/create-unstructured-workflow
从一句业务需求(如"PPT 按页构建解决方案知识库")出发,端到端创建 Dataphin 非结构化工作流: 需求分析 → 算子链路设计 → 数据集设计与创建 → 工作流 JSON 组装 → create-work-flow-by-json 创建 → 输出验证指引。 当用户场景涉及非结构化数据处理(文档解析 / 图片理解 / 音视频处理 / 知识库构建 / 向量化入库)或数据集增删改查时进入。 触发词:非结构化工作流、创建工作流、知识库构建、文档解析、向量化、create-work-flow-by-json、unstructured workflow。
$ npx -y skills add aliyun/alibabacloud-aiops-skills --skill create-unstructured-workflow --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/create-unstructured-workflow
Context preview
The summary Claude sees to decide when to auto-load this skill.
从一句业务需求(如"PPT 按页构建解决方案知识库")出发,端到端创建 Dataphin 非结构化工作流: 需求分析 → 算子链路设计 → 数据集设计与创建 → 工作流 JSON 组装 → create-work-flow-by-json 创建 → 输出验证指引。 当用户场景涉及非结构化数据处理(文档解析 / 图片理解 / 音视频处理 / 知识库构建 / 向量化入库)或数据集增删改查时进入。 触发词:非结构化工作流、创建工作流、知识库构建、文档解析、向量化、create-work-flow-by-json、unstructured workflow。
SKILL.md
create-unstructured-workflow.SKILL.mdname: create-unstructured-workflow
description: |-
从一句业务需求(如"PPT 按页构建解决方案知识库")出发,端到端创建 Dataphin 非结构化工作流:
需求分析 → 算子链路设计 → 数据集设计与创建 → 工作流 JSON 组装 → create-work-flow-by-json 创建 → 输出验证指引。
当用户场景涉及非结构化数据处理(文档解析 / 图片理解 / 音视频处理 / 知识库构建 / 向量化入库)或数据集增删改查时进入。
触发词:非结构化工作流、创建工作流、知识库构建、文档解析、向量化、create-work-flow-by-json、unstructured workflow。
关键限制:**仅支持离线(OFFLINE)**——实时工作流(TaskType=5/REALTIME 数据集)不在范围,Step 1 预检到即告知;仅 BASIC 项目(Env=PROD);数据集 5 字段建后不可变;LLM/评分/去重算子不吃 URL 需桥接;环境值必须回读禁止编造;写操作前 HITL 确认。
创建 Dataphin 非结构化工作流(需求 → 数据集 → 工作流 → 验证)
1. Scenario Description
用户用一句业务需求触发(例:"把 OSS 上的产品 PPT 按页解析,构建可检索的解决方案知识库"),本 skill 自动完成:
1. 需求分析(识别模态 + 格式兼容预检); 2. 算子链路设计(输出设计稿,**暂停等用户确认**); 3. 数据集准备(`list-datasets` 搜索复用 → 不存在则 `create-dataset` → `get-dataset` 回读); 4. 组装工作流 JSON(算子骨架 + 回读环境值 + 业务定制提示词); 5. `create-work-flow-by-json` 创建(默认测试模式 `TaskType=3 + Submit=false`); 6. 输出三层验证指引(结构自检 → PipelineId → 界面回显 + 试跑)。
**Architecture**:`Dataphin Tenant + BASIC Project + Dataset(文件存储 OSS + 元数据存储 PG/Milvus) + 非结构化工作流(算子 DAG) + 模型实例(LLM/Embedding)`。
2. Installation
aliyun plugin install --names aliyun-cli-dataphin-public
(详见 [`references/cli-installation-guide.md`](references/cli-installation-guide.md))
3. Environment Variables
**认证信息统一使用阿里云 CLI 配置(profile):凭证预先通过 `aliyun configure --profile <name>` 配置,本 skill 不直接读取 AK/SK 环境变量或任何本地文件。**
| 配置项 | 必填 | 说明 | |---|---|---| | CLI profile | 是 | `aliyun configure list` 中的有效 profile(AK / STS / RamRoleArn 均可);执行命令时用 `--profile <name>` 指定,缺省用默认 profile | | endpoint | 独立部署时必填 | 公共云用默认 endpoint;独立部署/POC 环境由父 skill Step 0 配置专用 profile(含 endpoint)并统一透传 | | `DATAPHIN_PROFILE` | 否 | 多租户场景下的 dataphin 本地 profile 名(`--dataphin-profile`) |
4. Authentication
> **Pre-check: Alibaba Cloud Credentials Required** > > **Security Rules:** > - **NEVER** read, echo, or print AK/SK values > - **NEVER** ask the user to input AK/SK directly in the conversation or command line > - **NEVER** use `aliyun configure set` with literal credential values > - **ONLY** use `aliyun configure list` to check credential status > > ```bash > aliyun configure list > ``` > Check the output for a valid profile (AK, STS, or OAuth identity). > > **If no valid profile exists, STOP here.** > 1. Obtain credentials from [Alibaba Cloud Console](https://ram.console.aliyun.com/manage/ak) > 2. Configure credentials **outside of this session** (via `aliyun configure` in terminal or environment variables in shell profile) > 3. Return and re-run after `aliyun configure list` shows a valid profile
