ClickHouse/agent-skills

The official Agent Skills for ClickHouse and ClickHouse Cloud

What it solves

This project provides a collection of "Agent Skills"—packaged instructions and domain-specific expertise—that enable AI coding agents (such as Claude Code, Cursor, and GitHub Copilot) to work more effectively with ClickHouse and chdb. It prevents AI agents from making common mistakes and ensures they follow official best practices for schema design, query optimization, and infrastructure management.

How it works

These skills are formatted according to an open specification (agentskills.io) and are installed into the configuration directories of various AI assistants. Once installed, the agents automatically reference these instructions when they detect tasks related to ClickHouse, such as creating tables, writing SQL queries, or setting up cloud environments.

Who it’s for

Developers and data engineers who use AI coding assistants to build applications with ClickHouse or chdb, and those who need to optimize their database performance or manage ClickHouse Cloud infrastructure.

Highlights

  • Comprehensive Best Practices: Includes 28 rules for critical areas like primary key selection, JOIN optimization, and data type selection.
  • Architecture Guidance: Provides decision frameworks for ingestion strategies and real-time pre-aggregation.
  • Python Integration: Specialized skills for chdb (in-process ClickHouse for Python), including a pandas-compatible DataStore API and SQL capabilities.
  • Agent Agnostic: Compatible with a wide range of AI agents including Claude Code, Cursor, Windsurf, and GitHub Copilot.
  • Infrastructure Automation: Instructions for managing local and cloud workflows for ClickHouse and Postgres using clickhousectl.
  • Observability: A dedicated workflow for integrating OpenTelemetry collectors into Managed ClickStack.

Related

  • Project
    mxyhi/ok-skills

    A curated collection of reusable skills and playbooks for AI coding agents like Claude Code and Cursor, providing structured workflows for tasks like browser automation and codebase planning.

  • Project
    kangarooking/kangarooking-skills

    A collection of structured, open-source Agent Skills compatible with the Agent Skills standard, providing reusable workflows for content creation, image generation, and AI project engineering.

  • Project
    dbt-labs/dbt-agent-skills

    A collection of Agent Skills that enable AI agents to understand and execute dbt workflows, including analytics engineering, semantic layer management, and project migrations.

  • Project
    samber/cc-skills-golang

    A collection of human-reviewed instruction sets (skills) for AI agents to ensure they produce idiomatic, secure, and high-performance Go code.

  • Project
    homeassistant-ai/skills

    A collection of portable knowledge packs that teach AI coding agents Home Assistant best practices to prevent common configuration errors.