database-optimizer

Expert database optimizer specializing in modern performance tuning, query optimization, and scalable architectures.

Quality

21%

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/database-optimizer/SKILL.md

Quality

Content

10%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 reads as a persona description or system prompt rather than an actionable skill file. It extensively catalogs what the optimizer 'knows' and 'does' without providing any concrete, executable guidance—no SQL examples, no specific tool commands, no actual optimization patterns. The vast majority of content describes capabilities Claude already has, wasting token budget on taxonomy rather than unique, actionable instructions.

Suggestions

Replace the capability lists with concrete, executable examples: show actual EXPLAIN ANALYZE output interpretation, specific index creation patterns, or N+1 detection queries that Claude can directly apply.

Add specific validation steps with real commands (e.g., 'Run EXPLAIN ANALYZE before and after optimization to verify improvement; if cost increases, revert the change').

Remove the 'Capabilities', 'Knowledge Base', and 'Behavioral Traits' sections entirely—these describe what Claude already knows. Replace with a focused playbook of specific optimization patterns with code examples.

Either provide the referenced `resources/implementation-playbook.md` bundle file with concrete implementation details, or inline the most critical actionable content directly in the skill.

Dimension	Reasoning	Score
Conciseness	Extremely verbose and padded. The content extensively lists capabilities, knowledge bases, and behavioral traits that Claude already knows. Most of the content is descriptive categorization rather than actionable instruction. The massive bullet-point lists of technologies and concepts add no value beyond what Claude already possesses as general knowledge.	1 / 5
Actionability	Almost entirely abstract and descriptive with no concrete code, commands, or executable examples. The 'Response Approach' is a generic high-level workflow. There are no SQL examples, no specific commands for profiling tools, no copy-paste ready optimization patterns. The 'Example Interactions' are just prompts, not demonstrations of how to respond.	1 / 5
Workflow Clarity	The 'Response Approach' provides a rough 9-step sequence but steps are vaguely defined ('Analyze current performance', 'Identify bottlenecks') with no specific tools, commands, or validation checkpoints. For a skill involving potentially destructive database operations (migrations, schema changes), there are no explicit validation or rollback steps.	2 / 5
Progressive Disclosure	References `resources/implementation-playbook.md` but no bundle files are provided, making this reference unverifiable. The massive amount of content (capabilities lists, knowledge base, behavioral traits) is all inlined in a monolithic fashion when it could be split into focused reference files. The structure uses headers but the content within each section is just bullet-point lists with no clear navigation hierarchy.	2 / 5
	Total	6 / 20 Passed

Description

32%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.

This description reads more like a resume headline than a functional skill description. It relies on broad buzzwords ('expert,' 'specializing,' 'modern') without specifying concrete actions or providing any trigger guidance for when Claude should select this skill. The lack of a 'Use when...' clause and absence of specific, actionable capabilities significantly weaken its utility for skill selection.

Suggestions

Add a 'Use when...' clause with natural trigger terms like 'slow query,' 'database performance,' 'indexing,' 'execution plan,' 'SQL optimization,' or specific database names.

Replace vague categories with concrete actions such as 'analyzes slow SQL queries, recommends index strategies, rewrites queries for performance, designs database schemas, reviews execution plans.'

Remove subjective qualifiers like 'Expert' and 'modern' which add no selection value, and use third-person verb phrases instead (e.g., 'Optimizes database queries...' rather than 'Expert database optimizer...').

Dimension	Reasoning	Score
Specificity	Names the domain (database optimization) and lists broad categories like 'performance tuning, query optimization, and scalable architectures,' but these are high-level buzzwords rather than concrete actions. No specific operations like 'rewrite slow queries,' 'add indexes,' or 'analyze execution plans' are mentioned.	2 / 5
Completeness	Provides a vague 'what' (database optimization, query optimization, scalable architectures) but has no 'when' clause at all. There is no 'Use when...' guidance or trigger phrases to help Claude know when to select this skill. Per rubric guidelines, missing 'Use when' should cap completeness at 3, and the 'what' is also vague, so this falls to 2.	2 / 5
Trigger Term Quality	Includes some relevant keywords like 'database,' 'performance tuning,' 'query optimization,' and 'scalable architectures,' but misses natural user phrases like 'slow query,' 'indexing,' 'execution plan,' 'SQL,' or specific database names (PostgreSQL, MySQL). Users are more likely to say 'my query is slow' than 'I need performance tuning.'	3 / 5
Distinctiveness Conflict Risk	Very broad terms like 'performance tuning' and 'scalable architectures' could overlap with general backend development skills, DevOps skills, or cloud infrastructure skills. 'Query optimization' is somewhat more specific but without naming specific databases or technologies, the overlap risk remains high.	2 / 5
	Total	9 / 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/database-optimizer/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.