clickzetta-skills

Complete guide for managing ClickZetta Analytics Agent domains via cz-cli: domain CRUD, table registration, column semantics (types/descriptions/aliases), metrics (simple & compound), Answer Builders, Knowledge Bases, and QA testing. Wizard-driven workflows with intent classification, routing tables, and troubleshooting references. Trigger when the user says: "analytics agent", "分析域", "语义层", "指标", "answer builder", "知识库", "多别名", "column semantics", "domain prompt", "metric create", "AB create", "session run", "domain table add", "semantics set", "knowledge space". Keywords: analytics agent, domain, semantics, metric, answer builder, knowledge base, alias, cz-cli, data analysis, AI agent, semantic layer

Create, query, and manage ClickZetta Lakehouse Semantic Views — schema-level logical models that encapsulate multi-table JOINs and aggregations into a business-friendly layer of logical tables, dimensions, metrics, and facts. Query with the semantic_view() function without writing JOINs or GROUP BY manually. Triggered when user says "create semantic view", "semantic view", "semantic layer", "define metrics", "define dimensions", "unified metric definitions", "business semantic model", "semantic_view()", "CREATE OR REPLACE SEMANTIC VIEW", "FACTS", "PRIVATE metric", "conditional metric", "window metric", "SHOW SEMANTIC VIEWS", "GRANT SELECT ON SEMANTIC VIEW". Keywords: semantic view, dimension, metric, fact, logical model, unified metrics, semantic layer, grain, chasm trap, FILTER metric

End-to-end data science workflow guide for ClickZetta Lakehouse, covering environment setup, data discovery, feature engineering (SQL + ZettaPark), and model inference deployment. Details: Python 3.10+/Jupyter/ZettaPark setup, project structure, data quality assessment, and inference (BITMAP profiling, UDF batch inference, vector search). Trigger when the user wants to do data science, ML, or analytical work using ClickZetta Lakehouse — connecting Jupyter to Lakehouse, doing EDA, building features, running ML inference, user profiling, audience segmentation, or batch scoring. Keywords: data science, ML, ZettaPark, Jupyter, feature engineering, EDA, profiling, inference

Use the ZettaPark Python library to work with ClickZetta Lakehouse data through a pandas-like DataFrame API that translates Python transformations into distributed SQL — no manual SQL needed. Covers Session creation, DataFrame construction and transformation (filter/select/join/groupBy), result collection (collect/to_pandas/show), writing tables (save_as_table), file operations (PUT/GET), and executing SQL. Trigger when the user says: "ZettaPark", "zettapark", "DataFrame API", "Python Lakehouse", "save_as_table", "session.table", "session.sql", "collect()", "to_pandas", "Python data engineering", "Python write to Lakehouse", "Python read from Lakehouse", "clickzetta_zettapark_python", "Python ETL", "Python ML on Lakehouse", "feature engineering Python", "Python DataFrame Lakehouse". Keywords: ZettaPark, DataFrame, pandas-like, Python, SQL translation, distributed compute

Guide users to connect their AI coding agents (Claude Code, Hermes Agent, OpenClaw, Opencode) to the Singsight AI Agent observability platform. Automatically reports every LLM call, tool execution, token usage, and session via OpenTelemetry. Triggered when the user says "connect Singsight", "install Singsight", "configure Singsight", "Agent observability", "OTel integration", "report token usage", "monitor AI Agent", "singsight install". Keywords: singsight, install, observability, opentelemetry, otel, agent telemetry, claude code, hermes, openclaw, opencode

dbt-clickzetta data modeling wizard: discovers Lakehouse data sources, infers modeling strategies, generates sources.yml and model files, and runs the full test suite. Presents choices rather than blank forms — explores data first, then proposes a justified plan for user confirmation. Trigger when the user wants to turn raw Lakehouse data into usable analytical tables — mentions dbt (dbt modeling, dbt model, sources.yml, incremental, dbt run, dbt test), wants ETL transformation, dimension/fact tables, or asks "how do I turn these tables into a queryable dataset". Keywords: dbt, dbt modeling, sources.yml, incremental, dbt run, dbt test, dimension table, fact table, ETL

dbt-clickzetta project initialization wizard: builds a dbt project connected to ClickZetta Lakehouse, covering installation checks, profiles.yml, layering standards, and dbt_project.yml generation. Hands off to clickzetta-dbt-modeling after completion. Trigger when the user wants to build a data warehouse or start a dbt project in ClickZetta — "I want to build a data warehouse with dbt", "dbt beginner guide", "dbt project init", "dbt from scratch", "how to connect dbt to ClickZetta", "dbt profiles configuration", "how do I write profiles.yml". Keywords: dbt, project setup, profiles.yml, dbt-clickzetta, initialization, ELT, data warehouse setup

