postgres

PostgreSQL best practices, query optimization, connection troubleshooting, and performance improvement. Load when working with Postgres databases.

1.43x

Quality

67%

Does it follow best practices?

Impact

93%

1.43x

Average score across 17 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/postgres/SKILL.md

Quality

Content

58%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.

The skill is an exemplary progressive-disclosure index: lean, well-organized, and pointing to real one-level-deep reference files. Its weakness is that SKILL.md itself contains no executable guidance or decision workflow, leaving actionability and sequencing entirely to the bundled references.

Suggestions

Add a short 'Quick start' or decision section with 2-3 concrete commands or SQL snippets (e.g. how to inspect a slow query) so the body is actionable on its own.

Include a brief triage workflow (e.g. 'For slow queries: check pg_stat_statements -> review indexes -> EXPLAIN ANALYZE') to give sequence and validation checkpoints.

Add a one-line note on verifying changes safely (e.g. test in a branch, check EXPLAIN before/after) given database operations can be destructive or batch-oriented.

Dimension	Reasoning	Score
Conciseness	The body is a lean overview table of references with one-line 'Use for' descriptors; it explains nothing Claude already knows and every line earns its place.	5 / 5
Actionability	The body provides navigation pointers ('Use for' columns) but no concrete commands, queries, or examples a user could execute directly from SKILL.md; actionable detail is deferred entirely to the references.	2 / 5
Workflow Clarity	There is no multi-step sequence for common tasks (e.g. diagnose a slow query, audit indexes) and no validation checkpoints, which matters because database operations are batch/destructive-adjacent; only a grouped topic listing is present.	2 / 5
Progressive Disclosure	It is a clear overview with one-level-deep references organized into three labeled tables, each reference pointing to a real file in references/ with a concise purpose column, making navigation easy.	5 / 5
	Total	14 / 20 Passed

Description

76%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.

The description is specific, third-person, and includes an explicit load trigger, distinguishing it well within a clear Postgres niche. It could improve by listing more concrete action verbs and broadening natural trigger-term coverage.

Suggestions

Add more concrete action verbs (e.g. 'diagnose slow queries', 'tune indexes', 'size connection pools') to raise specificity.

Expand the 'Load when' trigger to mention specific situations like slow queries, vacuuming, replication, or connection pool issues.

Include common synonyms such as 'PostgreSQL' and 'SQL' so the description matches more natural user phrasing.

Dimension	Reasoning	Score
Specificity	Names the Postgres domain and several concrete action areas ('query optimization', 'connection troubleshooting', 'performance improvement'), but each is a category rather than a fully enumerated set of actions, leaving minor coverage gaps.	4 / 5
Completeness	It clearly states what the skill does and includes an explicit 'Load when working with Postgres databases' trigger, but the 'when' clause is fairly terse and could name more specific triggering situations.	4 / 5
Trigger Term Quality	Natural terms like 'Postgres databases' and 'query optimization' are present and would be said by users, but common synonyms/variations (e.g. 'PostgreSQL', 'SQL tuning', 'slow queries') are missing.	4 / 5
Distinctiveness Conflict Risk	It targets a clear niche (Postgres operations) with distinct triggers, so it is unlikely to be selected for unrelated skills.	5 / 5
	Total	17 / 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: planetscale/database-skills
Path: skills/postgres/SKILL.md
Commit: 73b20b7

Reviewed: 15 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.