Tessl • The management layer for AI agent skills

SkillPublic

clickhouse-io

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

1.21x

Quality

68%

Does it follow best practices?

Impact

100%

1.21x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/clickhouse-io/SKILL.md

Quality

Content

57%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 strong, concrete, executable examples across the full range of ClickHouse topics, with effective GOOD/BAD contrasts. Its weaknesses are padding that teaches concepts Claude already knows, missing validation/feedback loops in batch and pipeline workflows, and a monolithic single-file structure that inlines reference-level material rather than splitting it into bundle files.

Suggestions

Remove or trim the 'Overview' and 'Key Features' sections — Claude already knows what ClickHouse and columnar storage are.

Add validation and error-recovery steps to batch-insert, ETL, and CDC workflows (e.g. verify inserted row counts, check system.query_log for failures, retry logic on insert errors).

Move the analytics query catalog (retention, funnel, cohort) and data pipeline patterns into separate reference files under references/ and keep SKILL.md as a concise overview with clearly signaled links.

Dimension	Reasoning	Score
Conciseness	The bulk of the body is lean, executable code, but the 'Overview' and 'Key Features' sections explain what ClickHouse is ("column-oriented database management system (DBMS) for online analytical processing (OLAP)") — a concept Claude already knows — plus minor padding like the closing "Remember:" note. This matches 'mostly efficient with some unnecessary explanation' rather than anchor 2's 'several padded sections'.	3 / 5
Actionability	The body is dominated by concrete, mostly executable SQL and TypeScript with useful GOOD/BAD contrasts, matching 'mostly executable guidance with minor gaps'. It falls short of fully copy-paste ready because the bulk-insert example builds SQL via string interpolation (an injection/escaping hazard) and some snippets depend on undeclared context (e.g. 'clickhouse' and 'dataSource' in the streaming example).	4 / 5
Workflow Clarity	The ETL and CDC sections present rough sequences (Extract → Transform → Load; LISTEN → insert), but batch-insert and data-pipeline workflows include no validation, error handling, or verification steps, and the rubric explicitly caps workflow clarity at 3 for batch/database operations without feedback loops. It is above anchor 2 because sequences are listed and reasonably defined.	3 / 5
Progressive Disclosure	The single SKILL.md inlines ~430 lines covering table design, query optimization, ingestion, monitoring, analytics queries, and pipeline patterns with no bundle files (references/, scripts/, assets/ are absent), so content that clearly belongs in separate reference files (e.g. retention/funnel/cohort queries, ETL/CDC pipelines) is inline. It scores 3 rather than 2 because the in-file section structure is substantial and easy to navigate, not minimal.	3 / 5
	Total	13 / 20 Passed

Description

65%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 is strongly distinctive thanks to naming ClickHouse explicitly, with good natural keyword coverage, but it reads as a topic list rather than a statement of concrete actions. Its main weakness is the complete absence of any 'when to use' trigger guidance, which caps completeness and limits practical activation value.

Suggestions

Add an explicit trigger clause, e.g. 'Use when working with ClickHouse, migrating analytics workloads from PostgreSQL/MySQL, or optimizing OLAP queries.'

Replace generic nouns ('patterns', 'best practices') with concrete actions such as 'design MergeTree table schemas, optimize analytical queries, batch-insert data, and build materialized views for real-time aggregations'.

Include common synonyms users might say — 'OLAP', 'columnar database', 'time-series analytics' — to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ("ClickHouse database") and a few activity areas ("query optimization", "analytics", "data engineering"), but the framing relies on generic nouns like "patterns" and "best practices" rather than concrete actions, matching the anchor for naming a domain with limited concrete actions. It falls short of the next anchor, which requires several specific operations like the PDF example's 'extracts text, fills forms, converts pages to images'.	3 / 5
Completeness	The 'what' is clear (ClickHouse patterns, query optimization, analytics, data engineering), but there is no 'Use when...' clause or any equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3. It is above anchor 2 because the 'what' is specific and concrete, not vague.	3 / 5
Trigger Term Quality	Natural keywords users would say are present — "ClickHouse", "query optimization", "analytics", "data engineering" — giving good coverage. It is not a 5 because common variations and synonyms such as "OLAP", "columnar", "materialized views", or "time-series" are missing.	4 / 5
Distinctiveness Conflict Risk	"ClickHouse" names a clear niche with distinct triggers, making it highly distinguishable from generic SQL, database, or analytics skills with minimal conflict risk. This matches the anchor for a clear niche with distinct triggers.	5 / 5
	Total	15 / 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: valeriibeck-star/claude-skills
Path: skills/clickhouse-io/SKILL.md
Revision: 0bda8b8

Reviewed: 2 days ago

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.

clickhouse-io

Table of Contents

Is this your skill?