ClickZetta Lakehouse data warehouse modeling wizard: explores the data landscape, then designs layered models (Traditional DW ODS/DWD/DWS/ADS, Medallion, or hybrid) with DDL and pipeline config together. Presents justified recommendations — never asks questionnaire-style questions. Core principle: use Dynamic Table for aggregation layers, not Materialized View. Trigger when the user says: "data warehouse modeling", "layering design", "ODS/DWD/DWS", "Medallion", "Bronze/Silver/Gold", "fact table", "dimension table", "star schema", "layered architecture", "modeling wizard", "build a data warehouse", "DW architecture", "design my data layers". Keywords: data warehouse, modeling, star schema, medallion, ODS, DWD, DWS, ADS, layering

ClickZetta Dynamic Table usage guide and routing hub, covering consultation (best practices, performance, incremental config), creation, and modification (ALTER, suspend/resume, columns). SQL conversion requests are delegated to the sql-to-dt sub-skill. Trigger when the user says: "dynamic table", "DT introduction", "dynamic table best practices", "dynamic table performance", "incremental computation", "REFRESH INTERVAL", "create dynamic table", "dynamic table scheduling", "dynamic table alerts", "ALTER DYNAMIC TABLE". Keywords: dynamic table, DT, REFRESH INTERVAL, incremental, suspend, resume, sql-to-dt

Table lineage visualization tool for ClickZetta Lakehouse: analyzes information_schema.job_history for table dependencies and cost, then renders an interactive HTML lineage graph. Trigger when user says "table lineage", "dependency graph", "data flow", "upstream/downstream analysis", "lineage visualization", or "pipeline visualization". Keywords: table lineage, dependency graph, data flow, upstream, downstream, visualization

Build and manage ClickZetta Table Stream change data capture pipelines, covering source change tracking, Stream creation, offset management, and idempotent incremental-ETL consumption. Includes change tracking setup, mode selection, metadata field usage — all ClickZetta-specific logic. Trigger when the user says: "create Table Stream", "Table Stream CDC", "Table Stream pipeline", "Table Stream incremental consumption", "Stream consumption", "change data capture", "capture table changes", "CDC with Table Stream", "incremental ETL from table", "track row changes", "consume stream data", "stream offset". Keywords: table stream, CDC, change capture, incremental ETL, stream, offset

Singdata Lakehouse official documentation knowledge base (English). Consult references/ when writing SQL or answering questions about query syntax, functions, data types, DDL/DML, dynamic tables, permissions, vclusters, data lake, AI functions, and other Lakehouse topics.

Use when working in this repository to discover CMT sources, plan migrations, start runs, monitor progress, verify migration outcomes, inspect run logs, or clean up failed runs through the official CMT v2 surface.

Publish all dbt models to Studio as assets and configure scheduled execution. All dbt model SQL code is centrally managed in Studio; models needing periodic execution get scheduling configuration. Reads dbt manifest.json, rewrites incremental SQL for scheduling parameters, guides user confirmation, then deploys automatically. Trigger when the user wants dbt models to run or be scheduled in Studio — mentions "publish dbt to Studio", "dbt scheduling", "dbt asset management", "dbt manifest", "dbt Studio tasks", "dbt pipeline deployment", or asks "how do I schedule dbt". Keywords: dbt Studio, publish dbt, dbt scheduling, dbt manifest, Studio asset, dbt deployment

