postgresql-optimization

PostgreSQL database optimization workflow for query tuning, indexing strategies, performance analysis, and production database management.

Quality

33%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/postgresql-optimization/SKILL.md

Quality

Content

21%Scale 1-5

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

This skill is essentially a high-level table of contents that delegates all actual work to other skills without providing any concrete, executable guidance itself. It suffers from severe verbosity through repetitive phase structures while simultaneously lacking any actionable content—no SQL examples, no configuration values, no specific commands. The skill would be far more useful if it were condensed to a fraction of its size and included actual PostgreSQL commands and examples.

Suggestions

Add concrete, executable examples: include actual SQL for EXPLAIN ANALYZE, specific pg_stat_statements queries for finding slow queries, and example CREATE INDEX statements with realistic scenarios.

Add specific PostgreSQL configuration values or ranges (e.g., 'shared_buffers: typically 25% of RAM, e.g., `shared_buffers = 4GB` for a 16GB server') instead of just listing parameter names.

Include validation steps: after creating indexes, show how to verify they're being used (`SELECT * FROM pg_stat_user_indexes WHERE idx_scan = 0`); after config changes, show how to verify they took effect.

Consolidate the 7 nearly identical phase structures into a more concise format—the repetitive 'Skills to Invoke / Actions / Copy-Paste Prompts' template wastes significant tokens without adding value.

Dimension	Reasoning	Score
Conciseness	The skill is heavily padded with repetitive structure across 7 phases that all follow the same template. It explains obvious concepts ('Check database version', 'Review configuration') that Claude already knows, and the 'Copy-Paste Prompts' sections just say 'Use @skill-name to do X' which adds no real value. The checklist and quality gates sections are nearly identical and redundant.	2 / 5
Actionability	The content is entirely vague and abstract. There are no concrete SQL commands, no actual EXPLAIN ANALYZE examples, no specific configuration values, no executable code. Every 'action' is a high-level description like 'Tune shared_buffers' or 'Identify missing indexes' without any specifics on how to do it. The 'Copy-Paste Prompts' just delegate to other skills rather than providing actual guidance.	1 / 5
Workflow Clarity	While there is a rough 7-phase sequence, the steps within each phase are poorly defined bullet lists with no specifics. There are no validation checkpoints, no feedback loops for error recovery, and no guidance on what to do if optimization doesn't improve performance. For database operations (which can be destructive), the complete absence of validation steps and safety measures is a significant gap.	2 / 5
Progressive Disclosure	The skill references many external skills (@database-optimizer, @sql-optimization-patterns, etc.) and related workflow bundles, which suggests some progressive disclosure intent. However, no bundle files are provided, the references are not clearly signaled with links, and the main file itself is bloated with repetitive structure that could be condensed significantly.	3 / 5
	Total	8 / 20 Passed

Description

45%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 identifies a clear domain (PostgreSQL optimization) and lists relevant topic areas, but relies on categorical labels rather than concrete actions. It completely lacks a 'Use when...' clause, which significantly hurts its ability to serve as a reliable skill selector. The PostgreSQL specificity helps with distinctiveness but trigger terms could be more comprehensive.

Suggestions

Add an explicit 'Use when...' clause with trigger phrases like 'Use when the user asks about slow PostgreSQL queries, EXPLAIN plans, index creation, postgres performance issues, or production database tuning.'

Replace categorical labels with concrete actions, e.g., 'Analyzes EXPLAIN plans, recommends and creates indexes, rewrites slow queries, configures PostgreSQL settings for performance, monitors production database health.'

Include natural synonyms and variations users might say: 'postgres', 'pg', 'slow query', 'query plan', 'vacuum', 'table bloat', 'connection pooling'.

Dimension	Reasoning	Score
Specificity	Names the domain (PostgreSQL database optimization) and lists several areas (query tuning, indexing strategies, performance analysis, production database management), but these are more like categories than concrete actions. It doesn't specify what actions are performed within each area (e.g., 'creates indexes', 'analyzes EXPLAIN plans', 'rewrites slow queries').	3 / 5
Completeness	Provides a reasonable 'what' (PostgreSQL optimization workflow covering several areas) but completely lacks a 'when' clause. There is no 'Use when...' or equivalent trigger guidance, which per the rubric should cap completeness at 3, and since the 'what' is also somewhat categorical rather than concrete, a score of 2 is appropriate.	2 / 5
Trigger Term Quality	Includes relevant keywords like 'PostgreSQL', 'query tuning', 'indexing', 'performance analysis', and 'database management', but misses natural user phrases like 'slow query', 'EXPLAIN', 'index', 'postgres', 'db performance', 'query plan', or file/tool-specific terms users would naturally mention.	3 / 5
Distinctiveness Conflict Risk	Specifying 'PostgreSQL' narrows the domain significantly and distinguishes it from general database skills or other RDBMS-specific skills. However, there could be minor overlap with general database management or SQL optimization skills since terms like 'performance analysis' and 'production database management' are broad.	4 / 5
	Total	12 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/postgresql-optimization/SKILL.md
Commit: 57c135b

Reviewed: 3 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.