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.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

92%

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

The content is a dense, actionable, and well-sequenced guide with copy-paste-ready commands and clear multi-step workflows. Its main weakness is progressive disclosure: it is a long monolithic file with inline reference material that could be split into separate reference files.

Suggestions

Move the detailed 'Output structure' and 'What to look at' field references into a separate references file (e.g. references/output-fields.md) and link to it from SKILL.md, keeping the body as a concise overview with worked examples.

De-duplicate the output-format guidance: 'Use --format json for compact JSON' and 'Default output format is json (compact). Use --format pretty' cover the same thing in two places — consolidate into one.

Consider extracting the many near-identical 'mise query:profile' command variations into a short reference table or examples file to tighten the body further.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — copy-paste commands and concise output-field explanations with no padding about what ClickHouse or the JSON DSL is — though a couple of format-related notes are lightly duplicated (e.g. compact-vs-pretty JSON appears in two places).	3 / 3
Actionability	It provides fully executable, copy-paste-ready commands throughout — 'mise build', 'mise query:profile -- ...', env-var setup, and 'mise query:diff' — with concrete examples per feature, matching the copy-paste-ready anchor.	3 / 3
Workflow Clarity	The A/B comparison is a clear 5-step numbered sequence (run → change → rebuild → re-run → diff) and the 'run, wait, then analyze' workflow is explicit; operations are read-only profiling so the absence of validation checkpoints is not penalized.	3 / 3
Progressive Disclosure	Sections are well-organized with clear headers, but the document is a fairly long monolithic single file with detailed output-structure reference content kept inline, and no bundle files exist to split material one level deep.	2 / 3
	Total	11 / 12 Passed

Description

100%

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, third-person, and clearly answers both what the skill does and when to use it with explicit trigger phrasings. It is well-scoped to a distinct niche and free of vague fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Profile GKG queries', 'optimizing query performance', 'comparing query plans', 'investigating slow queries', 'checking ClickHouse resource usage' — matching the multiple-specific-actions anchor rather than the domain-and-some-actions level below.	3 / 3
Completeness	States what it does ('Profile GKG queries against ClickHouse with the query-profiler CLI') and an explicit when ('For optimizing query performance, comparing query plans...'), so it clearly answers both what AND when with explicit triggers, unlike the level-2 anchor whose 'when' is only implied.	3 / 3
Trigger Term Quality	Natural phrasings a user would say — 'optimizing query performance', 'comparing query plans', 'investigating slow queries', 'ClickHouse resource usage' — give good coverage, above the 'some relevant keywords but missing variations' level.	3 / 3
Distinctiveness Conflict Risk	A clear niche (GKG queries against ClickHouse via the query-profiler CLI) with distinct triggers makes it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: gitlabhq/orbit-knowledge-graph
Commit: 00ca361

Reviewed: 4 days 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.