sql-expert
Expert system for generating, validating, and optimizing ClickHouse SQL. Use this when the user needs data, queries, or analysis.
75
71%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./resources/skills/sql-expert/SKILL.mdQuality
Discovery
42%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 correctly identifies the domain (ClickHouse SQL) and provides a basic structure with a 'Use when' clause, but suffers from overly generic trigger conditions that would cause conflicts with other data/query skills. The capabilities listed are reasonable but not highly specific, and the trigger terms miss natural ClickHouse-specific vocabulary users would employ.
Suggestions
Narrow the 'Use when' clause to ClickHouse-specific triggers: 'Use when the user mentions ClickHouse, columnar databases, MergeTree engines, or needs OLAP-style analytics queries'
Add more specific capabilities: 'write complex aggregations, optimize MergeTree table schemas, debug slow queries, create materialized views'
Include natural trigger terms users would say: 'ClickHouse', 'CH', 'columnar', 'OLAP', 'analytics database', 'time-series queries'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (ClickHouse SQL) and lists three actions (generating, validating, optimizing), but these are somewhat generic database operations rather than highly specific concrete actions like 'create materialized views' or 'optimize query performance with indexes'. | 2 / 3 |
Completeness | Has a 'what' (generating, validating, optimizing ClickHouse SQL) and includes a 'Use when' clause, but the trigger conditions are overly broad ('needs data, queries, or analysis') rather than specific to ClickHouse scenarios, making the 'when' weak and vague. | 2 / 3 |
Trigger Term Quality | Includes 'ClickHouse SQL', 'data', 'queries', and 'analysis' which are relevant but misses common variations users might say like 'database', 'table', 'SELECT', 'aggregation', or specific ClickHouse terms like 'MergeTree' or 'distributed tables'. | 2 / 3 |
Distinctiveness Conflict Risk | The trigger 'when the user needs data, queries, or analysis' is extremely generic and would conflict with virtually any data-related skill. Only 'ClickHouse' provides distinctiveness, but the broad triggers undermine this. | 1 / 3 |
Total | 7 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill file that demonstrates strong technical writing. It's concise yet comprehensive, with clear validation requirements, specific code examples showing good vs bad patterns, and a well-structured workflow. The content appropriately delegates to other skills and resources while maintaining focus on its core purpose.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, using bullet points and clear headers. It assumes Claude's competence with SQL and ClickHouse concepts without over-explaining basics. | 3 / 3 |
Actionability | Provides concrete, specific guidance with exact function calls (validate_sql, get_tables, explore_schema), specific syntax examples (Good vs Bad WHERE clauses), and clear tool usage patterns. | 3 / 3 |
Workflow Clarity | Section 4 provides a clear numbered workflow with explicit validation checkpoint, retry logic (max 3 attempts), and decision branching for different output types. The critical validation rule is prominently highlighted. | 3 / 3 |
Progressive Disclosure | Well-organized into logical sections (Schema Discovery, Syntax, Optimization, Execution). Appropriately references external resources (clickhouse-system-queries skill, references/system-query-log.md) without deep nesting. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 9 / 11 Passed | |
- Repository
- FrankChen021/datastoria
- Commit
68a8440
- 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.