postgres-patterns

PostgreSQL database patterns for query optimization, schema design, indexing, and security. Based on Supabase best practices.

1.12x

Quality

79%

Does it follow best practices?

Impact

96%

1.12x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./docs/ja-JP/skills/postgres-patterns/SKILL.md

Quality

Content

83%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 body is an exceptionally lean, actionable PostgreSQL reference with executable SQL for the common cases, but it lacks validation/verification checkpoints around the destructive config and security commands, which caps workflow clarity. Adding a brief verify step after the ALTER SYSTEM / REVOKE block would lift that dimension.

Suggestions

Add a verification step after the config template, e.g. 'Verify: SELECT pg_reload_conf(); then check SHOW max_connections; and confirm existing connections are unaffected before deploying.'

Add a guard before REVOKE/ALTER SYSTEM noting these are cluster-wide changes requiring a restart or reload and should be tested on a non-production instance first.

Consider splitting the anti-pattern detection queries into a separate reference file to push progressive_disclosure toward 5 while keeping SKILL.md as an overview.

Dimension	Reasoning	Score
Conciseness	A lean quick-reference of tables and executable SQL with almost no prose padding; it never explains concepts Claude already knows, and inline comments only justify non-obvious trade-offs (e.g. 'O(1) vs OFFSET').	5 / 5
Actionability	Copy-paste-ready SQL throughout — index creation, covering/partial indexes, RLS policies, UPSERT, cursor pagination, queue processing, anti-pattern detection, and config templates — covering the common PostgreSQL cases concretely.	5 / 5
Workflow Clarity	Although well-organized, the config-template section issues system-wide/destructive changes ('ALTER SYSTEM SET ...', 'REVOKE ALL ON SCHEMA public FROM public') with no validation or verification checkpoint, and the rubric caps database operations lacking feedback loops at 3.	3 / 5
Progressive Disclosure	Single self-contained file with clear section headers and a well-signaled '関連' (related) section pointing to peer skills/agents one level deep; not a 5 only because substantial content is inlined rather than split into reference files, though this is appropriate for a quick-reference.	4 / 5
	Total	17 / 20 Passed

Description

75%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 and well-scoped to PostgreSQL with four concrete capability areas, but it omits any 'when to use' trigger guidance, which the rubric penalizes by capping completeness at 3. Adding a 'Use when...' clause would raise the score materially.

Suggestions

Add an explicit trigger clause, e.g. 'Use when writing SQL queries, designing schemas, adding indexes, troubleshooting slow queries, or implementing RLS.'

Include natural user-facing synonyms such as 'slow queries', 'SQL', 'RLS', and 'database' alongside 'PostgreSQL' to improve trigger-term coverage.

Keep the third-person voice (it currently does) while adding the 'when' guidance so both what and when are answered concretely.

Dimension	Reasoning	Score
Specificity	Lists the PostgreSQL domain plus four concrete capability areas — 'query optimization, schema design, indexing, and security' — giving comprehensive coverage of specific actions, matching the multiple-concrete-actions anchor.	5 / 5
Completeness	The 'what' is clear (PostgreSQL patterns across four areas), but there is no 'when'/'Use when...' clause stating when Claude should invoke the skill; the rubric caps completeness at 3 when trigger guidance is missing.	3 / 5
Trigger Term Quality	Includes solid keywords ('PostgreSQL', 'query optimization', 'indexing', 'schema design', 'security') but is missing natural variations a user might say ('slow query', 'SQL', 'RLS', 'database'), so a few natural terms are absent.	4 / 5
Distinctiveness Conflict Risk	Clearly scoped to a PostgreSQL-specific niche with distinct triggers and minimal overlap risk against generic backend or data skills.	5 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: docs/ja-JP/skills/postgres-patterns/SKILL.md
Commit: e04ea0b

Reviewed: 2 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.