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.
68
83%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid skill description that clearly identifies a narrow, specific domain (GKG query profiling against ClickHouse) and provides explicit trigger scenarios. The trigger terms are natural and distinctive, making it easy for Claude to select this skill appropriately. The main weakness is that the specific actions could be more concrete—listing exact operations rather than general use-case categories.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (GKG queries, ClickHouse, query-profiler CLI) and some actions (optimizing query performance, comparing query plans, investigating slow queries, checking resource usage), but these are more like use-case categories than concrete specific actions like 'generate EXPLAIN plans' or 'capture execution metrics'. | 2 / 3 |
Completeness | Clearly answers both 'what' (profile GKG queries against ClickHouse with the query-profiler CLI) and 'when' (for optimizing query performance, comparing query plans, investigating slow queries, or checking ClickHouse resource usage). The 'For...' clause serves as an explicit trigger guidance equivalent to 'Use when...'. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'GKG queries', 'ClickHouse', 'query-profiler', 'query performance', 'query plans', 'slow queries', 'resource usage'. These are terms a user would naturally use when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: the combination of GKG, ClickHouse, and query-profiler CLI is very specific and unlikely to conflict with other skills. The domain is narrow and well-defined. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable skill with excellent executable examples and clear workflows for query profiling and A/B comparison. Its main weakness is length — the metrics interpretation guide and output structure documentation could be split into reference files, and some explanatory content about ClickHouse internals is unnecessary for Claude. Overall it serves as an effective operational guide.
Suggestions
Move the 'What to look at' metrics interpretation and 'Output structure' sections into a separate REFERENCE.md file, keeping only a brief summary and link in the main SKILL.md.
Trim explanations of ClickHouse concepts Claude already knows (e.g., CTE inlining, what read_rows means) to brief reminders or remove entirely.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with concrete examples, but includes some unnecessary explanation (e.g., 'No gRPC server or Rails needed', explaining what each metric means when Claude likely knows ClickHouse internals, and the 'Things to know' section has some padding). The 'What to look at' section explains ClickHouse concepts Claude already understands. Could be tightened by ~30%. | 2 / 3 |
Actionability | Excellent actionability throughout — every section provides copy-paste ready commands with realistic arguments, concrete JSON query examples, specific CLI flags, and exact output field paths. The A/B comparison workflow and diff commands are fully executable. | 3 / 3 |
Workflow Clarity | The A/B comparison workflow is clearly sequenced with numbered steps (run → change → rebuild → run → diff). The 'run, wait, then analyze' workflow is explicit. Multi-step processes have clear ordering. The separation of stdout/stderr is documented for pipeline correctness. Error handling for multi-query files is specified (failed queries recorded, run continues). | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear section headers, but it's a long monolithic document (~180 lines) that could benefit from splitting the 'What to look at' metrics reference and the detailed output structure into separate reference files. No bundle files are provided, and no external references are made, so everything is inline. | 2 / 3 |
Total | 10 / 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
- gitlabhq/orbit-knowledge-graph
- Commit
f5efc36
- 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.