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

61%

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

65%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 delivers a strong, concrete pattern library with executable SQL/TypeScript examples and good PASS/FAIL contrast, but it is a monolithic single file with no progressive disclosure and no validation steps for batch data-ingestion operations. Some space is spent explaining ClickHouse basics Claude already knows.

Suggestions

Split the body into referenced files (e.g. references/query-patterns.md, references/ingestion.md, references/monitoring.md) and keep SKILL.md as a concise overview with clearly signaled links.

Add validation/verification checkpoints to batch ingestion and CDC workflows (e.g. verify row counts after bulk insert, reconcile source vs. target counts before/after sync).

Remove the '概述' section explaining what ClickHouse and columnar storage are — Claude already knows this — and de-duplicate the materialized-view query that repeats the AggregatingMergeTree example.

Dimension	Reasoning	Score
Conciseness	The bulk is lean, executable code with PASS/FAIL contrast, but the '概述' section explains what ClickHouse/OLAP is — concepts Claude already knows — and the materialized-view query largely repeats the AggregatingMergeTree query, matching 'efficient; minor instances of over-explanation'.	4 / 5
Actionability	Nearly all SQL and TypeScript examples are concrete and executable with PASS/FAIL contrast, but the ETL example calls undefined helpers (extractFromPostgres, bulkInsertToClickHouse) and the CDC example inserts one row per notification — minor gaps that keep it below fully copy-paste-ready.	4 / 5
Workflow Clarity	Content is organized as a pattern reference rather than a sequenced workflow, and batch operations (bulk inserts, streaming ingestion, CDC sync) include no validation or verification steps, which caps workflow clarity at 3 per the rubric guidelines.	3 / 5
Progressive Disclosure	The ~450-line body has clear section headers but no bundle files at all — monitoring queries, funnel/cohort recipes, and pipeline patterns that clearly belong in separate reference files are all inlined in SKILL.md, matching 'some structure but content that should be separate is inline'.	3 / 5
	Total	14 / 20 Passed

Description

58%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 correctly anchors on the distinctive ClickHouse domain and lists several concrete capability areas, but it omits any 'Use when...' trigger guidance and lacks natural trigger phrases users would say. Adding explicit activation conditions would substantially improve it.

Suggestions

Add a 'Use when...' clause with concrete triggers, e.g. 'Use when designing ClickHouse table schemas, optimizing slow ClickHouse queries, or migrating data from PostgreSQL/MySQL to ClickHouse.'

Include natural trigger phrases users would actually say, such as 'MergeTree', 'materialized view', 'batch insert', 'real-time dashboard', and 'time-series analysis', to improve trigger term coverage.

Replace the generic '高性能分析工作负载的数据工程最佳实践' with more concrete, distinctive capabilities to reduce overlap with generic data-engineering skills.

Dimension	Reasoning	Score
Specificity	The description names the domain and several specific action areas — "ClickHouse数据库模式、查询优化、分析...数据工程最佳实践" — matching the 'lists several specific actions; minor gaps' anchor, though 'best practices' and '分析' are generic enough to keep it below the comprehensive anchor 5.	4 / 5
Completeness	The 'what' is clear (schemas, query optimization, analytics, data engineering practices), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Relevant keywords like "ClickHouse", "查询优化", and "分析" are present, but natural user phrasings (e.g. 'migrate from PostgreSQL', 'MergeTree', 'slow query', 'materialized view') and synonyms are missing, matching 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	The explicit "ClickHouse" niche makes it mostly distinct from other skills, but the broad tail "高性能分析工作负载的数据工程最佳实践" could overlap with generic data-engineering or SQL skills, so it is not at the minimal-conflict anchor 5.	4 / 5
	Total	14 / 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: c70874f

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.