chdb-sql

In-process ClickHouse SQL engine for Python — run ClickHouse SQL queries directly on local files, remote databases, and cloud storage without a server. Use when the user wants to write SQL queries against Parquet/CSV/ JSON files, use ClickHouse table functions (mysql(), s3(), postgresql(), iceberg(), deltaLake() etc.), build stateful analytical pipelines with Session, use parametrized queries, window functions, or other advanced ClickHouse SQL features. Also use when the user explicitly mentions chdb.query(), ClickHouse SQL syntax, or wants cross-source SQL joins. Do NOT use for pandas-style DataFrame operations — use chdb-datastore instead.

Quality

95%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

90%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 a lean, highly actionable overview with well-structured one-level-deep references and executable examples. It falls short of top marks only on workflow clarity (no explicit feedback loop) and progressive disclosure (a referenced examples file is missing from the bundle).

Suggestions

Add the missing examples/examples.md file referenced in the References section, or remove the broken link so navigation resolves.

For stateful Session pipelines that load from remote sources, add an explicit validate→fix→retry checkpoint (e.g., run scripts/verify_install.py before querying, and on DB::Exception consult the troubleshooting table then re-run).

Surface the verify_install.py validation step inside the decision tree or a 'Getting started' step rather than only in the troubleshooting table, so the verification checkpoint is part of the primary workflow.

Dimension	Reasoning	Score
Conciseness	Lean and efficient — opens with a one-line tagline, a decision tree, and executable code with terse inline comments; assumes Claude's competence and never explains what ClickHouse or SQL are. Every line earns its place.	5 / 5
Actionability	Fully executable, copy-paste-ready examples covering the common cases: chdb.query() on files/databases/s3/deltaLake, cross-source joins, Python data, output formats, parametrized queries, Session pipelines, and DB-API connections, plus a troubleshooting table with concrete fixes.	5 / 5
Workflow Clarity	The decision tree gives a clear sequenced API-selection flow and a verify_install.py checkpoint is referenced, but there is no explicit validate→fix→retry feedback loop; the troubleshooting table partially compensates but stops short of a recovery loop. Not 3 because the sequence and verify checkpoint are present; not 5 because error-recovery checkpoints are implicit rather than staged.	4 / 5
Progressive Disclosure	Good one-level-deep structure with clearly signaled links to references/table-functions.md, references/sql-functions.md, and references/api-reference.md (all present), but the body and References list both cite examples/examples.md ('9 runnable examples with expected output') which does not exist in the bundle — a broken navigation path that prevents a 5.	4 / 5
	Total	18 / 20 Passed

Description

100%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 exemplary: concrete capabilities, natural trigger terms, explicit what/when guidance, and a clear disambiguation boundary against a related skill. Third-person voice is maintained throughout with no padding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — run SQL queries on local files/remote databases/cloud storage, use table functions (mysql(), s3(), postgresql(), iceberg(), deltaLake()), build Session pipelines, parametrized queries, window functions, cross-source joins — with comprehensive coverage rather than vague language.	5 / 5
Completeness	Explicitly answers both what ('In-process ClickHouse SQL engine for Python — run ClickHouse SQL queries directly on local files, remote databases, and cloud storage without a server') and when ('Use when the user wants to write SQL queries against Parquet/CSV/JSON files... Also use when the user explicitly mentions chdb.query()...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger terms including file formats (Parquet/CSV/JSON), named table functions, 'chdb.query()', 'ClickHouse SQL syntax', and 'cross-source SQL joins' — phrases a user would actually say.	5 / 5
Distinctiveness Conflict Risk	Clear niche (ClickHouse SQL in-process for Python) with an explicit boundary — 'Do NOT use for pandas-style DataFrame operations — use chdb-datastore instead' — minimizing conflict risk with the sibling skill.	5 / 5
	Total	20 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: MapleTechLabs/maple
Path: .agents/skills/chdb-sql/SKILL.md
Commit: e387359

Reviewed: 1 day 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.