CtrlK
BlogDocsLog inGet started
Tessl Logo

clickhouse-best-practices

MUST USE when reviewing ClickHouse schemas, queries, or configurations. Contains 28 rules that MUST be checked before providing recommendations. Always read relevant rule files and cite specific rules in responses.

62

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/clickhouse-best-practices/SKILL.md
SKILL.md
Quality
Evals
Security

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 is rich with concrete, ClickHouse-specific guidance and a clear review workflow, but it is undermined by missing bundle files: every "read rules/<name>.md" instruction points to a `rules/` directory that is not present, and rule lists are redundantly repeated across three sections. Tightening the redundancy and shipping the referenced rule files would materially raise the score.

Suggestions

Bundle the referenced `rules/` directory (the 28 rule files listed in Review Procedures and Quick Reference) so the "Read these rule files in order" instructions are actually executable; until they exist, progressive disclosure and actionability are capped.

De-duplicate the rule listing: keep one canonical enumeration (e.g. the Quick Reference or the priority table) and have the Review Procedures sections link to it instead of restating the lists and the alter_sync rationale a second time in the checklist.

Add an explicit validation/verification step to the "How to Apply" workflow (e.g. "re-check each violation against the cited rule and confirm the fix compiles / passes prepareMigrations.test.ts") to lift workflow_clarity above the destructive/batch cap of 3.

DimensionReasoningScore

Conciseness

Mostly efficient and free of basic-concept padding, but the same rule set is enumerated three times (Review Procedures file lists, the Rule Categories by Priority table, and the Quick Reference) and the migration prose repeats the alter_sync/mutations_sync rationale in both the Langfuse section and the checklist, so it could be tightened; not a 4 because the redundancy exceeds minor trimming.

3 / 5

Actionability

Guidance is concrete and executable: specific file paths, exact template fragments like `{CLICKHOUSE_CLUSTERED_ONLY: SETTINGS alter_sync = 2}`, numeric thresholds (100-1,000 partitions, 10K-100K rows), and a copy-ready Output Format template; not a 5 because the primary action path ("Read these rule files in order") points at a `rules/` directory that is not bundled, so that instruction cannot actually be executed.

4 / 5

Workflow Clarity

The 5-step "How to Apply" priority order and the per-review-type ordered checklists give a clear sequence, but the top-level workflow lacks an explicit verify/validation checkpoint and the skill covers destructive batch operations (canonical migration ALTERs), so the destructive/batch cap of 3 applies despite the checklists partially mitigating it.

3 / 5

Progressive Disclosure

Sectioning and reference signaling are clear (ordered rule-file lists, named paths, one level deep), but scoring against the actual bundle structure reveals the referenced `rules/` directory and its ~28 rule files do not exist, so the overview-to-detail navigation is broken and substantial specialized content (the Langfuse rules) is inlined rather than split; matches the "some structure" anchor rather than a 4.

3 / 5

Total

13

/

20

Passed

Description

87%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 strong: it explicitly states both what the skill does and when to use it, with concrete ClickHouse-specific trigger phrases and low conflict risk. It could be marginally improved by enumerating a few more concrete review actions and adding common synonyms like "query optimization" or "migration".

DimensionReasoningScore

Specificity

Names the ClickHouse domain plus several concrete actions ("reviewing schemas, queries, or configurations", "read relevant rule files", "cite specific rules"), matching the anchor that lists several specific actions with minor coverage gaps; not a 5 because "reviewing" is a broad umbrella rather than a comprehensive enumeration of concrete operations.

4 / 5

Completeness

Explicitly answers both what ("Contains 28 rules that MUST be checked... Always read relevant rule files and cite specific rules") and when ("MUST USE when reviewing ClickHouse schemas, queries, or configurations") with concrete trigger phrases, matching the top anchor; the explicit "MUST USE when..." clause satisfies the trigger-guidance requirement so no cap applies.

5 / 5

Trigger Term Quality

Natural terms a user would say ("reviewing ClickHouse schemas, queries, or configurations") give good keyword coverage, matching the "good coverage, a few natural terms missing" anchor; not a 5 because synonyms and surface variants (e.g. "query optimization", "migration", "tuning") are absent.

4 / 5

Distinctiveness Conflict Risk

The ClickHouse-specific scope ("reviewing ClickHouse schemas, queries, or configurations") carves a clear niche with distinct triggers and minimal overlap with other skills, matching the "clear niche with distinct triggers; minimal conflict risk" anchor.

5 / 5

Total

18

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
langfuse/langfuse
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.