ClickHouse Agent Skills

Official ClickHouse skills: schema and query rules, architecture decisions, chDB for Python and ClickHouse Cloud workflows

562 ★ on the repository
Last commit Oct 19, 2026
Apache-2.0

SkillEditors’ pick

clickhouse/agent-skillsAuthor:ClickHouse

Install

Works in: Claude Code
Cursor
Windsurf
GitHub Copilot
Gemini CLI
Cline
Codex
Goose
Roo Code
Amp
Koda
Coddy

In your terminal, with SkillFoxx CLI

npx skillfoxx add skills/clickhouse-agent-skills

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Extended accessThe tool runs code or makes network calls and only reads external data.

The chdb-sql and chdb-datastore skills have the agent run scripts/verify_install.py
Cloud scenarios walk the agent through clickhousectl commands against a ClickHouse Cloud account

This is third-party code. Review the repository files before installing.

What it does

A skill set from the ClickHouse team that teaches the agent to design tables, pick sorting keys and data types, tune JOINs and set up ingestion. A separate skill guides architecture decisions for real-time workloads: insert strategies, partitioning, upserts and pre-aggregation. The chdb-sql and chdb-datastore skills cover in-process ClickHouse for Python, including a pandas-compatible API and queries over files and external databases. There are also workflows for clickhousectl (local development and ClickHouse Cloud), managed Postgres, wiring an OpenTelemetry collector into ClickStack, and troubleshooting the Node.js client.

Who it is for. For developers and analysts building schemas, queries and pipelines on ClickHouse or chDB.

Good fit when

You are designing a table and choosing ORDER BY and column types
ClickHouse queries or JOINs are slow
You want to crunch Parquet or CSV data in Python with chDB
You are setting up ClickHouse locally or in ClickHouse Cloud with clickhousectl

Not a fit when

The project does not use ClickHouse or chDB
You need the agent to query a live database: ClickHouse has a separate MCP server for that

Example request

Create a table for user events with user_id, event_type, JSON properties and a timestamp following ClickHouse best practices

Limitations

The skills provide knowledge and instructions but do not connect to a database themselves. Cloud workflows need a ClickHouse Cloud account, and managed Postgres is in beta. chDB runs on macOS and Linux with Python 3.9+.

How to disable. Delete the skill folders from your agent's skills directory or uninstall the plugin via /plugin.

FAQ

How is this different from the ClickHouse MCP server?

The MCP server gives the agent database access, while the skills teach it to design schemas and write queries correctly. They work well together.

Do I need ClickHouse Cloud?

No, the rules and chDB work with open-source ClickHouse. The cloud is only needed for the clickhousectl cloud and ClickStack workflows.

Discussion

No questions or reviews yet.

Skills

ClickHouse MCP Server

Editors’ pick

Official ClickHouse MCP server: the agent lists databases and tables and runs SQL, read-only by default

MCP serverExtended access899

Altinity MCP Server

A Go MCP server for querying ClickHouse: schemas, SQL, tools generated from views, OAuth and Kubernetes deployment

MCP serverBroad access38

Tinybird Agent Skills

Official Tinybird skills: datafile and SQL rules, the tb CLI, and the TypeScript and Python SDKs

SkillMinimal access22

Elastic Agent Skills

Editors’ pick

Official Elastic skills for Elasticsearch, Kibana, Observability, Security and Elastic Cloud: ES|QL, indices, dashboards, alert triage

PluginBroad access603

Databricks AI Dev Kit

Needs a VPN

Databricks Field Engineering's agent kit: an installer for Databricks skills, an MCP server and a visual Builder App

PluginBroad access2K

Lieflat Charts

A data visualization skill for agents: turns data into polished interactive HTML charts and full reports with one visual language

SkillMinimal access6.5K

README in short

The README lists the repository's skills: prioritized rules for schemas, queries and ingestion, an architecture advisor, chDB SQL and DataStore, clickhousectl workflows for ClickHouse and Postgres, OpenTelemetry setup for ClickStack and Node.js client troubleshooting. Install with npx skills add or with clickhousectl skills. The skills follow the agentskills.io spec and work in Claude Code, Cursor, Windsurf, Copilot, Gemini CLI, Codex and other agents. Apache 2.0 licensed.

README badge

Original SKILL.md

---
name: chdb-datastore
description: >-
  Use when the user has tabular data (pandas DataFrame, parquet, csv,
  Arrow, json) and wants to filter, group, aggregate, join, or speed
  up slow pandas. Provides chDB DataStore — same pandas API,
  ClickHouse engine underneath. Also handles reading from S3, MySQL,
  PostgreSQL, MongoDB, ClickHouse Cloud, Iceberg, Delta Lake as
  DataFrames and joining across sources.
  TRIGGER when: user mentions DataFrame, parquet, csv, "fast pandas",
  "speed up pandas", or cross-source DataFrame joins; user imports
  `chdb.datastore` or `from datastore import DataStore`.
  SKIP this skill for raw SQL syntax (use chdb-sql instead),
  ClickHouse server administration, or non-Python DataStore API work.
license: Apache-2.0
compatibility: Requires Python 3.9+, macOS or Linux. pip install chdb.
metadata:
  author: chdb-io
  version: "4.1"
  homepage: https://clickhouse.com/docs/chdb
---

# chdb DataStore — It's Just Faster Pandas

## The Key Insight

```python
# Change this:
import pandas as pd
# To this:
import chdb.datastore as pd
# Everything else stays the same.
```

DataStore is a **lazy, ClickHouse-backed pandas replacement**. Your existing pandas code works unchanged — but operations compile to optimized SQL and execute only when results are needed (e.g., `print()`, `len()`, iteration).

```bash
pip install chdb
```

Report a problem