clickhouse-architecture-advisor

MUST USE when designing ClickHouse architectures, selecting between ingestion or modeling patterns, or translating best practices into workload-specific system designs. Complements clickhouse-best-practices with decision frameworks and explicit provenance labels.

Quality

88%

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

77%

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

The body is concise and well-sequenced with explicit validation checkpoints, but its actionability and progressive disclosure are undermined because every referenced bundle file (rules/, mappings/, AGENTS.md, examples/) is missing from the actual bundle.

Suggestions

Ship the referenced bundle files (rules/decision-*.md, mappings/doc_links.yaml, AGENTS.md, examples/) so the core 'read the rule files' step can actually be executed; without them the skill cannot perform its primary function.

Add a brief fallback in SKILL.md for when a referenced rule file is absent (e.g., fall back to official docs plus the provenance taxonomy), so actionability does not collapse when the bundle is incomplete.

Confirm each referenced path resolves one level deep with no dead links, and surface the file listing inline so Claude can verify the references exist before depending on them.

Dimension	Reasoning	Score
Conciseness	The body is lean — numbered lists, short labeled sections, and an output template — with no tutorial-style explanations of concepts Claude already knows; every section earns its place.	3 / 3
Actionability	Guidance is concrete in form (specific file paths, a provenance taxonomy, and a copy-paste output template), but the core actionable step 'Read the relevant decision rule files in rules/' and 'Use mappings/doc_links.yaml' depends on files that are not present in the bundle, leaving key details missing.	2 / 3
Workflow Clarity	A clear six-step required-behavior sequence with explicit checkpoints (step 5 'Never present field guidance as official', step 6 uncertainty disclosure) plus a per-recommendation 'Validation' field requiring 'concrete SQL, metric, or smoke test'.	3 / 3
Progressive Disclosure	SKILL.md is well organized and signals one-level-deep references (rules/, mappings/doc_links.yaml, AGENTS.md, examples/), but those referenced bundle files do not exist, so the disclosure structure does not actually resolve and navigation is broken.	2 / 3
	Total	10 / 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.

A strong, specific description that clearly states both the capability and the explicit trigger conditions, while distinguishing itself from the related best-practices skill. It uses third-person voice and avoids vague fluff.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'designing ClickHouse architectures', 'selecting between ingestion or modeling patterns', 'translating best practices into workload-specific system designs' — rather than vague language, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what ('Complements clickhouse-best-practices with decision frameworks and explicit provenance labels') and when ('MUST USE when designing ClickHouse architectures...'), with an explicit 'MUST USE when' trigger clause.	3 / 3
Trigger Term Quality	Uses natural domain terms a ClickHouse practitioner would say ('ClickHouse architectures', 'ingestion', 'modeling patterns', 'best practices', 'workload-specific system designs'), giving good coverage rather than only generic or jargon-only phrasing.	3 / 3
Distinctiveness Conflict Risk	Explicitly positions itself as complementary to 'clickhouse-best-practices' with a distinct architecture-decisioning niche, making it unlikely to trigger for the wrong skill.	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: MapleTechLabs/maple
Path: .agents/skills/clickhouse-architecture-advisor/SKILL.md
Commit: 8d347f8

Reviewed: about 14 hours 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.