Write data to ClickZetta Lakehouse using the Spark Connector or Flink Write Connector. Covers Spark DataFrame read/write configuration (Maven dependencies, connection parameters, read/write code), Flink Table API writes (CDC mode igs-dynamic-table, append-only mode igs-dynamic-table-append-only), checkpoint configuration, buffer/flush tuning, and key constraints such as primary-key table limitations. Trigger when the user says "Spark Connector", "Flink Connector", "Spark writes to Lakehouse", "Flink writes to Lakehouse", "spark-clickzetta", "igs-flink-connector", "Spark DataFrame write", "Flink CDC write", "Flink sink", or "spark.read.format clickzetta". Keywords: Spark, Flink, DataFrame, connector, read, write, CDC, igs-dynamic-table

Migration guide for SQL workloads moving to ClickZetta Lakehouse from Snowflake, Databricks, or Spark SQL. Covers object concept mapping, syntax differences, function mapping tables, MERGE INTO limitations, strict implicit type conversion, and migration pitfalls. For native ClickZetta SQL syntax reference the Lakehouse documentation. Triggered when the user mentions migration source platforms (Snowflake, Databricks, Spark SQL) together with ClickZetta, asks about specific functions/syntax (IFF, LISTAGG, FLATTEN, TARGET_LAG, APPLY CHANGES INTO, ZORDER, WITH RECURSIVE, WHEN NOT MATCHED BY SOURCE), or asks about compatibility/differences. Keywords: Snowflake migration, Databricks migration, Spark SQL migration, vs Snowflake, vs Spark, vs Databricks, syntax differences, function mapping, implicit type conversion

Manage ClickZetta Studio tasks: data development (SQL/Python/Shell), batch sync (INTEGRATION/MULTI_DI), real-time CDC (MULTI_REALTIME), Kafka streaming (REALTIME), and composite Flow DAGs. Covers folder organization, 7-field cron scheduling, dependency management, Python task creation (save-script), DRAFT/offline state control, and troubleshooting. Separates DDL (drafts) from ETL pipelines (scheduled). Trigger: "create Studio task", "task scheduling", "cz-cli task", "task dependency", "DDL task", "ETL orchestration", "sync task", "Flow task", "组合任务", "task cron", "save-script", "undeploy", "task failed", "batch sync", "CDC sync". Keywords: Studio task, task management, cz-cli task, scheduling, DAG, DDL draft, ETL pipeline, sync task, CDC, INTEGRATION, MULTI_DI, MULTI_REALTIME, REALTIME, Python task, save-script, undeploy, DRAFT, cron, Flow, composite task, 组合任务

Build Kafka-to-Lakehouse ingestion pipelines using READ_KAFKA Pipe or Kafka External Table + Table Stream. Covers: connection validation, JSON/CSV parsing, Pipe DDL, SASL auth, VCluster sizing, latency monitoring, tuning. Trigger when the user says: "Kafka ingestion", "Kafka Pipe", "read_kafka", "Kafka external table", "Kafka consumer", "message queue import", "Kafka backlog", "ingest from Kafka", "stream data to Lakehouse", "real-time Kafka pipeline", "Kafka to ODS". Keywords: Kafka, Pipe, read_kafka, message queue, streaming ingestion, real-time ETL

Manage ClickZetta Lakehouse Volume objects for mounting object storage (OSS/COS/S3), querying files, and importing/exporting data. Covers creating External Volumes (OSS/COS/S3), User Volume file operations (PUT/GET/REMOVE), SELECT FROM VOLUME direct file queries, COPY INTO TABLE imports, COPY INTO VOLUME exports, and more. Triggered when users say "create Volume", "mount OSS", "mount S3", "mount COS", "Volume management", "query OSS files", "query S3 files", "upload files to Volume", "PUT files", "GET files", "import data from Volume", "export to Volume", "COPY INTO VOLUME", "SELECT FROM VOLUME", "User Volume", "data lake files", "data export", "export data", "export CSV", "export Parquet", "COPY OVERWRITE INTO". Keywords: Volume, OSS, COS, S3, mount, file query, COPY INTO, external storage

