clickhouse-best-practices

MUST USE when reviewing ClickHouse schemas, queries, or configurations. Contains 28 rules that MUST be checked before providing recommendations. Always read relevant rule files and cite specific rules in responses.

Quality

72%

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 ./.agents/skills/clickhouse-best-practices/SKILL.md

Quality

Content

57%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 skill body is well-structured as a navigational hub over a rules/ bundle with clear per-review-type procedures, but it is verbose due to repeated rule listings across several sections and lacks inline executable examples. Tightening the duplicate catalogs and adding validation feedback loops would lift the weaker dimensions.

Suggestions

Consolidate the rule listings: the 'Review Procedures', 'Rule Categories by Priority', and 'Quick Reference' sections repeat the same rule names — keep one canonical index and link to the rest.

Add a brief inline example or the single most-impactful rule excerpt so the body is actionable without requiring every rule file to be opened first.

For schema and mutation reviews (destructive/batch operations), add an explicit validate-then-proceed checkpoint (e.g. dry-run ALTER, verify parts) so the workflow has a feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is largely a catalog and quick-reference of rule names duplicated across multiple sections (Review Procedures, Rule Categories by Priority, Quick Reference, When to Apply), which is repetitive padding rather than net-new guidance Claude does not already know.	3 / 5
Actionability	It points to specific rule files and gives checklist items, but provides no inline code, commands, or concrete examples — guidance is descriptive ('Read these rule files', 'Check for') rather than executable in the body itself.	3 / 5
Workflow Clarity	Review procedures are clearly sequenced per review type with ordered rule-file lists and checklists, and the priority application order is explicit, though there are no explicit validate/retry feedback loops for batch or destructive schema operations.	4 / 5
Progressive Disclosure	The SKILL.md acts as an overview pointing one level deep into a rules/ directory and a compiled AGENTS.md, with rule files named consistently; however the quick-reference duplicates inline content that already lives in those referenced files.	4 / 5
	Total	14 / 20 Passed

Description

87%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 is strong: it explicitly states both what the skill does and when to use it, uses a clear MUST USE trigger, and is tightly scoped to ClickHouse. It would benefit from a few more natural synonyms or file extensions for trigger terms, but there is no over-claiming or fluff.

Dimension	Reasoning	Score
Specificity	Describes concrete actions ('reviewing ClickHouse schemas, queries, or configurations', 'read relevant rule files', 'cite specific rules') and names the domain clearly, though the actions are review-oriented rather than a broad list of distinct capabilities.	4 / 5
Completeness	Explicitly answers both 'what' (contains 28 rules to check before recommending) and 'when' ('MUST USE when reviewing ClickHouse schemas, queries, or configurations') with a concrete trigger phrase.	5 / 5
Trigger Term Quality	Includes natural user-facing terms ('ClickHouse', 'schemas', 'queries', 'configurations') and the explicit 'MUST USE when reviewing' trigger, but lacks common synonyms or file extensions a user might naturally say.	4 / 5
Distinctiveness Conflict Risk	Scoped tightly to ClickHouse-specific review with a clear niche and a 'MUST USE' trigger tied to ClickHouse artifacts, minimizing overlap with generic SQL or database skills.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: MapleTechLabs/maple
Path: .agents/skills/clickhouse-best-practices/SKILL.md
Commit: e387359

Reviewed: 1 day 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.