**Pre-check: Aliyun CLI >= 3.4.8 required** > Run `aliyun version` to verify >= 3.4.8. If not installed or version too low, > see `references/cli-installation-guide.md` for installation instructions.
**Pre-check: Aliyun CLI plugin update required** > [MUST] run `aliyun configure set --auto-plugin-install true` to enable automatic plugin installation. > [MUST] run `aliyun plugin update` to ensure that any existing plugins are always up-to-date.
5. RAM Policy
最小权限策略详见 [`../../ram-policies.md`](../../ram-policies.md)。
> **[MUST] Permission Failure Handling:** When any command or API call fails due to permission errors at any point during execution, follow this process: > 1. Read `../../ram-policies.md` to get the full list of permissions required by this SKILL > 2. Use `ram-permission-diagnose` skill to guide the user through requesting the necessary permissions > 3. Pause and wait until the user confirms that the required permissions have been granted
6. Parameter Confirmation
> **IMPORTANT: Parameter Confirmation** — Before executing any command or API call, > ALL user-customizable parameters (e.g., RegionId, instance names, CIDR blocks, > passwords, domain names, resource specifications, etc.) MUST be confirmed with the > user. Do NOT assume or use default values without explicit user approval.
| 参数 | 必填 | 描述 | 默认值 | |---|---|---|---| | `--op-tenant-id` | 是 | 租户 ID(大整数,shell 变量传递) | — | | ProjectId | 是 | BASIC 模式项目 ID | — | | 业务需求描述 | 是 | 一句话业务目标(决定模态与链路) | — | | 源数据格式 | 是 | 文件扩展名清单(决定格式兼容预检结果) | — | | 数据集名 / 表名 | 是 | 用户确认(表名须匹配 `^[a-z][a-z0-9_]{0,63}$`) | — | | TaskName / Directory | 是 | 工作流任务名 / 所属目录 | 测试目录 | | TaskType / Submit | 否 | 调度类型 / 是否提交 | `3`(手动)/ `false` |
7. Observability (MUST follow for every aliyun command)
**session-id 由父 skill `alibabacloud-dataphin-skills` 在套件入口加载时生成(32-char 小写 hex),本子 skill 加载时直接继承同一 session-id,不再重新生成。**
**Rule: Every `aliyun` CLI command that calls a cloud API MUST include the `--user-agent` flag.** Local utility commands (e.g. `configure`, `plugin`, `version`) do not support this flag and should be excluded.
--user-agent AlibabaCloud-Agent-Skills/create-unstructured-workflow/{session-id}Example (assuming session-id is `a1b2c3d4e5f6a7b8c9d0e1f2a3b4c5d6`):
aliyun dataphin-public list-datasets --op-tenant-id "$TENANT_ID" \
--dataset-query '{"ProjectId": 123, "Keyword": "知识库", "IncludeVersionList": true, "Page": 1, "PageSize": 10}' \
--user-agent AlibabaCloud-Agent-Skills/create-unstructured-workflow/a1b2c3d4e5f6a7b8c9d0e1f2a3b4c5d6Do not skip, alter the format, or omit `--user-agent` on any `aliyun` API command invocation.
