clickhouse-io

ClickHouse数据库模式、查询优化、分析以及高性能分析工作负载的数据工程最佳实践。

Quality

62%

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 ./docs/zh-CN/skills/clickhouse-io/SKILL.md

Quality

Content

76%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 strong, actionable ClickHouse pattern reference with executable SQL and TypeScript throughout and clean section structure. Its main weaknesses are the lack of validation/feedback loops in the batch ingestion and ETL workflows and some conceptual padding in the overview.

Suggestions

Add explicit validation checkpoints to the ETL and batch-insert workflows (e.g. verify row counts, retry on insert failure) so the destructive/batch operations include fix-and-retry feedback loops.

Trim the '概述' and '关键特性' sections that restate what ClickHouse/OLAP is, since Claude already knows these concepts.

Consider splitting the analytics-query catalog (time-series, funnel, cohort) into a separate reference file to deepen progressive disclosure for the larger sections.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean, executable SQL/TypeScript, with only minor over-explanation (the '概述' paragraph defining ClickHouse/OLAP and the '关键特性' bullet list of concepts Claude already knows) that could be trimmed, matching the 'efficient; minor instances of over-explanation' anchor.	4 / 5
Actionability	It provides copy-paste-ready, fully executable SQL DDL/queries and TypeScript ingestion code covering the common cases (MergeTree families, batch insert, materialized views, system monitoring), matching the 'fully executable; copy-paste ready code' anchor.	5 / 5
Workflow Clarity	A rough sequence exists in the ETL/CDC examples (Extract → Transform → Load) but there are no validation checkpoints or fix-and-retry feedback loops for the batch ingestion operations, so per the batch-operation cap workflow clarity stays at 3.	3 / 5
Progressive Disclosure	The document is well-organized with clear section headers (table design, query optimization, ingestion, materialized views, monitoring, analytics patterns) and no nested references, though all ~250 lines are inlined in SKILL.md with no split-out reference files, leaving a minor organization gap.	4 / 5
	Total	16 / 20 Passed

Description

48%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 clearly identifies the ClickHouse analytics domain but is noun-heavy and lacks concrete action verbs or an explicit 'Use when...' trigger clause. It is reasonably distinct but would benefit from rewrite into third-person verb phrases plus a trigger clause.

Suggestions

Rewrite the description using concrete third-person action verbs, e.g. 'Designs ClickHouse table schemas, optimizes analytical queries, and builds batch ingestion pipelines.'

Add an explicit 'Use when...' trigger clause listing natural user phrases (ClickHouse, MergeTree, OLAP, columnar analytics, time-series dashboards).

Include file-format or engine synonyms (MergeTree, .sql, Kafka integration) to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain thoroughly ("ClickHouse数据库模式、查询优化、分析...数据工程最佳实践") but uses noun-phrase topics rather than concrete action verbs like 'design tables' or 'optimize queries', matching the 'names the domain but actions are minimal or generic' anchor.	2 / 5
Completeness	A clear 'what' is present (ClickHouse schema/optimization/analytics/data-engineering best practices) but there is no 'Use when...' or equivalent 'when' clause, so per the judging guideline completeness is capped at 3.	3 / 5
Trigger Term Quality	It surfaces relevant keywords (ClickHouse, 查询优化, 分析, 数据工程) but misses common variations and synonyms users might say (OLAP, MergeTree, columnar, analytics workload), matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The ClickHouse-specific framing carves a clear niche with minimal conflict risk, though absence of explicit trigger phrases leaves minor overlap with general SQL/database skills, matching the 'mostly distinct; minor overlap risk' anchor.	4 / 5
	Total	12 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: docs/zh-CN/skills/clickhouse-io/SKILL.md
Commit: e04ea0b

Reviewed: 2 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.