Create and manage ClickZetta Lakehouse multi-table real-time sync (CDC) tasks, syncing MySQL/PostgreSQL databases to Lakehouse. Three sync modes: full database mirror, multi-table mirror, sharded table merge. Binlog/WALs-based with full load + incremental sync. Triggered when the user says "multi-table real-time sync", "full database sync", "database mirror", "CDC full database", "multi-table CDC", "sharded table merge", "MySQL full database sync", "PostgreSQL full database sync", "database migration", "sync operations", "sync SOP", "Binlog position expired", "full re-sync", "add sync table". Covers source DB preparation, sync mode selection, task deployment, operations SOP, monitoring/alerting, and troubleshooting — all ClickZetta Studio specific logic. Keywords: CDC, real-time sync, MySQL, PostgreSQL, change data capture, mirror, merge, multi-table

Reference index for creating Dynamic Tables. Covers SQL patterns supported by incremental computation and incremental refresh configuration options. Keywords: dynamic table, DT creator, incremental, SQL patterns, refresh configuration

Automatically converts CREATE TABLE DDL + INSERT OVERWRITE SQL from Hive/Spark or any batch processing system into Dynamic Table DDL and companion files (refresh, prev_refresh, backfill). Trigger when the user provides DDL and INSERT OVERWRITE and requests conversion, or says "convert to DT", "sql to dt", "convert to dynamic table", "INSERT OVERWRITE to DT", "DDL conversion", "create dynamic table". Keywords: sql-to-dt, convert to DT, INSERT OVERWRITE, DDL conversion, dynamic table

ClickZetta Lakehouse product overview: core concepts, object model, architecture, and Studio module introduction. Covers: Account/Instance/Workspace/Schema hierarchy, VCluster types and CRU billing, Dynamic Table, Table Stream CDC, Pipe, Synonym, permission system (RBAC/ACL), storage-compute separation, brand relationships (ClickZetta = Yunqi = Singdata), and Studio six modules. Trigger when user asks: "what is a workspace", "what is a VCluster", "what is CRU", "Lakehouse architecture", "object hierarchy", "permission system", "compare concepts with Snowflake", "what is Studio", "storage-compute separation", "ClickZetta introduction". Keywords: concepts, architecture, workspace, schema, VCluster, Studio, overview, object model

Manage ClickZetta Lakehouse SQL pipeline objects: Dynamic Table, Materialized View, Table Stream, and Pipe. Covers full lifecycle: create, modify, suspend/resume, drop, and status inspection. SQL commands only — no Studio GUI involved. Trigger when the user says: "create dynamic table", "create materialized view", "create pipe", "create table stream", "suspend/resume dynamic table", "view refresh history", "change refresh interval", "ingest from Kafka", "continuous ingest from object storage", "CDC change capture", "incremental compute", "real-time ETL", "data pipeline", "pipeline", "streaming", "dynamic table refresh failed", "design ETL", "build data pipeline", "data ingestion plan", "Medallion Architecture", "Bronze Silver Gold", "lakehouse layering", "Bronze layer", "Silver layer", "Gold layer". Keywords: SQL pipeline, dynamic table, materialized view, table stream, Pipe, data pipeline

Create and manage ClickZetta Lakehouse batch sync tasks, supporting both single-table and multi-table modes. Single-table mode is suitable for simple source-to-target table sync; multi-table mode supports full database mirror, multi-table mirror, and sharded table merge. Triggered when the user says "batch sync", "offline sync", "sync database to Lakehouse", "full database migration", "multi-table sync", "periodic sync", "scheduled data sync", "sharded table merge", "offline data migration". Covers single-table/multi-table batch sync task creation, data source configuration, column mapping, sync rules, scheduling, deployment, and task operations — all ClickZetta Studio specific logic. Keywords: batch sync, offline sync, full load, mirror, multi-table sync, scheduled sync

Router skill: selects the best data ingestion method for ClickZetta Lakehouse based on data source, latency, sync scope, and continuity requirements. Routes to specialized skills: Kafka Pipe, OSS/S3/COS Pipe, Studio batch sync, Studio real-time sync, Studio CDC, file/URL import, or programmatic ingestion guidance. Trigger: user wants to get external data INTO Lakehouse but hasn't chosen a method, OR asks which ingestion approach fits their scenario. Covers: Kafka, MySQL, PostgreSQL, SQL Server, TiDB, OSS, S3, COS, local files, URLs, programmatic application writes, Python/ZettaPark. Does NOT cover: querying data, pipeline monitoring/diagnosis, Dynamic Table tuning, internal table transformations, or data export. Keywords: data ingestion, import, sync, ETL, migrate, load data, ingest, pipeline selection

