cc-skill-clickhouse-io

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

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

Quality

Content

65%

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

The body is highly actionable with abundant executable code, but it carries unnecessary explanatory preamble, lacks validation checkpoints for its batch/destructive operations, and is a monolithic wall of content with no reference structure to split out detail.

Suggestions

Remove the Overview explanation of what ClickHouse is and the 'Key Features' list — Claude already knows this; keep only the patterns that add new information.

Add validation/verification checkpoints to batch and destructive workflows (e.g. verify row counts after bulk insert, confirm CDC payload schema before insert), and replace string-interpolated SQL with parameterized inserts.

Move the lengthy query collections (analytics queries, pipeline patterns) into reference files under references/ and link to them from the SKILL.md overview to add one-level-deep progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly useful executable code, but the Overview and 'Key Features' list explain what ClickHouse is and its basic capabilities — concepts Claude already knows — adding tokens that don't earn their place.	2 / 3
Actionability	Nearly every section ships complete, copy-paste-ready SQL and TypeScript (MergeTree DDL, aggregation queries, materialized views, CDC listener), with explicit GOOD/BAD contrasts; the code is concrete and executable.	3 / 3
Workflow Clarity	Sections are sequenced by topic, but batch/destructive operations (bulk insert, ETL, CDC) have no validation or verification checkpoints, and the insert example uses unparameterized string interpolation that would fail or be unsafe; per the rubric, missing feedback loops on batch operations cap this at 2.	2 / 3
Progressive Disclosure	Content is organized into clear sections, but everything lives inline in one ~430-line monolithic file with no references to separate files and no bundle files present, so there is no progressive disclosure structure to navigate.	2 / 3
	Total	9 / 12 Passed

Description

57%

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 identifies a clear niche and relevant terms but stays at the level of capability areas rather than concrete actions and omits an explicit use-when trigger, capping it at mid-level on most dimensions.

Suggestions

Add concrete actions, e.g. 'Design MergeTree tables, optimize analytical queries, and build aggregation pipelines in ClickHouse.'

Append a 'Use when...' clause with natural trigger terms such as 'ClickHouse', 'OLAP', 'columnar database', or 'analytical workloads'.

Include common variations users might say (e.g. 'column-store', 'SQL analytics') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names a concrete domain and several capability areas ('query optimization, analytics, and data engineering best practices') but lists no discrete actions (e.g. 'build tables', 'optimize queries', 'aggregate metrics'), so it does not reach the 'multiple specific concrete actions' bar.	2 / 3
Completeness	It states what the skill covers but provides no 'Use when...' clause or equivalent trigger guidance, so the 'when' half is only implied rather than explicit.	2 / 3
Trigger Term Quality	It surfaces relevant terms like 'ClickHouse', 'analytics', and 'query optimization' that users would say, but omits common natural variations such as 'OLAP', 'column-store', 'SQL', or 'columnar database'.	2 / 3
Distinctiveness Conflict Risk	The 'ClickHouse' and 'high-performance analytical workloads' framing carves out a clear, distinct niche with triggers unlikely to fire for other skills.	3 / 3
	Total	9 / 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
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: a3068b7

Reviewed: about 14 hours 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.