sql-expert

Expert system for generating, validating, and optimizing ClickHouse SQL. Use this when the user needs data, queries, or analysis.

Quality

76%

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 ./resources/skills/sql-expert/SKILL.md

Quality

Content

77%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 efficient, actionable rule set with a strong validated workflow and feedback loop. Its main weakness is progressive disclosure: it references a references/ file and an external skill that are not present in the bundle.

Suggestions

Ship the referenced 'references/system-query-log.md' file (or remove the reference) so the deferred-to resource actually resolves.

Trim the top 'CRITICAL RULE' banner since mandatory validation is already enforced in the Section 4 workflow, reducing repetition.

Add at least one complete executable example query to lift actionability from fragments to copy-paste-ready.

Dimension	Reasoning	Score
Conciseness	The body is largely lean bullet-point rules with concrete examples and assumes Claude's knowledge, but the emphatic 'CRITICAL RULE' banner repeats the mandatory-validation point already covered in the workflow section.	4 / 5
Actionability	Provides concrete, executable guidance — specific syntax rules (fully qualified names, no trailing semicolons, LIMIT) and a bad/good primary-key filter example — though most examples are fragments rather than complete copy-paste queries.	4 / 5
Workflow Clarity	Section 4 gives a clear Generate → Validate → Decide sequence with an explicit mandatory validation checkpoint and a feedback loop ('If invalid: Read the error, fix the SQL, and retry (max 3 attempts)'), appropriate for database operations.	5 / 5
Progressive Disclosure	Sections are well-organized, but the body instructs loading 'references/system-query-log.md' via skill_resource and defers to a 'clickhouse-system-queries' skill, while no references/ directory (or bundle files) exists — a dangling reference that undermines navigation.	3 / 5
	Total	16 / 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 cleanly states a concrete capability set and an explicit trigger clause, landing solidly above average. It could be sharpened by tying the trigger to SQL/ClickHouse-specific phrases to reduce overlap with generic data-analysis skills.

Suggestions

Add SQL/ClickHouse-specific trigger terms (e.g., 'when the user asks for ClickHouse queries, SQL, or database analysis') to improve trigger_term_quality and distinctiveness.

Tie the 'when' clause more concretely to the ClickHouse domain rather than the generic 'data, queries, or analysis'.

Consider mentioning schema discovery or optimization as a capability to round out specificity.

Dimension	Reasoning	Score
Specificity	Names the ClickHouse SQL domain and three concrete actions — 'generating, validating, and optimizing' — giving good coverage, though it omits ancillary capabilities like schema discovery that appear in the body.	4 / 5
Completeness	Both 'what' (generating, validating, optimizing ClickHouse SQL) and 'when' ('Use this when the user needs data, queries, or analysis') are explicitly present, but the 'when' is somewhat generic rather than tied to concrete SQL/ClickHouse triggers.	4 / 5
Trigger Term Quality	The trigger clause 'when the user needs data, queries, or analysis' uses natural terms users would say, but misses obvious synonyms like 'SQL' and 'ClickHouse' in the trigger itself.	4 / 5
Distinctiveness Conflict Risk	The ClickHouse SQL niche is distinctive, but the broad trigger 'needs data, queries, or analysis' creates minor overlap risk with general analytics or database skills.	4 / 5
	Total	16 / 20 Passed

Validation

81%

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 — 13 / 16 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: FrankChen021/datastoria
Path: resources/skills/sql-expert/SKILL.md
Commit: d0859a2

Reviewed: 15 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.