Token导航 LogoToken导航

Agent Skill · 研究检索

alibabacloud-dataworks-data-governance(阿里巴巴云数据工场数据治理)

用于辅助数据整理、表格处理、CSV/Excel 分析、指标计算和图表准备。它适合让 Agent 清洗字段、汇总数据、发现异常、生成统计口径或把分析结果转成可读说明。使用时需要确认数据来源、字段含义和时间范围,避免把样本数据当全量事实;涉及敏感数据、导出文件或批量写回时,应先确认权限和脱敏边界。

alibabacloud-dataworks-data-governance 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为接触敏感数据;许可证为 MIT-0,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 30,203。

总安装 2,916周安装 124GitHub Stars 公开资料未说明下载 1,022核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
0.0.1-beta.1

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:alibabacloud-dataworks-data-governance(阿里巴巴云数据工场数据治理)
来源仓库:https://github.com/sdk-team/alibabacloud-dataworks-data-governance
安装命令:
openclaw skills install alibabacloud-dataworks-data-governance
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install alibabacloud-dataworks-data-governance

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

用于管理 DataWorks 数据资产标签,实现元数据分类与治理。支持创建、更新、绑定/解绑标签键值,提升数据可发现性。适用于数据目录建设与合规审计场景,标准化数据血缘管理。安装命令:openclaw skills install alibabacloud-dataworks-data-governance。

操作前需确认工作空间权限,避免误改他人数据标签。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install alibabacloud-dataworks-data-governance;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

alibabacloud-dataworks-data-governance 怎么安装?

在终端执行 openclaw skills install alibabacloud-dataworks-data-governance。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

alibabacloud-dataworks-data-governance 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

alibabacloud-dataworks-data-governance 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

alibabacloud-dataworks-data-governance 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

alibabacloud-dataworks-data-governance 用的人多吗?

公开数据是累计安装 2,916 次,近一周安装 124 次,下载 1,022 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

alibabacloud-dataworks-data-governance 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
alibabacloud-dataworks-data-governance

阿里巴巴云数据工场数据治理 · 本页

2,916—接触敏感数据MIT-0有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
alibabacloud-dataworks-data-governance
description
|
Triggers
data governance, data asset tags, DataWorks tags, CreateDataAssetTag, UpdateDataAssetTag, ListDataAssetTags, TagDataAssets, UnTagDataAssets, ListDataAssets, tag management, query data assets, list data assets

DataWorks Data Governance Tag Management

Manage data asset tags via the DataWorks Data Governance API, including creating, updating, and querying tag keys/values, as well as batch binding and unbinding tags on data assets.

FORBIDDEN API — DeleteDataAssetTag must NOT be used in this skill. Calling DeleteDataAssetTag is strictly prohibited. Do not implement, suggest, or invoke this API under any circumstances. If a user requests deletion of a tag key or tag value, inform them that this operation is outside the scope of this skill and must be handled through other authorized channels.

Architecture: DataWorks Data Governance Tag API (ROA style) + Alibaba Cloud Python Common SDK


Pre-check: Aliyun CLI >= 3.3.1 required Run aliyun version to verify >= 3.3.1. If not installed or version too low, see references/cli-installation-guide.md for installation instructions. Then [MUST] run aliyun configure set --auto-plugin-install true to enable automatic plugin installation.

Pre-check: Alibaba Cloud Credentials Required Security Rules: - NEVER read, echo, or print AK/SK values (e.g., echo $ALIBABA_CLOUD_ACCESS_KEY_ID is FORBIDDEN) - 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

Installation

pip3 install alibabacloud_tea_openapi==0.4.4 alibabacloud_credentials==1.0.8 alibabacloud_tea_util==0.3.14 alibabacloud_openapi_util==0.2.4

RAM Permissions

ProductRAM ActionResource ScopeDescription
DataWorksdataworks:CreateDataAssetTag*Create a data asset tag key
DataWorksdataworks:UpdateDataAssetTag*Update a data asset tag key
DataWorksdataworks:ListDataAssetTags*Query the data asset tag list
DataWorksdataworks:TagDataAssets*Bind tags to data assets
DataWorksdataworks:UnTagDataAssets*Unbind tags from data assets
DataWorksdataworks:ListDataAssets*Query the data asset list
[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 references/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

