postgresql-table-design

Use this skill when designing or reviewing a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

65%

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

The content is highly actionable with executable SQL and well-organized sections, but it is over-long for a single file with redundant type guidance and no progressive disclosure into separate reference files. Schema-evolution guidance also lacks an explicit validate/retry workflow.

Suggestions

Split large sections (Data Types, Indexing, Partitioning, JSONB Guidance, Extensions) into separate reference files linked from a concise overview in SKILL.md.

Remove the redundant "Do not use the following data types" list — consolidate it into the Data Types section to avoid repeating the timestamptz/text/numeric/identity guidance.

Add an explicit numbered schema-evolution workflow with validation checkpoints (e.g. test in transaction → validate → apply concurrently → verify) for destructive DDL.

Dimension	Reasoning	Score
Conciseness	Mostly efficient reference-style rules that assume Claude's competence, but the ~200-line body has redundancy — the "Do not use the following data types" section repeats guidance already given in "Data Types" — and could be tightened, so it falls short of every-token-earns-its-place.	2 / 3
Actionability	Provides concrete, executable DDL throughout — e.g. `BIGINT GENERATED ALWAYS AS IDENTITY`, `CREATE INDEX ON tbl (id) INCLUDE (name, email)`, and complete users/orders/profiles example tables — copy-paste ready.	3 / 3
Workflow Clarity	Schema evolution is a destructive/batch context; while safe patterns are given (transactional DDL testing, `CREATE INDEX CONCURRENTLY`), there is no explicit sequenced validate→fix→retry feedback loop, which caps this dimension at 2.	2 / 3
Progressive Disclosure	No bundle files exist and the entire body is a ~200-line monolithic SKILL.md; sections like Data Types, Indexing, Partitioning, and JSONB Guidance are clearly separable into reference files but are all inline with no navigation, matching the "content that should be separate is inline" anchor.	2 / 3
	Total	9 / 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.

The description is third-person, explicitly triggers on a well-defined niche, and clearly states both what and when. Its main gap is trigger-term breadth, missing common phrasings like "tables" or "database design" that a user would naturally say.

Suggestions

Add common user phrasings to the trigger clause, e.g. "Use when designing or reviewing PostgreSQL tables, database schema, or indexes."

Mention concrete objects the user would name ("tables", "indexes", "constraints") rather than only the abstract word "schema".

Dimension	Reasoning	Score
Specificity	Enumerates multiple concrete capability areas — "best-practices, data types, indexing, constraints, performance patterns, and advanced features" — beyond just naming the domain, matching the comprehensive-action anchor.	3 / 3
Completeness	Explicitly states both what it covers (best-practices, data types, indexing, etc.) and when to use it ("Use this skill when designing or reviewing a PostgreSQL-specific schema").	3 / 3
Trigger Term Quality	Includes natural terms ("PostgreSQL", "schema", "designing or reviewing") but omits common variations a user would actually say such as "table(s)", "database design", or "indexes", so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	"PostgreSQL-specific schema" is a clear niche distinct from generic SQL or other-database skills, making mis-triggering unlikely.	3 / 3
	Total	11 / 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: wshobson/agents
Commit: 5cc2549

Reviewed: about 4 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.