8. Core Workflow(六步流程)
TENANT_ID="30001011" # 租户 ID
PROJECT_ID="789" # BASIC 模式项目 ID
PROFILE="<aliyun configure list 中的有效 profile 名>"
SESSION_ID="<inherited from alibabacloud-dataphin-skills>"
UA="AlibabaCloud-Agent-Skills/create-unstructured-workflow/$SESSION_ID"
**本 skill 所有 `aliyun` API 命令统一携带 `--profile "$PROFILE"`(认证信息只来自 CLI 配置);独立部署模式下按父 skill Step 0 约定另追加 `--skip-secure-verify`。**
**铁律:所有算子配置、字段结构、枚举值只能来自 `references/` 参考文档或 API 实时回读,禁止凭记忆编造。**
Step 1 需求分析(只读,不调 API)
1. **覆盖边界预检(先于一切,30 秒内给结论)**:出现下列任一信号——用户提“**实时**工作流”/要求 `TaskType=5`,或输入数据集 `Scenario=REALTIME`(元数据为 STREAM_TABLE 实时元表、无 MetadataStorageConfig)——**立即按实时能力边界处置**(见 §12 ✗ 平台限制):有已有实时工作流可回读作基线 → 可走复刻/变体链路([`references/realtime-workflow-notes.md`](references/realtime-workfl
Read more
name: create-unstructured-workflow description: |- 从一句业务需求(如"PPT 按页构建解决方案知识库")出发,端到端创建 Dataphin 非结构化工作流: 需求分析 → 算子链路设计 → 数据集设计与创建 → 工作流 JSON 组装 → create-work-flow-by-json 创建 → 输出验证指引。 当用户场景涉及非结构化数据处理(文档解析 / 图片理解 / 音视频处理 / 知识库构建 / 向量化入库)或数据集增删改查时进入。 触发词:非结构化工作流、创建工作流、知识库构建、文档解析、向量化、create-work-flow-by-json、unstructured workflow。 关键限制:**仅支持离线(OFFLINE)**——实时工作流(TaskType=5/REALTIME 数据集)不在范围,Step 1 预检到即告知;仅 BASIC 项目(Env=PROD);数据集 5 字段建后不可变;LLM/评分/去重算子不吃 URL 需桥接;环境值必须回读禁止编造;写操作前 HITL 确认。
创建 Dataphin 非结构化工作流(需求 → 数据集 → 工作流 → 验证)
1. Scenario Description
用户用一句业务需求触发(例:"把 OSS 上的产品 PPT 按页解析,构建可检索的解决方案知识库"),本 skill 自动完成:
1. 需求分析(识别模态 + 格式兼容预检); 2. 算子链路设计(输出设计稿,**暂停等用户确认**); 3. 数据集准备(`list-datasets` 搜索复用 → 不存在则 `create-dataset` → `get-dataset` 回读); 4. 组装工作流 JSON(算子骨架 + 回读环境值 + 业务定制提示词); 5. `create-work-flow-by-json` 创建(默认测试模式 `TaskType=3 + Submit=false`); 6. 输出三层验证指引(结构自检 → PipelineId → 界面回显 + 试跑)。
**Architecture**:`Dataphin Tenant + BASIC Project + Dataset(文件存储 OSS + 元数据存储 PG/Milvus) + 非结构化工作流(算子 DAG) + 模型实例(LLM/Embedding)`。
2. Installation
aliyun plugin install --names aliyun-cli-dataphin-public
(详见 [`references/cli-installation-guide.md`](references/cli-installation-guide.md))
3. Environment Variables
**认证信息统一使用阿里云 CLI 配置(profile):凭证预先通过 `aliyun configure --profile <name>` 配置,本 skill 不直接读取 AK/SK 环境变量或任何本地文件。**
| 配置项 | 必填 | 说明 | |---|---|---| | CLI profile | 是 | `aliyun configure list` 中的有效 profile(AK / STS / RamRoleArn 均可);执行命令时用 `--profile <name>` 指定,缺省用默认 profile | | endpoint | 独立部署时必填 | 公共云用默认 endpoint;独立部署/POC 环境由父 skill Step 0 配置专用 profile(含 endpoint)并统一透传 | | `DATAPHIN_PROFILE` | 否 | 多租户场景下的 dataphin 本地 profile 名(`--dataphin-profile`) |
4. Authentication