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.
ParameterRequired/OptionalDescriptionDefault
region_idRequiredAlibaba Cloud Region ID, e.g. cn-hangzhouNone — confirm with user
tag_keyRequired (create/update)Tag key nameNone — confirm with user
tag_valuesOptionalList of tag values[]
descriptionOptionalDescription of the tag keyNone
categoryOptionalTag category: Normal or CUSTOMNormal
managersOptionalList of tag manager user IDs[]
data_asset_idsRequired (bind/unbind)List of data asset identifiers, max 100None — confirm with user
data_asset_typeRequired (bind/unbind)Asset type, e.g. ACS::DataWorks::TableNone — confirm with user
project_idConditionally requiredProject space ID (required when DataAssetType is ACS::DataWorks::Task)None
env_typeConditionally requiredProject environment — required when project_id is set: Prod / DevNone
asset_typeRequired (ListDataAssets)Asset object type: Table, Task, Node, WorkFlow, DataServiceApi, DataQualityRuleNone — confirm with user
asset_tagsOptional (ListDataAssets)Filter by tag key-value list, max 20, e.g. [{"Key":"k1","Value":"v1"}]None
asset_nameOptional (ListDataAssets)Asset name keyword for fuzzy searchNone
asset_idsOptional (ListDataAssets)List of asset module IDsNone
asset_ownerOptional (ListDataAssets)Asset owner user IDNone
sort_byOptional (ListDataAssets)Sort field and direction, e.g. CreateTime DescCreateTime Desc

Core Workflow

Initialize SDK Client

import re
from alibabacloud_tea_openapi.client import Client as OpenApiClient
from alibabacloud_credentials.client import Client as CredentialClient
from alibabacloud_tea_openapi import models as open_api_models
from alibabacloud_tea_util import models as util_models
from alibabacloud_openapi_util.client import Client as OpenApiUtilClient
import json

_VALID_DATA_ASSET_TYPES = {
    'ACS::DataWorks::Table', 'ACS::DataWorks::Task',
    'ACS::DataWorks::Node', 'ACS::DataWorks::WorkFlow',
    'ACS::DataWorks::DataServiceApi', 'ACS::DataWorks::DataQualityRule'
}
_VALID_ASSET_TYPES = {'Table', 'Task', 'Node', 'WorkFlow', 'DataServiceApi', 'DataQualityRule'}
_VALID_CATEGORIES  = {'Normal', 'CUSTOM'}
_VALID_ENV_TYPES   = {'Prod', 'Dev'}

def _validate_region_id(region_id):
    if not isinstance(region_id, str) or not region_id:
        raise ValueError('region_id must be a non-empty string')
    if not re.match(r'^[a-z]{2}-[a-z0-9-]+$', region_id):
        raise ValueError(f'Invalid region_id format: {region_id!r}')

def _validate_tags(tags, max_len=20):
    if not isinstance(tags, list) or len(tags) == 0:
        raise ValueError('tags must be a non-empty list')
    if len(tags) > max_len:
        raise ValueError(f'tags exceeds max length {max_len}, got {len(tags)}')
    for t in tags:
        if not isinstance(t, dict) or 'Key' not in t or 'Value' not in t:
            raise ValueError('Each tag must be a dict with "Key" and "Value"')

def _validate_asset_ids(ids, max_len=100):
    if not isinstance(ids, list) or len(ids) == 0:
        raise ValueError('data_asset_ids must be a non-empty list')
    if len(ids) > max_len:
        raise ValueError(f'data_asset_ids exceeds max length {max_len}, got {len(ids)}')

def _validate_page(page_number, page_size):
    if not isinstance(page_number, int) or page_number < 1:
        raise ValueError(f'page_number must be an integer >= 1, got {page_number!r}')
    if not isinstance(page_size, int) or not (1 <= page_size <= 100):
        raise ValueError(f'page_size must be an integer between 1 and 100, got {page_size!r}')

def create_client(region_id: str) -> OpenApiClient:
    _validate_region_id(region_id)
    credential = CredentialClient()
    config = open_api_models.Config(credential=credential)
    config.endpoint = f'dataworks.{region_id}.aliyuncs.com'
    config.user_agent = 'AlibabaCloud-Agent-Skills'
    return OpenApiClient(config)

1. Create Tag Key (CreateDataAssetTag)

def create_data_asset_tag(client, key: str, values=None, description=None,
                           value_policy=None, category='Normal', managers=None):
    if not isinstance(key, str) or not key.strip():
        raise ValueError('key must be a non-empty string')
    if category not in _VALID_CATEGORIES:
        raise ValueError(f'category must be one of {_VALID_CATEGORIES}, got {category!r}')
    if values is not None:
        if not isinstance(values, list):
            raise ValueError('values must be a list')
    if managers is not None:
        if not isinstance(managers, list):
            raise ValueError('managers must be a list')

    params = open_api_models.Params(
        action='CreateDataAssetTag',
        version='2024-05-18',
        protocol='HTTPS',
        method='POST',
        auth_type='AK',
        style='ROA',
        pathname='/api/v1/data-governance/tags',
        req_body_type='json',
        body_type='json'
    )
    body = {'Key': key}
    if values is not None:
        body['Values'] = values
    if description is not None:
        body['Description'] = description
    if value_policy is not None:
        body['ValuePolicy'] = value_policy
    if category:
        body['Category'] = category
    if managers is not None:
        body['Managers'] = managers

    request = open_api_models.OpenApiRequest(body=body)
    runtime = util_models.RuntimeOptions()
    runtime.connect_timeout = 5000   # ms
    runtime.read_timeout = 30000     # ms
    return client.call_api(params, request, runtime)