Import data from URLs, local files, or Volume paths into ClickZetta tables. Covers the complete workflow: file download, format inference, table creation, COPY INTO import, and result verification. Includes ClickZetta USER VOLUME mechanism, COPY INTO syntax, format inference rules, and write mode semantics. Trigger when the user says: "import data", "load from URL", "upload CSV to table", "file import", "COPY INTO", "load file into Lakehouse", "import CSV", "import Parquet", "import JSON", "bulk load data", "load data from file", "ingest file", "PUT file", "upload to Volume". Keywords: file import, URL, CSV, JSON, Parquet, COPY INTO, Volume, bulk load

Build ClickZetta object storage (OSS/S3/COS) data ingestion pipelines, covering both continuous ingestion (PIPE) and one-time batch import scenarios. Continuous ingestion supports LIST_PURGE scan mode and EVENT_NOTIFICATION message notification mode; batch import supports Volume + INSERT INTO and Volume + COPY INTO methods. Triggered when user says "object storage import", "OSS data pipeline", "S3 data import", "PIPE continuous ingestion", "auto file loading", "bucket data sync", "COS import", "batch import from OSS", "load data from OSS", "Volume import". Includes PIPE continuous ingestion (two INGEST_MODEs), batch import (Volume + COPY/INSERT), Connection/Volume creation, monitoring and management — all ClickZetta-specific logic. Keywords: OSS, S3, COS, object storage, PIPE, COPY INTO, file ingestion

Comprehensive review and diagnosis of ClickZetta Lakehouse data pipelines. Starting from any entry point (task name / schema / table name / business domain keyword), autonomously discovers all pipeline objects (Studio tasks, Lakehouse tables, pipeline objects, run records), identifies missing scheduling dependencies, DDL idempotency issues, layer skipping, Dynamic Table anti-patterns, and other common problems. Delivers prioritized fix recommendations and executes them. Trigger when the user says: "review pipeline", "check data pipeline", "pipeline diagnosis", "pipeline has issues", "task failed", "data is wrong", "pipeline review", "check ETL", "pipeline health check", "data lineage check", "pipeline overview", "pipeline audit", "task dependency check", "DT refresh failing", "data inconsistency", "pipeline not working". Keywords: pipeline review, diagnosis, task dependency, data lineage, DT health, pipeline discovery

Create and manage ClickZetta Lakehouse real-time sync tasks (single-table), syncing data from external sources to Lakehouse in real time. Supports Kafka, MySQL, PostgreSQL, and other data sources as the source, with Lakehouse as the target. Real-time sync tasks are continuously running streaming tasks — no scheduling required; they start running upon submission. Triggered when the user says "Studio real-time sync", "realtime sync", "single-table CDC sync", "real-time data sync", "Kafka real-time sync to Lakehouse", "MySQL single-table real-time sync", "single-table real-time sync", "real-time data migration". Covers real-time sync task creation, data source configuration, column mapping (including JSONPath computed columns), deployment, and operations — all ClickZetta Studio specific logic. Keywords: real-time sync, single table, Kafka source, MySQL source, streaming, CDC

Use ClickZetta built-in AI functions: AI_COMPLETE (call LLMs) and AI_EMBEDDING (text vectors). Covers CREATE API CONNECTION (TYPE ai_function), AI_COMPLETE, AI_EMBEDDING. Keywords: AI_COMPLETE, AI_EMBEDDING, LLM, text embedding, semantic search, built-in AI function

Create and use External Functions (custom UDFs) in ClickZetta Lakehouse using Python or Java, deployed on Alibaba Cloud FC / Tencent Cloud SCF / AWS Lambda. Covers CREATE API CONNECTION (TYPE CLOUD_FUNCTION), CREATE EXTERNAL FUNCTION, Python/Java UDF code structure and packaging. Keywords: external function, UDF, Python UDF, Java UDF, custom function, cloud function