cc-skill-clickhouse-io

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

Quality

50%

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/cc-skill-clickhouse-io/SKILL.md

Quality

Content

50%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 content is rich with executable ClickHouse SQL and code examples, but it is verbose, explains basic concepts Claude already knows, and lacks a sequenced workflow with validation checkpoints for its batch/write operations.

Suggestions

Trim the Overview and Best Practices sections — remove explanations of what ClickHouse is, what column-oriented storage means, and obvious GOOD/BAD commentary; keep only non-obvious ClickHouse-specific guidance.

Add an explicit end-to-end workflow (design table -> bulk insert -> query via materialized view -> monitor via system.query_log) with a validation checkpoint after inserts (e.g. verify row counts / run a sample aggregation) to lift workflow clarity above the batch-validation cap.

Move large reference blocks (full DDL templates, system-table monitoring queries, ETL/CDC code) into a references/ file and link from SKILL.md so the overview stays lean.

Dimension	Reasoning	Score
Conciseness	The body is a long monologue (~300+ lines) that explains concepts Claude already knows — e.g. the 'Overview' describing what ClickHouse and 'Column-oriented storage / Data compression' are, and '✅ GOOD / ❌ BAD' commentary restating obvious indexing rules — with significant padding throughout the Best Practices and Overview sections.	2 / 5
Actionability	Provides concrete, mostly copy-paste-ready SQL and TypeScript examples (MergeTree/ReplacingMergeTree DDL, materialized views, system.query_log monitoring, bulk-insert code), with only minor gaps such as the streaming-insert snippet being a stub.	4 / 5
Workflow Clarity	Sections are organized by topic but there is no end-to-end sequenced workflow; more importantly, batch insert / CDC / ETL operations involving writes have no validation or verification checkpoint, and the rubric caps batch/destructive skills without validation at 3.	3 / 5
Progressive Disclosure	Single-file skill with no references/scripts/assets bundle; it is organized into clear sections, but a large amount of reference-like material (full DDL templates, monitoring queries, ETL/CDC code) is inlined rather than split out, and there is no navigation to deeper material.	3 / 5
	Total	12 / 20 Passed

Description

51%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 niche and is reasonably specific, but it is missing an explicit 'Use when...' trigger clause and leans on category labels rather than concrete actions, capping completeness and trigger quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when working with ClickHouse, optimizing analytical queries, or designing columnar tables for high-throughput analytics.'

Replace abstract category labels ('best practices') with concrete actions like 'design MergeTree tables, optimize queries, build materialized views, and bulk-insert data.'

Include synonyms and natural phrasings users would say ('ClickHouse', 'columnar database', 'OLAP', '.sql analytics').

Dimension	Reasoning	Score
Specificity	Quotes 'patterns, query optimization, analytics, and data engineering best practices' — names the domain plus several concrete activity areas, but these are categories of work rather than discrete actions (it does not list things like 'optimize queries', 'design MergeTree tables', 'build materialized views').	3 / 5
Completeness	Has a clear 'what' (ClickHouse patterns for analytics/data engineering) but no 'Use when...' clause; per the rubric, a missing explicit trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural terms like 'query optimization', 'analytics', and 'data engineering', but misses common phrasings a user would actually say (e.g. 'ClickHouse query', 'tune ClickHouse', 'analytical workloads' is jargon-heavy) and lacks file-type or synonym coverage.	3 / 5
Distinctiveness Conflict Risk	'ClickHouse database patterns ... for high-performance analytical workloads' is a clearly distinct niche tied to a named product, with only minor overlap risk against generic SQL or data-engineering skills.	4 / 5
	Total	13 / 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: sickn33/antigravity-awesome-skills
Path: skills/cc-skill-clickhouse-io/SKILL.md
Commit: 1f67c44

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.