2. Update Tag Key (UpdateDataAssetTag)

def update_data_asset_tag(client, key: str, values=None, description=None, managers=None):
    if not isinstance(key, str) or not key.strip():
        raise ValueError('key must be a non-empty string')
    if values is not None:
        if not isinstance(values, list):
            raise ValueError('values must be a list')
    if managers is not None:
        if not isinstance(managers, list):
            raise ValueError('managers must be a list')

    params = open_api_models.Params(
        action='UpdateDataAssetTag',
        version='2024-05-18',
        protocol='HTTPS',
        method='PUT',
        auth_type='AK',
        style='ROA',
        pathname='/api/v1/data-governance/tags',
        req_body_type='json',
        body_type='json'
    )
    body = {'Key': key}
    if values is not None:
        body['Values'] = values
    if description is not None:
        body['Description'] = description
    if managers is not None:
        body['Managers'] = managers

    request = open_api_models.OpenApiRequest(body=body)
    runtime = util_models.RuntimeOptions()
    runtime.connect_timeout = 5000   # ms
    runtime.read_timeout = 30000     # ms
    return client.call_api(params, request, runtime)

3. List Tag Keys (ListDataAssetTags)

def list_data_asset_tags(client, key=None, category=None, page_number=1, page_size=10):
    _validate_page(page_number, page_size)
    if category is not None and category not in _VALID_CATEGORIES:
        raise ValueError(f'category must be one of {_VALID_CATEGORIES}, got {category!r}')

    params = open_api_models.Params(
        action='ListDataAssetTags',
        version='2024-05-18',
        protocol='HTTPS',
        method='GET',
        auth_type='AK',
        style='ROA',
        pathname='/api/v1/data-governance/tags',
        req_body_type='json',
        body_type='json'
    )
    queries = {
        'PageNumber': page_number,
        'PageSize': page_size
    }
    if key:
        queries['Key'] = key
    if category:
        queries['Category'] = category

    request = open_api_models.OpenApiRequest(
        query=OpenApiUtilClient.query(queries)
    )
    runtime = util_models.RuntimeOptions()
    runtime.connect_timeout = 5000   # ms
    runtime.read_timeout = 30000     # ms
    return client.call_api(params, request, runtime)

4. Bind Tags to Data Assets (TagDataAssets)

def tag_data_assets(client, tags: list, data_asset_ids: list, data_asset_type: str,
                    project_id=None, env_type=None, auto_trace_enable=False):
    _validate_tags(tags, max_len=20)
    _validate_asset_ids(data_asset_ids, max_len=100)
    if data_asset_type not in _VALID_DATA_ASSET_TYPES:
        raise ValueError(f'data_asset_type must be one of {_VALID_DATA_ASSET_TYPES}, got {data_asset_type!r}')
    if data_asset_type == 'ACS::DataWorks::Task':
        if project_id is None or env_type is None:
            raise ValueError('project_id and env_type are required when data_asset_type is ACS::DataWorks::Task')
    if env_type is not None and env_type not in _VALID_ENV_TYPES:
        raise ValueError(f'env_type must be one of {_VALID_ENV_TYPES}, got {env_type!r}')

    params = open_api_models.Params(
        action='TagDataAssets',
        version='2024-05-18',
        protocol='HTTPS',
        method='POST',
        auth_type='AK',
        style='ROA',
        pathname='/api/v1/data-governance/tags/bind',
        req_body_type='json',
        body_type='json'
    )
    body = {
        'Tags': tags,
        'DataAssetIds': data_asset_ids,
        'DataAssetType': data_asset_type,
        'AutoTraceEnable': auto_trace_enable
    }
    if project_id is not None:
        body['ProjectId'] = project_id
    if env_type is not None:
        body['EnvType'] = env_type

    request = open_api_models.OpenApiRequest(body=body)
    runtime = util_models.RuntimeOptions()
    runtime.connect_timeout = 5000   # ms
    runtime.read_timeout = 30000     # ms
    return client.call_api(params, request, runtime)

