clickhouse-io

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

Quality

52%

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-TW/skills/clickhouse-io/SKILL.md

Quality

Content

55%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.

A content-rich, actionable reference with strong executable SQL and TypeScript examples, but it is monolithic with no progressive disclosure, repeats background Claude already knows, and lacks validation checkpoints for its batch/ETL/CDC operations. Strong on actionability, weaker on structure and workflow safety.

Suggestions

Move the general overview ('key features', column-store explanation) out of SKILL.md or trim it heavily, since Claude already knows what ClickHouse is.

Add validation checkpoints to the batch-insert, ETL, and CDC pipelines (e.g. verify inserted row counts, retry on failure, confirm sync lag) so destructive/batch operations have feedback loops.

Split the long document into one-level-deep reference files (e.g. references/query-optimization.md, references/data-pipelines.md, references/monitoring.md) and have SKILL.md serve as a concise overview with clear links.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with compact SQL/TypeScript blocks, but it opens with general ClickHouse background ('ClickHouse 是一個列式資料庫管理系統... 關鍵特性：列式儲存/資料壓縮...') that Claude already knows, and inline comments restate the obvious (e.g. '良好：先使用索引欄位'), which could be tightened.	3 / 5
Actionability	It provides extensive copy-paste-ready SQL DDL and TypeScript insert/streaming/CDC examples covering the common cases, with PASS/FAIL contrasts; only minor gaps (e.g. some example tables like 'trades' are referenced but never defined via DDL) keep it from a 5.	4 / 5
Workflow Clarity	Content is organized by topic rather than as a sequenced workflow, and the data-pipeline/ETL/CDC and batch-insert sections perform batch and destructive operations without any validation or verification checkpoints (no 'verify row counts', no error/retry loop); per the rubric this caps workflow_clarity at 3.	3 / 5
Progressive Disclosure	The body is one large monolithic document (~430 lines) with section headers but no bundle files and no one-level-deep references; content that could live in separate references (full API/reference, ETL patterns, monitoring queries) is all inlined, so structure is present but not split for navigation.	3 / 5
	Total	13 / 20 Passed

Description

50%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 a ClickHouse-specific niche and lists several relevant capability areas, but it lacks an explicit 'Use when...' trigger clause and its capability terms are category-level rather than concrete enumerated actions. It is solid but not exceptional.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when working with ClickHouse, optimizing OLAP queries, or building analytical pipelines on columnar data.'

Replace category-level terms with concrete actions (e.g. 'design MergeTree tables, optimize analytical queries, build materialized views') to raise specificity.

Include natural user phrases and synonyms such as 'OLAP', 'columnar database', 'analytics SQL', or 'ClickHouse SQL' to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (ClickHouse) and several concrete capability areas ('query optimization', 'analytics', 'data engineering best practices'), but these are categories rather than enumerated concrete actions like 'extract text', 'fill forms', 'merge documents'; it lists 3-4 areas without being comprehensive or fully concrete.	3 / 5
Completeness	It gives a clear 'what' (the patterns and practices it covers) but has no 'Use when...' clause or equivalent trigger guidance, so per the rubric a missing 'when' caps completeness at 3.	3 / 5
Trigger Term Quality	It contains relevant terms ('ClickHouse', 'query optimization', 'analytics') but lacks the natural phrases and synonyms a user would say (e.g. 'OLAP', 'column-store', 'SQL queries', 'materialized views', '.ch'), and offers no natural-language trigger variants.	3 / 5
Distinctiveness Conflict Risk	The ClickHouse-specific framing creates a clear niche distinct from general SQL/database skills, with only minor overlap risk against a generic 'SQL' or 'data engineering' skill; it is mostly distinct.	4 / 5
	Total	13 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: affaan-m/ECC
Path: docs/zh-TW/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.