clickhouse/agent-skills
7 skills41.4k installs3.6k starsGitHub
Install
npx skills add https://github.com/clickhouse/agent-skillsSkills in this repo
1Clickhouse Best PracticesClickHouse Best Practices is official ClickHouse Inc guidance with thirty-one prioritized rules across schema design, query optimization, data ingestion, and AI agent connectivity. Agents must read applicable rule files before answering and cite them as Per rule-name, because columnar storage, sparse indexes, and MergeTree mechanics differ from general database intuition. Schema reviews check ORDER BY immutability, cardinality ordering, filter column inclusion, native types, LowCardinality strings, Nullable avoidance, and partition lifecycle limits. Query reviews cover JOIN algorithm selection, pre-join filtering, ANY JOIN usage, skipping indices, and ORDER BY filter alignment. Insert reviews enforce ten to one hundred thousand row batches, async inserts for small batches, ReplacingMergeTree over frequent UPDATE, and avoiding OPTIMIZE TABLE abuse. Agent workflows require MCP or CLI connection, seven-step schema discovery, and LIMIT plus timeout safe querying. Responses use a Rules Checked, Findings, and Recommendations structure with violations, compliant notes, and prioritized fixes.9kinstalls2Clickhouse Architecture AdvisorThis skill adds workload aware architecture decisioning on top of clickhouse best practices Official docs remain the source of truth This skill must always prefer official ClickHouse documentation when available 1 Identify the workload shape observability security SIEM product analytics IoT telemetry market data financial services mixed OLAP with point lookups 2 Read the relevant decision rule files in rules 3 Use mappings doc_links yaml to attach official documentation 4 Classify every recommendation as official derived field 5 Never present field guidance as official guidance 6 If a recommendation is uncertain say so explicitly official Use this when the recommendation is directly backed by official docs derived Use this when the recommendation is not stated verbatim in docs but follows logically from documented ClickHouse behavior The clickhouse architecture advisor agent skill provides documented workflows prerequisites triggers and safety guidance from its SKILL md source Agents load it when user requests match the description and follow step by step instructions without inventing capabilities It integrates with standard agent tooling for the6.3kinstalls3Chdb Sqlchdb-sql is an agent skill from clickhouse/agent-skills that apply chdb-sql agent skill workflows from documented skill.md guidance. # chdb SQL — ClickHouse in Your Python Process Run ClickHouse SQL directly in Python — no server needed. Query local files, remote databases, and cloud storage with full ClickHouse SQL power. ```bash pip install chdb ``` ## Decision Tree: Pick the Right API ``` 1. One-off query on files or databases → chdb.query() 2. Multi-step analysis with ta Developers invoke chdb-sql during build/integrations work for backend & apis tasks. The skill documents triggers, prerequisites, and step-by-step workflows grounded in SKILL.md. Compatible with Claude Code, Cursor, and Codex agent runtimes that load marketplace skills. Review the Security Audits panel on this listing before installing in production environments. Category Backend & APIs with development vertical focus supports repeatable agent-guided delivery.5.7kinstalls4Chdb Datastorechdb-datastore is an agent skill from clickhouse/agent-skills that apply chdb-datastore agent skill workflows from documented skill.md guidance. # 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 Developers invoke chdb-datastore during build/integrations work for backend & apis tasks. The skill documents triggers, prerequisites, and step-by-step workflows grounded in SKILL.md. Compatible with Claude Code, Cursor, and Codex agent runtimes that load marketplace skills. Review the Security Audits panel on this listing before installing in production environments. Category Backend & APIs with development vertical focus supports repeatable agent-guided delivery.5.7kinstalls5Clickhouse Js Node Troubleshootingclickhouse-js-node-troubleshooting is an agent skill from clickhouse/agent-skills focused on the official ClickHouse Node.js client (@clickhouse/client). It walks through socket hang-up and Keep-Alive failures, stream handling mistakes, data type mismatches, read-only user restrictions, proxy and TLS setup, and long-running query timeouts. The skill is triggered by vague reports like random connection drops or failing inserts in a Node.js context, even when the user has not named the root cause. Developers reach for it while wiring analytics backends, ETL jobs, or API routes that query or insert into ClickHouse and need fast, client-specific fixes instead of generic database advice.5.3kinstalls6Clickhouse Js Node Codingclickhouse-js-node-coding is an agent skill from clickhouse/agent-skills for building with the ClickHouse Node.js client `@clickhouse/client` in Node.js, Next.js Node runtime routes, React Server Components, and Server Actions—not Edge or browser runtimes. It maps tasks to 12 reference files covering client configuration, ping health checks, JSONEachRow inserts and selects, async inserts, query parameter binding with `{name: Type}` syntax, sessions, compression, and modern types like Dynamic, Variant, JSON, Time, Time64, and QBit. The skill mandates `query_params` instead of template-literal SQL interpolation, explicit SQL injection warnings, and `await client.close()` in snippets. Use it when wiring analytics endpoints, bulk event ingestion, or parameterized reporting queries in Node backends backed by ClickHouse.4.8kinstalls7Clickhouse Managed Postgres RcaProvides an evidence-based RCA workflow for performance issues on a ClickHouse-managed Postgres instance, scraping Prometheus and the Slow Query Patterns API. A developer uses it to investigate slow queries and get a recommended (not auto-applied) fix.4.6kinstalls