> **Pre-check: Alibaba Cloud Credentials Required** > > **Security Rules:** > - **NEVER** read, echo, or print AK/SK values > - **NEVER** ask the user to input AK/SK directly in the conversation or command line > - **NEVER** use `aliyun configure set` with literal credential values > - **ONLY** use `aliyun configure list` to check credential status > > ```bash > aliyun configure list > ``` > Check the output for a valid profile (AK, STS, or OAuth identity). > > **If no valid profile exists, STOP here.** > 1. Obtain credentials from [Alibaba Cloud Console](https://ram.console.aliyun.com/manage/ak) > 2. Configure credentials **outside of this session** (via `aliyun configure` in terminal or environment variables in shell profile) > 3. Return and re-run after `aliyun configure list` shows a valid profile
**Pre-check: Aliyun CLI >= 3.4.8 required** > Run `aliyun version` to verify >= 3.4.8. If not installed or version too low, > see `references/cli-installation-guide.md` for installation instructions.
**Pre-check: Aliyun CLI plugin update required** > [MUST] run `aliyun configure set --auto-plugin-install true` to enable automatic plugin installation. > [MUST] run `aliyun plugin update` to ensure that any existing plugins are always up-to-date.
5. RAM Policy
最小权限策略详见 [`../../ram-policies.md`](../../ram-policies.md)。
> **[MUST] Permission Failure Handling:** When any command or API call fails due to permission errors at any point during execution, follow this process: > 1. Read `../../ram-policies.md` to get the full list of permissions required by this SKILL > 2. Use `ram-permission-diagnose` skill to guide the user through requesting the necessary permissions > 3. Pause and wait until the user confirms that the required permissions have been granted
6. Parameter Confirmation
> **IMPORTANT: Parameter Confirmation** — Before executing any command or API call, > ALL user-customizable parameters (e.g., RegionId, instance names, CIDR blocks, > passwords, domain names, resource specifications, etc.) MUST be confirmed with the > user. Do NOT assume or use default values without explicit user approval.
| 参数 | 必填 | 描述 | 默认值 | |---|---|---|---| | `--op-tenant-id` | 是 | 租户 ID(大整数,shell 变量传递) | — | | ProjectId | 是 | BASIC 模式项目 ID | — | | 业务需求描述 | 是 | 一句话业务目标(决定模态与链路) | — | | 源数据格式 | 是 | 文件扩展名清单(决定格式兼容预检结果) | — | | 数据集名 / 表名 | 是 | 用户确认(表名须匹配 `^[a-z][a-z0-9_]{0,63}$`) | — | | TaskName / Directory | 是 | 工作流任务名 / 所属目录 | 测试目录 | | TaskType / Submit | 否 | 调度类型 / 是否提交 | `3`(手动)/ `false` |
7. Observability (MUST follow for every aliyun command)
**session-id 由父 skill `alibabacloud-dataphin-skills` 在套件入口加载时生成(32-char 小写 hex),本子 skill 加载时直接继承同一 session-id,不再重新生成。**
**Rule: Every `aliyun` CLI command that calls a cloud API MUST include the `--user-agent` flag.** Local utility commands (e.g. `configure`, `plugin`, `version`) do not support this flag and should be excluded.
