智能体工作流

alibabacloud-dataworks-datastudio-develop

aliyun/alibabac…s-skills

DataWorks data development Skill. Create, configure, validate, deploy, update, move, and rename nodes and workflows. Manage components, file resources, and UDF functions. Covers 150+ node types: Shell, SQL, Python, DI, Flink, EMR, etc. Supports scheduled and manual workflow orchestration via aliyun CLI or Python SDK. WARNING: Supports mutating operations (Move, Rename) requiring explicit user confirmation. Delete operations are NOT supported by this skill. Triggers: DataWorks, data development nodes, workflows, FlowSpec, scheduling tasks, data integration, ETL pipelines, .spec.json. Also triggers for Alibaba Cloud data development, scheduling node configuration, FlowSpec format, or DI task orchestration.

  • 521 次安装
  • 281 星标
  • 收录于

安装命令

npx skills add https://github.com/aliyun/alibabacloud-aiops-skills --skill alibabacloud-dataworks-datastudio-develop

SKILL.md

DataWorks Data Development

❗ 5-SECOND SUMMARY — Read This First

Credentials: Run aliyun configure list first. The CLI is almost always pre-configured (STS token). Do NOT search for credential files — just check the CLI config.

Install plugin first: Run aliyun plugin install --names dataworks-public. All commands use plugin mode (kebab-case): aliyun dataworks-public create-node ...

APIs: create-workflow-definition → create-node (per node) → create-pipeline-run (deploy). For updates: update-node → create-pipeline-run. NEVER use deploy-file, submit-file, create-file, create-business.

FlowSpec: Copy the exact JSON from the "Quick Start" section below. Do NOT guess the format. version is "2.0.0", kind is "CycleWorkflow" or "Node". Common wrong values: apiVersion, type, Workflow, metadata — all wrong.

Publish after update: update-node → create-pipeline-run(type=Online) → poll get-pipeline-run → exec-pipeline-run-stage. deploy-file does NOT work.

⚡ MANDATORY: Read Before Any API Call

These absolute rules are NOT optional — violating ANY ONE means the task WILL FAIL: