing indexes for frequent queries
  • Moving queries between PostgreSQL, MySQL, SQL Server and Oracle

What Makes It Unique

The skill requires evidence before advice: the agent analyzes execution plans before recommending changes and reports before-and-after performance numbers. It covers four database dialects in one skill and has a reference for the differences between them.

Under The Hood

The skill is a SKILL.md with five reference files that the agent loads by topic. It ships no scripts. The examples are SQL for you to adapt. The workflow tells the agent to run EXPLAIN ANALYZE, which executes the query against your database, and to create indexes with CREATE INDEX, which changes the schema. The agent needs a database connection or pasted plans from you to follow those steps.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers