CtrlK
BlogDocsLog inGet started
Tessl Logo

sql-pro

Master modern SQL with cloud-native databases, OLTP/OLAP optimization, and advanced query techniques. Expert in performance tuning, data modeling, and hybrid analytical systems.

32

Quality

26%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/sql-pro/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

17%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/role description rather than an actionable skill file. It is dominated by extensive lists of capabilities, knowledge areas, and behavioral traits that Claude already possesses, while lacking concrete code examples, specific commands, executable workflows, or validation steps. The content would need a fundamental restructuring to be useful as a skill.

Suggestions

Replace the capability/knowledge/behavioral trait lists with concrete, executable SQL examples covering the most common use cases (e.g., window functions, EXPLAIN analysis, index creation patterns).

Add specific validation steps to the workflow, such as 'Run EXPLAIN ANALYZE and verify no sequential scans on large tables' or 'Test with LIMIT before running full queries on production.'

Provide copy-paste ready code snippets for key patterns like query optimization, partitioning, and CTE usage instead of just naming the concepts.

Remove sections that describe what Claude already knows (e.g., lists of database platforms, general SQL features) and focus only on project-specific conventions, preferred patterns, or non-obvious techniques.

DimensionReasoningScore

Conciseness

Extremely verbose and padded. The bulk of the content is long lists of capabilities, knowledge bases, behavioral traits, and example interactions that Claude already knows. These are descriptions of what an SQL expert does, not actionable instructions. The content reads like a resume or role description rather than a skill file.

1 / 5

Actionability

The Instructions section provides only four high-level steps ('Define query goals', 'Inspect schema', 'Optimize queries', 'Verify correctness') with no concrete code, commands, or executable examples. The 'Example Interactions' section lists prompts but provides no actual SQL examples, query patterns, or copy-paste ready code.

2 / 5

Workflow Clarity

There is a rough 4-step sequence in Instructions and an 8-step Response Approach, but both are vague and lack specific validation checkpoints. For a skill involving query optimization and potentially destructive operations on production databases, the absence of concrete validation steps (e.g., specific EXPLAIN commands, rollback procedures) is a significant gap.

2 / 5

Progressive Disclosure

The content is a monolithic wall of bullet-point lists with no references to external files and no meaningful structure beyond flat section headers. The massive capability lists should be either removed (Claude knows these) or split into reference files. There are no bundle files to support progressive disclosure.

2 / 5

Total

7

/

20

Passed

Description

36%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 reads more like a resume bullet point or marketing tagline than a functional skill description. It uses buzzword-heavy language ('Master modern SQL,' 'Expert in') without specifying concrete actions Claude can perform, and it completely lacks trigger guidance for when this skill should be selected. The first-person-adjacent 'Expert in' phrasing and lack of actionable specificity significantly weaken its utility for skill selection.

Suggestions

Add an explicit 'Use when...' clause with natural trigger phrases like 'Use when the user asks to write SQL queries, optimize database performance, design schemas, or work with databases like PostgreSQL, MySQL, or cloud data warehouses.'

Replace vague category labels with concrete actions: e.g., 'Writes and optimizes SQL queries, designs database schemas, creates indexes, analyzes query execution plans, and tunes OLTP/OLAP workloads.'

Remove marketing-style language ('Master,' 'Expert in') and use third-person active voice describing what the skill does, not what it claims expertise in.

DimensionReasoningScore

Specificity

Names the domain (SQL, databases) and mentions broad categories like 'performance tuning' and 'data modeling,' but these are high-level labels rather than concrete actions. No specific operations like 'write queries,' 'create indexes,' or 'design schemas' are listed.

2 / 5

Completeness

Provides a vague 'what' (SQL mastery, optimization, data modeling) but completely lacks any 'when' clause or trigger guidance. There is no 'Use when...' or equivalent explicit guidance for when Claude should select this skill.

2 / 5

Trigger Term Quality

Includes some relevant keywords like 'SQL,' 'OLTP,' 'OLAP,' 'performance tuning,' 'data modeling,' and 'cloud-native databases.' However, it misses natural user phrases like 'write a query,' 'optimize query,' 'database schema,' 'joins,' 'indexes,' or specific database names (PostgreSQL, MySQL, etc.).

3 / 5

Distinctiveness Conflict Risk

The mention of OLTP/OLAP and cloud-native databases provides some specificity, but terms like 'data modeling' and 'performance tuning' are broad enough to overlap with general database skills, backend development skills, or data engineering skills.

3 / 5

Total

10

/

20

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.