--user-agent AlibabaCloud-Agent-Skills/create-unstructured-workflow/{session-id}Example (assuming session-id is `a1b2c3d4e5f6a7b8c9d0e1f2a3b4c5d6`):
aliyun dataphin-public list-datasets --op-tenant-id "$TENANT_ID" \
--dataset-query '{"ProjectId": 123, "Keyword": "知识库", "IncludeVersionList": true, "Page": 1, "PageSize": 10}' \
--user-agent AlibabaCloud-Agent-Skills/create-unstructured-workflow/a1b2c3d4e5f6a7b8c9d0e1f2a3b4c5d6Do not skip, alter the format, or omit `--user-agent` on any `aliyun` API command invocation.
8. Core Workflow(六步流程)
TENANT_ID="30001011" # 租户 ID PROJECT_ID="789" # BASIC 模式项目 ID PROFILE="<aliyun configure list 中的有效 profile 名>" SESSION_ID="<inherited from alibabacloud-dataphin-skills>" UA="AlibabaCloud-Agent-Skills/create-unstructured-workflow/$SESSION_ID"
**本 skill 所有 `aliyun` API 命令统一携带 `--profile "$PROFILE"`(认证信息只来自 CLI 配置);独立部署模式下按父 skill Step 0 约定另追加 `--skip-secure-verify`。**
**铁律:所有算子配置、字段结构、枚举值只能来自 `references/` 参考文档或 API 实时回读,禁止凭记忆编造。**
Step 1 需求分析(只读,不调 API)
1. **覆盖边界预检(先于一切,30 秒内给结论)**:出现下列任一信号——用户提“**实时**工作流”/要求 `TaskType=5`,或输入数据集 `Scenario=REALTIME`(元数据为 STREAM_TABLE 实时元表、无 MetadataStorageConfig)——**立即按实时能力边界处置**(见 §12 ✗ 平台限制):有已有实时工作流可回读作基线 → 可走复刻/变体链路([`references/realtime-workflow-notes.md`](references/realtime-workfl
Official Alibaba Cloud Agent Skills collection, providing AI agents with rich Alibaba Cloud product capabilities and general-purpose tooling.
Other skills on alibabacloud-aiops-skills.
- /alibabacloud-agentbay-aio-skills
Execute code in a secure cloud sandbox via AgentBay SDK. Use this skill whenever users request to run, execute, or evaluate code (Python, JavaScript, R, Java), including plotting charts, running scripts, or viewing code output. Covers requests like "run this code", "execute
Open skill - /alibabacloud-agentloop-dataset
Operate Alibaba Cloud AgentLoop Dataset resources with aliyun CLI and the AgentLoop API version 2026-05-20. Use when requests concern AgentLoop datasets, data rows, Dataset schemas, embedding fields, semantic search, ExecuteQuery, AgentSpace data, 数据集, 数据写入, 数据查询, 语义检索, or ask
Open skill - /alibabacloud-agentloop-evaluation
Orchestrate AgentLoop evaluation workflows through the Aliyun CLI plugin with safe previews, saved evaluator and evaluator-skill management, one-shot sample tests, trace or dataset batch runs, polling, and result inspection. Analyze evaluation quality and low-score cases from
Open skill - /alibabacloud-agentloop-experience
Proactively use AgentLoop Recall to retrieve prior Alibaba Cloud AgentLoop experience through the bundled SearchContext CLI whenever the user asks or implies that prior work may help. Trigger for requests to check, search, recall, retrieve, look up, review, consult, reference,
Open skill - /alibabacloud-agentloop-management
AgentLoop APM接入 / AI可观测接入 / 应用监控接入 / 自研探针 / 探针安装. Use for Python aliyun-bootstrap (aliyun-instrument), Java AliyunJavaAgent, Golang instgo, Node.js cms_node_sdk, PHP/.NET OpenTelemetry, ack-onepilot, LicenseKey, AgentLoop workspace agentloop-*. Also for LangChain, Dify,
Open skill - /alibabacloud-avatar-video
Use Alibaba Cloud DashScope API and LingMou to generate AI video and speech. Seven capabilities — (1) LivePortrait talking-head (image + audio → video, two-step), (2) EMO talking-head, (3) AA/AnimateAnyone full-body animation (three-step), (4) T2I text-to-image (Wan 2.x, default
Open skill

