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

66%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/clickhouse-best-practices/SKILL.md

Quality

Discovery

47%

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 clearly identifies its niche (ClickHouse review) but is weak on specificity of what it actually does beyond 'checking 28 rules.' It uses imperative/instructional language ('MUST USE', 'Always read') rather than describing capabilities, and lacks concrete actions or outputs. The ClickHouse focus provides good distinctiveness but the description would benefit from listing specific review capabilities and more natural trigger terms.

Suggestions

Replace vague 'Contains 28 rules' with specific capabilities like 'Validates schema design, optimizes query performance, checks MergeTree engine configuration, reviews partition strategies, and identifies anti-patterns in ClickHouse SQL.'

Add a proper 'Use when...' clause with natural trigger terms: 'Use when the user asks about ClickHouse table design, query optimization, MergeTree configuration, materialized views, or ClickHouse best practices.'

Rewrite in third person descriptive voice (e.g., 'Reviews ClickHouse schemas and queries against 28 best-practice rules') instead of imperative instructions ('MUST USE', 'Always read').

Dimension	Reasoning	Score
Specificity	The description mentions 'reviewing ClickHouse schemas, queries, or configurations' and '28 rules' but does not list any concrete actions beyond 'reviewing' and 'providing recommendations'. It lacks specific capabilities like 'optimize query performance', 'validate schema design', or 'check index usage'.	1 / 3
Completeness	The 'when' is partially addressed with 'when reviewing ClickHouse schemas, queries, or configurations', but the 'what' is weak — it only says it contains 28 rules and that they must be checked. It doesn't clearly explain what the skill actually does or produces. The 'MUST USE' phrasing attempts to serve as a trigger but is directed at Claude's behavior rather than being a proper 'Use when...' clause.	2 / 3
Trigger Term Quality	Includes relevant keywords like 'ClickHouse', 'schemas', 'queries', and 'configurations' which users might naturally mention. However, it misses common variations like 'ClickHouse SQL', 'table design', 'MergeTree', 'materialized views', or 'query optimization'.	2 / 3
Distinctiveness Conflict Risk	ClickHouse is a specific technology, and the description clearly scopes to ClickHouse schemas, queries, and configurations. This is unlikely to conflict with other skills unless there are multiple ClickHouse-related skills.	3 / 3
	Total	8 / 12 Passed

Implementation

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a strong, well-structured skill that provides clear workflows for reviewing ClickHouse schemas, queries, and insert strategies. Its main weakness is redundancy—the same 28 rules are presented three different ways (review procedures, priority table, and quick reference), which inflates token usage without proportional value. The actionability and workflow clarity are excellent, with concrete checklists, ordered rule reading sequences, and a structured output format.

Suggestions

Consolidate the three overlapping rule listings (Review Procedures checklists, Rule Categories table, and Quick Reference) into a single reference section to reduce redundancy and save tokens.

Remove the 'When to Apply' section—Claude can infer activation triggers from the skill description and content, and this list restates what's already obvious from the review procedures.

Dimension	Reasoning	Score
Conciseness	The skill is fairly well-organized but contains significant redundancy: the Quick Reference section largely duplicates the Review Procedures section's rule listings, and the Rule Categories table adds yet another layer of the same information. The 'When to Apply' section lists triggers Claude could infer. However, the Langfuse-specific rules and review checklists are genuinely useful additions.	2 / 3
Actionability	The skill provides highly actionable guidance: specific rule files to read in order, concrete checklists for each review type, a structured output format template, and specific thresholds (e.g., 10K-100K rows, 100-1,000 partitions). The Langfuse-specific rules include concrete file paths and exact SETTINGS clauses to use. The citation format ('Per `rule-name`...') is explicit.	3 / 3
Workflow Clarity	The workflow is clearly sequenced with a 5-step priority order for answering questions, three distinct review procedures each with ordered rule file reading lists and validation checklists, and a structured output format that includes violations with current/required/fix structure. The checklists serve as validation checkpoints for each review type.	3 / 3
Progressive Disclosure	The skill is an excellent overview document that points to 28 rule files in `rules/` with clear naming conventions and one-level-deep references. Content is appropriately split: SKILL.md provides the workflow, checklists, and quick reference while detailed rule bodies live in individual files. Navigation is well-signaled with consistent naming prefixes and organized by category.	3 / 3
	Total	11 / 12 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: langfuse/langfuse
Commit: 6a26032

Reviewed: 4 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.