query-clickhouse-via-metabase

Run ClickHouse `system.query_log` analysis via the internal Metabase API. Use when investigating slow queries, materialization candidates, per-team query performance, ClickHouse cost or memory issues, or any system.query_log question. Covers prod-us and prod-eu, SSO-gated cookie auth via `hogli`, and ready-to-run query patterns.

Quality

86%

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

88%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 highly actionable and well-structured with executable commands, real SQL patterns, explicit error handling, and a clear sequenced workflow with validation. Its main weakness is that it inlines a fair amount of reference material rather than offloading it to bundle files.

Suggestions

Move the bulk SQL query patterns (top slow queries, per-team cost summary, query_id lookup) into a references/ file and keep one representative example inline, to reduce token load.

Extract the Metabase response parsing and error-symptom tables into a separate reference file, linking from the main body.

Trim a few explanatory asides (e.g., the fail-fast rationale and repeated DB-ID-change warnings) since they restate guidance already implied by the commands.

Dimension	Reasoning	Score
Conciseness	Mostly lean and operational with executable commands and SQL, assuming Claude's competence; minor instances of explanatory padding (e.g., restating that DB IDs change, the fail-fast rationale) could be trimmed slightly.	4 / 5
Actionability	Fully executable, copy-paste-ready commands (hogli metabase:query with --save, --database-id, real SQL examples) plus concrete error-symptom tables and parsing snippets that cover the common cases.	5 / 5
Workflow Clarity	The investigation workflow is explicitly sequenced (frame -> pick smallest window -> filter type -> group then drill -> capture query_id) with validation checkpoints (fail-fast on wrong DB ID, error response table, login prompts) and feedback loops for auth/SQL errors.	5 / 5
Progressive Disclosure	Well-organized into clear sections (Environment, Authentication, Running a query, patterns, workflow, limitations) with no nested references, though the body inlines several large query patterns and reference material that could live in separate reference files for a skill of this length.	4 / 5
	Total	18 / 20 Passed

Description

85%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, complete, and distinct, clearly stating both what the skill does and when to use it with concrete trigger phrases tied to a narrow internal niche. It is slightly jargon-heavy but appropriately scoped.

Dimension	Reasoning	Score
Specificity	Names the domain (system.query_log analysis via Metabase) and several concrete actions (investigating slow queries, materialization candidates, per-team performance, cost/memory issues), with minor gaps like not naming the actual analysis outputs.	4 / 5
Completeness	Explicitly answers 'what' (Run ClickHouse system.query_log analysis via the internal Metabase API) and 'when' (Use when investigating slow queries, materialization candidates, per-team query performance, cost or memory issues) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes strong natural trigger terms ('slow queries', 'per-team query performance', 'cost or memory issues') that a user would plausibly say, though it leans slightly on internal jargon (system.query_log, materialization candidates) rather than everyday phrasing.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (ClickHouse query_log via Metabase, prod-us/prod-eu, SSO-gated cookie auth via hogli) with distinct triggers that are unlikely to overlap with unrelated skills.	5 / 5
	Total	18 / 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: PostHog/posthog
Path: .agents/skills/query-clickhouse-via-metabase/SKILL.md
Commit: 6fca5f8

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.