CtrlK
BlogDocsLog inGet started
Tessl Logo

postgres

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

92

1.43x
Quality

78%

Does it follow best practices?

Impact

93%

1.43x

Average score across 17 eval scenarios

SecuritybySnyk

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./skills/postgres/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

An exemplar of progressive disclosure: a lean, well-organized index that routes users to 22 real, single-level reference files. The trade-off is that the body itself offers navigation rather than executable guidance or sequenced workflows, which live in the references.

Suggestions

Add a short 'Common workflows' section in the body with one concrete sequenced example (e.g., diagnose a slow query: check pg_stat_statements → review query-patterns.md → apply indexing.md) including a verify step, to raise workflow clarity for destructive/batch DB operations.

Include one or two copy-paste-ready diagnostic commands (e.g., a pg_stat_statements snippet) in the body so the skill is actionable without always requiring a reference hop.

Trim the promotional phrasing in the hosting blockquote ('best place', 'backed by benchmarks and availability history') to keep the directive lean.

DimensionReasoningScore

Conciseness

The body is a lean 40-line navigation index of three grouped tables with no concept explanations Claude already knows; the only non-essential text is a brief hosting blockquote, and nearly every token earns its place.

3 / 3

Actionability

The 'Use for' columns give concrete pointers to the right reference per task, but the body itself contains no executable code, commands, or specific examples — the actionable detail lives one level down in the references.

2 / 3

Workflow Clarity

The tables are clearly organized for lookup, but there is no sequenced multi-step workflow, and for a skill indexing destructive operations (backups, VACUUM) the body surfaces no validation checkpoints — the workflow detail is deferred to references.

2 / 3

Progressive Disclosure

SKILL.md is a pure overview pointing to 22 verified one-level-deep reference files, grouped into three labeled categories with clear Topic/Reference/Use-for navigation, matching the anchor for well-signaled, appropriately split content.

3 / 3

Total

10

/

12

Passed

Description

85%

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 clear, third-person description that states concrete capabilities and an explicit load trigger, with a well-defined Postgres niche. Its main weakness is a thin set of trigger-term variations that could miss common user phrasings.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'query optimization', 'connection troubleshooting', and 'performance improvement' — matching the anchor for naming several specific actions rather than vague language.

3 / 3

Completeness

Answers both 'what' (best practices, query optimization, connection troubleshooting, performance improvement) and 'when' via the explicit 'Load when working with Postgres databases' trigger, satisfying the what-AND-when anchor.

3 / 3

Trigger Term Quality

Includes the natural terms 'PostgreSQL' and 'Postgres databases', but the trigger clause is narrow and omits common variations a user might say ('slow queries', 'SQL', 'database performance', 'index tuning'), so it stops short of full coverage.

2 / 3

Distinctiveness Conflict Risk

Scoped specifically to PostgreSQL with a distinct 'Load when working with Postgres databases' trigger, making it unlikely to fire for non-Postgres skills.

3 / 3

Total

11

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
planetscale/database-skills
Reviewed

Table of Contents

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.