query-performance

Validate what a ClickHouse query actually costs before merging it — at production scale through read-only environment access, or on a revived Testcontainers dataset extrapolated to 20k/500k/1M entities. Use when a DAO query changes, when an endpoint is slow, or when a reviewer asks "what does this cost at scale".

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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.

A tightly written, expert-level methodology with a clear validated workflow and an excellent reporting template. Its one real weakness is progressive disclosure: the body leans on several referenced files that are not bundled, leaving those navigations broken.

Suggestions

Bundle the referenced files (rendering.md, environments.md, instrumentation.md) under references/ so the inline 'see X.md' links resolve, or inline the minimal content those references were meant to provide.

Add at least one concrete, copy-paste-ready probe (e.g. the reference-count CTE comparison query or a settings snippet) to lift actionability from methodology-level to fully executable.

Verify the opik-backend bundle files (clickhouse.md, testing.md) actually exist in the bundle, or rephrase the Related section so it does not present missing files as available references.

Dimension	Reasoning	Score
Conciseness	Dense and lean throughout, assuming Claude's competence — it never explains what ClickHouse, CTEs, or basic SQL are, and every section adds non-obvious domain-specific failure-mode knowledge that earns its tokens.	5 / 5
Actionability	Highly concrete methodology guidance (≥5 runs, p50/p90/p95/min, one-variable-per-variant, a ready before/after table template) but stops short of literal executable SQL/commands, delegating those to referenced files.	4 / 5
Workflow Clarity	A clear 7-step loop with explicit validation checkpoints (equivalence gate, ≥5-run spread checks) and feedback loops (keep/discard fast, keep the number either way, Stays/Drops/Caller's-call/No-change decision criteria).	5 / 5
Progressive Disclosure	The body is well-sectioned and references are clearly signaled inline (rendering.md, environments.md, instrumentation.md, clickhouse.md, testing.md), but no references/, scripts/, or assets/ bundle directories exist, so every referenced path is a broken link with no resolvable detail behind it.	3 / 5
	Total	17 / 20 Passed

Description

92%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.

A strong, specific description that clearly states both the capability and concrete usage triggers tied to a well-defined ClickHouse query-cost niche. Minor room for more natural synonyms in the trigger phrasing.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — validating query cost, read-only production access, and Testcontainers extrapolation to 20k/500k/1M entities — with comprehensive coverage of the validation approach and scale targets.	5 / 5
Completeness	Explicitly answers both what ('Validate what a ClickHouse query actually costs before merging it') and when via a concrete 'Use when' clause with multiple specific triggers.	5 / 5
Trigger Term Quality	Includes natural trigger phrases ('Use when a DAO query changes, when an endpoint is slow, or when a reviewer asks what does this cost at scale') but misses common synonyms like 'slow query' or 'query optimization'.	4 / 5
Distinctiveness Conflict Risk	A sharply defined niche (ClickHouse cost validation, DAO queries, Testcontainers, read-only prod access) with distinct triggers that are unlikely to fire for unrelated skills.	5 / 5
	Total	19 / 20 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: comet-ml/opik
Path: .agents/skills/query-performance/SKILL.md
Commit: 657e319

Reviewed: 3 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.