CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

76

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

92%

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, actionable, and well-structured with real reference files, but it points to a non-existent examples/examples.md, which weakens navigation and progressive disclosure.

Suggestions

Either create the referenced examples/examples.md with the promised 9 runnable examples, or remove the link to it from the References section and the troubleshooting/decision areas.

If kept, add a brief inline one-line example or two in SKILL.md so the broken external reference is not the only source of runnable examples.

Verify any other path mentions (e.g., scripts/verify_install.py — which does exist) resolve, so all signaled references are reachable.

DimensionReasoningScore

Conciseness

Lean body with a compact decision tree and tight code blocks using one-line comments; no padding and no explanation of concepts Claude already knows.

3 / 3

Actionability

Fully executable, copy-paste-ready examples with real table functions, params, and output-format arguments; the inline code is complete rather than pseudocode.

3 / 3

Workflow Clarity

A clear decision tree sequences API selection and the Session example is multi-step, with an environment-check step in troubleshooting; as a query/analysis skill it has no destructive batch operation requiring feedback loops.

3 / 3

Progressive Disclosure

Good one-level-deep structure with real, well-signaled reference files (api-reference, table-functions, sql-functions), but the body references "examples/examples.md" which does not exist, so a navigation path is broken.

2 / 3

Total

11

/

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.

The description is specific, trigger-rich, and clearly disambiguated from the sibling chdb-datastore skill. It answers both what and when with concrete actions and natural keyword coverage. No changes needed.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "run ClickHouse SQL queries directly on local files, remote databases, and cloud storage", "build stateful analytical pipelines with Session", "parametrized queries, window functions" — rather than vague language.

3 / 3

Completeness

Explicitly answers both what (in-process ClickHouse engine running queries on files/databases/cloud) and when via two explicit "Use when…" / "Also use when…" trigger clauses.

3 / 3

Trigger Term Quality

Covers natural user phrasings well: "SQL queries against Parquet/CSV/JSON files", "chdb.query()", "ClickHouse SQL syntax", and "cross-source SQL joins".

3 / 3

Distinctiveness Conflict Risk

Clear ClickHouse-specific niche with explicit disambiguation ("Do NOT use for pandas-style DataFrame operations — use chdb-datastore instead") making conflict with sibling skills unlikely.

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
MapleTechLabs/maple
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.