Skip to skills
AI Craft Pad
Home/Skills/Data & databases/chdb-sql
First-party source

Chdb Sql

Embedded analytical SQL for Python tasks that need ClickHouse functions without operating a separate database server.

Editorial review checked 2026-10-29 against this instruction snapshot. Supporting scripts and runtime behavior remain outside this editorial review.

What it does

The instruction file distinguishes a one-off query, a persistent Session and a DB-API connection. Its examples combine local files, Python data and remote table functions. References cover query parameters, output formats and connectors; this is an application workflow rather than server administration.

Best for

SQL-oriented analysis of Parquet or CSV files, small reproducible analytical pipelines, and experiments that need ClickHouse expressions inside a Python process.

Tradeoffs and requirements

Installing a skill does not install or validate chDB. The source declares Python and platform requirements. Queries against remote services can move sensitive data, and persistent session directories need an explicit lifecycle. Parameter binding should replace string interpolation for values.

Requires Python 3.9+, macOS or Linux. pip install chdb.

Install from the source

Inspect the pinned source snapshot and its supporting files first. The command selects this skill through the open-source skills CLI. Node.js and agent-specific setup may be required. Installation can download code; this catalog never runs it.

npx skills add https://github.com/ClickHouse/agent-skills/tree/69a8354b05b5942e5cea77b6c87be7788303fc18/skills/chdb-sql --skill chdb-sql

Review pinned skill folder ↗ · CLI documentation ↗

After source review, use npx skills check and npx skills update to inspect and apply upstream updates. Re-check changed instructions before running them.

Safety & review signals

Static review only. This is not a security audit or a guarantee of safety.

SKILL.md text only; scripts, dependencies and runtime behavior not audited.

  • Network Access — review the source context.
  • Shell Or Package Install — review the source context.

Allowed tools declaration: Unknown. Runtime permissions and network behavior: Unknown.

AI Craft Pad Skill Score

86/100 · Metadata coverage 100% · Model 1.0

Scores summarize observable discovery signals. Popularity and repository activity apply to the whole repository. Unknown runtime safety earns no certification.

Documentation
100/100
100
Maintenance
100/100
100
License Clarity
100/100
100
Repository Health
100/100
100
Compatibility Evidence
80/100
80
Popularity
50/100
50
Originality
80/100
80
Static Safety
60/100
60
Read the formula and limits →

Supporting-file static inspection

Bounded source inspection, not a runtime security audit. No source code was executed.

2 text files inspected at this exact repository snapshot. 5 files outside the inspection budget or type allowlist. Dependencies were not installed or independently audited.

  • Network Client: 1 file — inspect context before use.

Absence of a pattern is not proof of safety. Permission needs and runtime behavior remain Unknown.

Inspected file inventory

Suggested workflow

Prove a parameterized query on a local fixture first. Select the simplest API that provides the required state, then introduce external data only after reviewing connector permissions.

How to judge the result

Verify output schema, exact aggregates and behavior on missing files. For persistent sessions, reopen the database and confirm expected state; for remote joins, check transfer volume and credential handling separately.

Similar skills to compare

Related by category; compare scope and dependencies before choosing an alternative.

Data & databases87/100

360 feedback system

sickn33/agentic-awesome-skills

Explore 360 feedback system as a data & databases workflow from sickn33/agentic-awesome-skills. Compare its source, maintenance and review signals before choosing it for your agent.

Community sourceMIT3 matching source records
48,737 repo stars1 text flagReview ↗
Data & databases87/100

access matrix

sickn33/agentic-awesome-skills

Explore access matrix as a data & databases workflow from sickn33/agentic-awesome-skills. Compare its source, maintenance and review signals before choosing it for your agent.

Community sourceMIT3 matching source records
48,737 repo stars1 text flagReview ↗
Data & databases87/100

adhx

sickn33/agentic-awesome-skills

Explore adhx as a data & databases workflow from sickn33/agentic-awesome-skills. Compare its source, maintenance and review signals before choosing it for your agent.

Community sourceMIT3 matching source records
48,737 repo stars3 text flagsReview ↗

More from this source

Data & databases86/100

chdb datastore

ClickHouse/agent-skills

A Python DataFrame workflow for exploring files and joining tabular sources through the embedded ClickHouse engine.

First-party sourceApache-2.0Editorial review
562 repo stars2 text flagsReview ↗
Data & databases86/100

clickhouse architecture advisor

ClickHouse/agent-skills

A workload-first decision aid for ClickHouse ingestion, enrichment, time-series storage and changing data.

First-party sourceApache-2.0Editorial review
562 repo stars0 text flagsReview ↗
Data & databases86/100

clickhouse best practices

ClickHouse/agent-skills

A structured review of ClickHouse schema, query and insertion choices with links to focused rules.

First-party sourceApache-2.0Editorial review
562 repo stars2 text flagsReview ↗

Works well in these suggested workflows

Editorial combinations of complementary roles; review each source independently.