clickhouse-io
ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.
40
37%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./docs/ja-JP/skills/clickhouse-io/SKILL.mdQuality
Discovery
32%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 the domain (ClickHouse) and broadly names capability areas but lacks specific concrete actions and entirely omits explicit trigger guidance ('Use when...'). The vague terms like 'patterns' and 'best practices' reduce its effectiveness for skill selection, and the broad analytics/data engineering language could cause overlap with other database-related skills.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about ClickHouse queries, table engines, MergeTree optimization, or analytical database design.'
Replace vague terms like 'patterns' and 'best practices' with specific concrete actions such as 'design MergeTree table schemas, write optimized aggregation queries, configure materialized views, troubleshoot query performance.'
Include additional natural trigger terms users might say, such as 'columnar database', 'OLAP', 'MergeTree', 'ReplacingMergeTree', 'ClickHouse SQL', or '.ch' to improve keyword coverage and distinctiveness.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (ClickHouse database) and some general action areas (query optimization, analytics, data engineering best practices), but doesn't list specific concrete actions like 'write MergeTree table definitions' or 'optimize GROUP BY queries'. The terms 'patterns' and 'best practices' are somewhat vague. | 2 / 3 |
Completeness | Describes what the skill covers at a high level but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' portion is also fairly weak/vague, warranting a score of 1. | 1 / 3 |
Trigger Term Quality | Includes relevant keywords like 'ClickHouse', 'query optimization', 'analytics', and 'data engineering', which users might naturally say. However, it's missing common variations and specific terms like 'columnar database', 'MergeTree', 'materialized views', 'OLAP', or file format mentions that users working with ClickHouse would reference. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'ClickHouse' specifically provides some distinctiveness from generic database or SQL skills. However, terms like 'analytics', 'data engineering best practices', and 'query optimization' are broad enough to overlap with skills for other analytical databases (e.g., BigQuery, Snowflake, DuckDB). | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides highly actionable, executable ClickHouse examples covering a wide range of patterns, which is its primary strength. However, it is excessively verbose, includes unnecessary explanations of concepts Claude already knows (OLAP basics, columnar storage benefits), and packs everything into a single monolithic file without any progressive disclosure. The lack of validation checkpoints in multi-step workflows like ETL and CDC is also a notable gap.
Suggestions
Remove the overview section explaining what ClickHouse is and its key features—Claude already knows this. Start directly with table design patterns.
Split content into separate files: keep SKILL.md as a concise overview with links to QUERY_PATTERNS.md, TABLE_DESIGN.md, DATA_PIPELINES.md, and MONITORING.md.
Add validation/verification steps to multi-step workflows: e.g., after creating materialized views, show how to verify data is flowing correctly; after ETL loads, show how to validate row counts.
Trim the analytics query examples to 2-3 representative patterns instead of exhaustively covering time-series, retention, funnel, and cohort analysis.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~350+ lines. It explains basic concepts Claude already knows (what OLAP is, what columnar storage is, what ClickHouse's key features are). The overview section is entirely unnecessary. Many patterns are exhaustively listed (retention analysis, funnel analysis, cohort analysis, CDC, ETL) when a more focused selection would suffice. The best practices section restates common knowledge. | 1 / 3 |
Actionability | The skill provides fully executable SQL queries and TypeScript code examples throughout. CREATE TABLE statements, INSERT patterns, monitoring queries, and materialized view definitions are all copy-paste ready with concrete column names, types, and realistic data patterns. | 3 / 3 |
Workflow Clarity | While individual patterns are clear, multi-step processes like the ETL pipeline and CDC setup lack validation checkpoints. The data insertion section shows good/bad patterns but doesn't include error handling or verification steps. The materialized view workflow doesn't mention how to validate that the view is working correctly. | 2 / 3 |
Progressive Disclosure | The entire skill is a monolithic wall of content with no references to external files. All content—table design, query optimization, data insertion, materialized views, monitoring, analytics queries, data pipelines, and best practices—is crammed into a single file with no progressive disclosure structure. This would benefit greatly from splitting into separate reference files. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- affaan-m/everything-claude-code
- Commit
64cd1ba
- Reviewed
Table of Contents
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.