clickhouse-io

ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads. Use when writing ClickHouse schemas or queries, or when an analytical query is too slow.

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 ./skills/clickhouse-io/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 body is a dense, largely executable catalog of ClickHouse patterns with effective PASS/FAIL contrast examples, but it front-loads concept explanations Claude already knows, inlines everything rather than splitting reference material into bundle files, and presents batch/ETL/CDC workflows without any validation checkpoints. Moving the query catalog and pipeline patterns to reference files and adding verify steps would lift the weakest dimensions.

Suggestions

Cut the 'Overview' and 'Key Features' sections — Claude already knows ClickHouse is a column-oriented OLAP database — and lead with the pattern catalog itself.

Split the 'Common Analytics Queries' and 'Data Pipeline Patterns' sections into reference files (e.g., references/queries.md, references/pipelines.md) so SKILL.md stays a lean overview with clearly signaled one-level-deep pointers.

Add validation checkpoints to the batch and ingestion workflows: verify row counts after bulk inserts, handle insert errors with retry in the ETL/CDC examples, and confirm query results before treating a pipeline run as successful.

Dimension	Reasoning	Score
Conciseness	The body includes unnecessary explanation of concepts Claude already knows — "ClickHouse is a column-oriented database management system (DBMS) for online analytical processing (OLAP)" and a "Key Features" list of column storage and compression — which is padding beyond the mostly efficient pattern catalog, matching anchor 3 rather than anchor 4's minor over-explanation.	3 / 5
Actionability	Most examples are concrete, executable SQL (MergeTree DDL, sumMerge queries, system.query_log checks) that is copy-paste ready, but several TypeScript snippets call undefined helpers like extractFromPostgres() and bulkInsertToClickHouse(), leaving minor gaps that keep it at anchor 4 rather than 5.	4 / 5
Workflow Clarity	The body covers batch and database operations (bulk inserts, ETL via setInterval, CDC handlers) but none of these workflows include validation or verification checkpoints (no insert confirmation, no error recovery), and the rubric caps workflow clarity at 3 for batch/destructive operations without feedback loops; the PASS/FAIL comparisons are helpful but do not constitute checkpoints.	3 / 5
Progressive Disclosure	Sections are well-organized with clear headers, but ~440 lines of reference material (analytics query catalog, pipeline patterns, monitoring recipes) are all inlined in SKILL.md with no bundle files, so content that clearly belongs in separate reference files is inline — matching anchor 3 rather than anchor 4's appropriately split structure.	3 / 5
	Total	13 / 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.

A strong description in the style of the reference examples: it names the domain and capability areas, and pairs them with an explicit, concrete 'Use when...' trigger clause including the highly natural 'analytical query is too slow' phrase. Only minor polish is needed (replacing 'patterns/best practices' with concrete actions and adding a few synonyms).

Dimension	Reasoning	Score
Specificity	The description lists several specific capabilities ("query optimization", "analytics", "data engineering best practices") for a named domain, but "patterns" and "best practices" are generic nouns rather than fully concrete actions, matching anchor 4 rather than the comprehensive verb-driven coverage of anchor 5.	4 / 5
Completeness	Both what ("ClickHouse database patterns, query optimization, analytics, and data engineering best practices") and when ("Use when writing ClickHouse schemas or queries, or when an analytical query is too slow") are explicitly answered, with the 'when' clause containing concrete trigger phrases matching the anchor 5 example structure.	5 / 5
Trigger Term Quality	Natural user phrases are present ("ClickHouse", "writing ClickHouse schemas or queries", "an analytical query is too slow"), giving good keyword coverage; a few natural terms are missing (e.g., "OLAP", "slow query", "materialized view"), so it falls short of anchor 5's comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	"ClickHouse" is a specific named technology establishing a clear niche with distinct triggers; only minimal overlap risk exists through the generic word "analytics", matching anchor 5's clear-niche description.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: skills/clickhouse-io/SKILL.md
Commit: c70874f

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.