CtrlK
BlogDocsLog inGet started
Tessl Logo

clickhouse-query-profiling

Profile GKG queries against ClickHouse with the query-profiler CLI. For optimizing query performance, comparing query plans, investigating slow queries, or checking ClickHouse resource usage.

65

Quality

77%

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 ./.claude/skills/clickhouse-query-profiling/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%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 highly actionable with comprehensive copy-paste-ready command examples and clear section organization. The main gap is the absence of explicit validation/verification checkpoints in the multi-query and diffing workflows, given that batch runs can produce partial failures.

Suggestions

Add an explicit verification step after multi-query runs, e.g. 'Check the output JSON for any {"error": ...} entries and re-run failing queries individually to debug.'

For the A/B comparison workflow, add a checkpoint to confirm the before/after files exist and are non-empty before running `mise query:diff`.

Tighten the 'Things to know' and 'What to look at' sections by merging closely related bullets to improve token efficiency.

DimensionReasoningScore

Conciseness

The body is mostly lean and code-forward with minimal over-explanation of concepts Claude already knows; a few explanatory passages (e.g. the 'Things to know' bullets and 'What to look at' detail) are useful but could be tightened slightly.

4 / 5

Actionability

Provides copy-paste-ready, fully executable commands across all common cases (basic search, EXPLAIN, profiling, health, multi-query, diffing) with concrete flag usage and example query JSON.

5 / 5

Workflow Clarity

The A/B comparison and 'run, wait, then analyze' workflows are clearly sequenced with explicit steps, but validation/verification checkpoints are implicit (no explicit validate->fix->retry loop despite batch/multi-query runs where queries can fail).

4 / 5

Progressive Disclosure

Content is well-organized into clear sections (Build, Configuration, Running, Output, A/B comparison, Diffing) with no nested references; it is a self-contained overview rather than relying on multi-level file references, which fits a skill without external bundle files.

5 / 5

Total

18

/

20

Passed

Description

70%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 specific and well-targeted to a distinct niche with a clear 'what' and reasonable 'when' guidance. It could improve by adding more natural user-facing trigger phrases and synonyms alongside the technical terminology.

Suggestions

Add a 'Use when...' clause with natural user phrasing such as 'Use when the user asks to profile a ClickHouse query, compare query plans, or investigate why a GKG query is slow.'

Include common synonyms users might say (e.g. 'ClickHouse query plans', 'EXPLAIN', 'query benchmarking') to broaden trigger term coverage.

Consider naming file or query types users would reference (e.g. '.json DSL queries') to improve trigger term quality.

DimensionReasoningScore

Specificity

Names the concrete action ('Profile GKG queries against ClickHouse with the query-profiler CLI') plus several specific uses (optimizing performance, comparing query plans, investigating slow queries, checking resource usage); not quite comprehensive enough for a 5.

4 / 5

Completeness

Has a clear 'what' (profile queries and get back stats/plans/profiling/health) and a 'when' clause ('For optimizing query performance, comparing query plans, investigating slow queries, or checking ClickHouse resource usage'), though the trigger guidance could be more explicit with concrete user phrasing.

4 / 5

Trigger Term Quality

Includes some natural terms ('query performance', 'slow queries', 'query plans', 'ClickHouse resource usage') but relies on fairly technical jargon and lacks common synonyms or variations a user would naturally say.

3 / 5

Distinctiveness Conflict Risk

Targets a clearly distinct niche (GKG JSON DSL queries against ClickHouse via the query-profiler CLI) with unique triggers and minimal overlap risk with other skills.

5 / 5

Total

16

/

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
gitlabhq/orbit-knowledge-graph
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.