clickhouse-io

ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

57%

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

The body delivers highly actionable, executable ClickHouse code across many patterns, but it is a monolithic inline catalog with no progressive disclosure and only modest conciseness due to general-concept padding, and it lacks validation feedback loops for its batch/destructive operations.

Suggestions

Split detailed reference material (e.g., engine-family comparison, full analytics-query library, CDC pipeline details) into files under references/ and link to them from SKILL.md, leaving a concise overview plus quick-start patterns inline.

Add validation/checkpoint steps to batch and destructive workflows — e.g., verify row counts after bulk insert, and a validate-fix-retry loop for the ETL/CDC pipelines.

Trim the 'Overview' and 'Key Features' sections that restate general OLAP concepts Claude already knows, to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	Most of the body is lean, executable code with terse headers, but the 'Overview' section and 'Key Features' bullets ('Column-oriented storage', 'Data compression') restate general OLAP/ClickHouse concepts Claude already knows, matching anchor 2's 'mostly efficient but includes some unnecessary explanation'.	2 / 3
Actionability	Extensive fully executable SQL and TypeScript examples (MergeTree schemas, bulk/streaming inserts, materialized views, system.query_log monitoring, funnel/cohort queries) are copy-paste ready and specific, matching anchor 3.	3 / 3
Workflow Clarity	Content is organized as a labeled pattern catalog rather than a sequenced workflow, and for batch/destructive contexts (bulk insert, CDC, ETL) there are no validation checkpoints or verify-fix-retry loops; per the rubric guideline this caps workflow_clarity at 2 rather than 3, while clear section ordering keeps it above 1.	2 / 3
Progressive Disclosure	No references/scripts/assets bundle files exist and the entire ~445-line body is a single monolithic inline file with no links to separate reference material, matching anchor 1's 'monolithic wall of text'; it is below anchor 2 because there is no signaled one-level-deep reference structure at all.	1 / 3
	Total	8 / 12 Passed

Description

72%

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 a distinct ClickHouse niche with strong, natural trigger terms, but it lacks an explicit 'Use when...' clause and uses domain-area nouns rather than concrete verb-led actions, capping completeness and specificity.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers (e.g., 'Use when designing ClickHouse schemas, optimizing analytical queries, or migrating analytics workloads from PostgreSQL/MySQL').

Lead with concrete verb-led actions (e.g., 'Design MergeTree table schemas, optimize analytical queries, and build materialized views') instead of noun-led capability areas.

Dimension	Reasoning	Score
Specificity	Names the ClickHouse domain and several action areas ('query optimization, analytics, and data engineering') but uses noun-led capability areas rather than concrete verb-led actions, matching anchor 2; it falls short of anchor 3 which expects multiple discrete concrete actions like 'Extract text, fill forms, merge documents'.	2 / 3
Completeness	It states what the skill does (patterns, optimization, analytics, data engineering) but lacks any explicit 'Use when...' trigger clause, so per the judging guideline a missing trigger caps completeness at 2 rather than 3.	2 / 3
Trigger Term Quality	'ClickHouse', 'query optimization', 'analytics', and 'data engineering' are natural terms a user would say when needing this skill, giving good coverage comparable to the anchor-3 example; it is above anchor 2 because it does not miss common variations.	3 / 3
Distinctiveness Conflict Risk	'ClickHouse ... high-performance analytical workloads' is a clear, specific niche with distinct triggers unlikely to conflict with generic SQL or PostgreSQL skills, matching anchor 3.	3 / 3
	Total	10 / 12 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/everything-claude-code
Commit: 4130457

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.