/alibabacloud-dataworks-data-agent

name: alibabacloud-dataworks-data-agent
description: >
  Interact with DataWorks Data Agent for conversational data analysis,
  session lifecycle management, and artifact download. Use this Skill when users
  want to chat with a Data Agent for data querying, create or resume Agent
  sessions, list session history, download analysis artifacts, check
  token usage, or cancel an active session.
license: Apache-2.0
compatibility: >
  Requires aliyun CLI >= 3.4.5 with dataworks-public plugin >= 0.5.9.
  Credentials managed by aliyun CLI profiles.
metadata:
  domain: aiops
  owner: dataworks-team
  contact: dataworks-agent@alibaba-inc.com

DataWorks Data Agent

Interact with DataWorks Data Agent via `aliyun dataworks-public` CLI.

Prerequisites

• aliyun CLI >= 3.4.5: `aliyun version`
• dataworks-public plugin >= 0.5.9: `aliyun plugin list | grep dataworks`
• If plugin outdated: `aliyun plugin update aliyun-cli-dataworks-public`
• Verify profile: `aliyun configure list | grep <profile>`

API Reference

| Action | Key Params | |---|---| | `create-agent-session` | `{"Meta":{"Agent":{"AgentName":"dataworks_data_agent"}}}` | | `prompt-agent-session` | `{"SessionId":"<id>","Prompt":[{"Type":"text","Text":"..."}]}` | | `load-agent-session` | `{"SessionId":"<id>"}` | | `list-agent-sessions` | `{"AgentName":"dataworks_data_agent","MaxResults":20}` | | `list-agent-session-artifacts` | `{"SessionId":"<id>"}` | | `get-agent-session-artifact-meta` | `{"SessionId":"<id>","ArtifactPath":"<path>"}` | | `get-agent-session-token-usage` | `{"SessionId":"<id>"}` | | `cancel-agent-session` | `{"SessionId":"<id>"}` |

Usage

aliyun dataworks-public <action> --profile <profile> --region <region> --params '<JSON>' --user-agent AlibabaCloud-Agent-Skills/alibabacloud-dataworks-data-agent/<session-id>

Workflow

# 1. Create session (extract SessionId from $.JsonRpcResponse.Result.SessionId)
#    NOTE: do NOT add a top-level ClientToken field — the dataworks-public plugin
#    rejects it ("unknown field: ClientToken"); keep the request body minimal
aliyun dataworks-public create-agent-session --profile default --region cn-shanghai \
  --params '{"Meta":{"Agent":{"AgentName":"dataworks_data_agent"}}}' \
  --user-agent AlibabaCloud-Agent-Skills/alibabacloud-dataworks-data-agent/<session-id>

# 2. Send prompt (reuse SessionId from step 1)
aliyun dataworks-public prompt-agent-session --profile default --region cn-shanghai \
  --params '{"SessionId":"<session-id>","Prompt":[{"Type":"text","Text":"your question"}]}' \
  --user-agent AlibabaCloud-Agent-Skills/alibabacloud-dataworks-data-agent/<session-id>

# 3. List artifacts
aliyun dataworks-public list-agent-session-artifacts --profile default --region cn-shanghai \
  --params '{"SessionId":"<session-id>"}' \
  --user-agent AlibabaCloud-Agent-Skills/alibabacloud-dataworks-data-agent/<session-id>

# 4. Download artifact (path must come from list result)
aliyun dataworks-public get-agent-session-artifact-meta --profile default --region cn-shanghai \
  --params '{"SessionId":"<session-id>","ArtifactPath":"<path>"}' \
  --user-agent AlibabaCloud-Agent-Skills/alibabacloud-dataworks-data-agent/<session-id>

# 5. Load history
aliyun dataworks-public load-agent-session --profile default --region cn-shanghai \
  --params '{"SessionId":"<session-id>"}' \
  --user-agent AlibabaCloud-Agent-Skills/alibabacloud-dataworks-data-agent/<session-id>

# 6. Check token usage
aliyun dataworks-public get-agent-session-token-usage --profile default --region cn-shanghai \
  --params '{"SessionId":"<session-id>"}' \
  --user-agent AlibabaCloud-Agent-Skills/alibabacloud-dataworks-data-agent/<session-id>

# 7. Cancel session
aliyun dataworks-public cancel-agent-session --profile default --region cn-shanghai \
  --params '{"SessionId":"<session-id>"}' \
  --user-agent AlibabaCloud-Agent-Skills/alibabacloud-dataworks-data-agent/<session-id>

Context & File Attachment

# With dataset context
aliyun dataworks-public prompt-agent-session --profile default --region cn-shanghai \
  --params '{"SessionId":"<id>","Prompt":[{"Type":"text","Text":"query"}],"Meta":{"Context":"{\"datasetUuid\":\"xxx\"}"}}' \
  --user-agent AlibabaCloud-Agent-Skills/alibabacloud-dataworks-data-agent/<session-id>

# With file attachment
aliyun dataworks-public prompt-agent-session --profile default --region cn-shanghai \
  --params '{"SessionId":"<id>","Prompt":[{"Type":"text","Text":"analyze"},{"Type":"file","Name":"data.csv","Uri":"file:///path/to/data.csv"}]}' \
  --user-agent AlibabaCloud-Agent-Skills/alibabacloud-dataworks-data-agent/<session-id>

Guidelines

• **Unclear intent** (MANDATORY): When the user's request is vague (e.g., "help me handle this") without specifying a clear action target (data analysis / session management), you MUST ask the user to clarify before calling any API. Do NOT guess or infer the intent — ask what they want to do and what specific data/target they need. Only proceed after the user provides clear instructions. Your final response MUST contain a direct question to the user (e.g., "What would you like to do?"). Do NOT end the task by writing a note or file about the vagueness — you MUST ask the user interactively.
• **Session reuse**: If the user mentions a previous conversation, check `list-agent-sessions` for non-RELEASED sessions and reuse the SessionId.
• **No active session** (MANDATORY): If the user states they haven't created a session, see Security Constraint #7.
• **Follow-up turns**: If the user sends a short acknowledgment after your report (e.g., "OK"), your final response MUST still restate the key conclusion of the workflow in one line (e.g., the "No active session" outcome, or the analysis/session result) before closing — do NOT end with only a generic acknowledgment such as "Got it, let me know if you need anything".
• **Reporting completeness** (MANDATORY): Your final response MUST mention each action the user reques