5. List Data Assets (ListDataAssets)

def list_data_assets(client, asset_type: str, tags=None, name=None, ids=None,
                     owner=None, project_id=None, sort_by=None,
                     page_number=1, page_size=10):
    if asset_type not in _VALID_ASSET_TYPES:
        raise ValueError(f'asset_type must be one of {_VALID_ASSET_TYPES}, got {asset_type!r}')
    _validate_page(page_number, page_size)
    if tags is not None:
        _validate_tags(tags, max_len=20)

    params = open_api_models.Params(
        action='ListDataAssets',
        version='2024-05-18',
        protocol='HTTPS',
        method='GET',
        auth_type='AK',
        style='ROA',
        pathname='/api/v1/data-governance/assets',
        req_body_type='json',
        body_type='json'
    )
    queries = {
        'Type': asset_type,
        'PageNumber': page_number,
        'PageSize': page_size
    }
    if tags is not None:
        queries['Tags'] = json.dumps(tags)
    if name is not None:
        queries['Name'] = name
    if ids is not None:
        queries['Ids'] = json.dumps(ids)
    if owner is not None:
        queries['Owner'] = owner
    if project_id is not None:
        queries['ProjectId'] = project_id
    if sort_by is not None:
        queries['SortBy'] = sort_by

    request = open_api_models.OpenApiRequest(
        query=OpenApiUtilClient.query(queries)
    )
    runtime = util_models.RuntimeOptions()
    runtime.connect_timeout = 5000   # ms
    runtime.read_timeout = 30000     # ms
    return client.call_api(params, request, runtime)

6. Unbind Tags from Data Assets (UnTagDataAssets)

def untag_data_assets(client, tags: list, data_asset_ids: list, data_asset_type: str,
                      project_id=None, env_type=None):
    _validate_tags(tags, max_len=20)
    _validate_asset_ids(data_asset_ids, max_len=100)
    if data_asset_type not in _VALID_DATA_ASSET_TYPES:
        raise ValueError(f'data_asset_type must be one of {_VALID_DATA_ASSET_TYPES}, got {data_asset_type!r}')
    if data_asset_type == 'ACS::DataWorks::Task':
        if project_id is None or env_type is None:
            raise ValueError('project_id and env_type are required when data_asset_type is ACS::DataWorks::Task')
    if env_type is not None and env_type not in _VALID_ENV_TYPES:
        raise ValueError(f'env_type must be one of {_VALID_ENV_TYPES}, got {env_type!r}')

    params = open_api_models.Params(
        action='UnTagDataAssets',
        version='2024-05-18',
        protocol='HTTPS',
        method='POST',
        auth_type='AK',
        style='ROA',
        pathname='/api/v1/data-governance/tags/unbind',
        req_body_type='json',
        body_type='json'
    )
    body = {
        'Tags': tags,
        'DataAssetIds': data_asset_ids,
        'DataAssetType': data_asset_type
    }
    if project_id is not None:
        body['ProjectId'] = project_id
    if env_type is not None:
        body['EnvType'] = env_type

    request = open_api_models.OpenApiRequest(body=body)
    runtime = util_models.RuntimeOptions()
    runtime.connect_timeout = 5000   # ms
    runtime.read_timeout = 30000     # ms
    return client.call_api(params, request, runtime)

Response Handling

def handle_response(response):
    status_code = response.get('statusCode')
    body = response.get('body', {})
    if status_code == 200 and body.get('Data'):
        print(f"[SUCCESS] RequestId: {body.get('RequestId')}")
        return body.get('Data')
    else:
        code = body.get('Code')
        message = body.get('Message')
        raise Exception(f"[FAIL] Code={code}, Message={message}, RequestId={body.get('RequestId')}")

Success Verification

Operation success criteria:

  • HTTP status code 200
  • Response body Data field is true (create/update/bind/unbind operations)
  • Response body Data is an object (ListDataAssetTags, ListDataAssets)

For detailed step-by-step verification commands, see references/verification-method.md.


Cleanup

client = create_client('cn-hangzhou')  # Replace with actual Region

# Unbind tags from data assets
untag_data_assets(client,
    tags=[{"Key": "k1", "Value": "v1"}],
    data_asset_ids=["maxcompute-table.project.tableName"],
    data_asset_type="ACS::DataWorks::Table"
)
Note: Deletion of tag keys or tag values via DeleteDataAssetTag is not supported in this skill. Do not attempt to call this API.

Best Practices

  1. Batch limits: Tags max 20, DataAssetIds max 100 per request — split into batches if needed
  2. Task-type assets: When DataAssetType is ACS::DataWorks::Task, both ProjectId and EnvType are required
  3. Value policy: Use ValuePolicy (e.g. regex ^L[1-7]$) when creating a tag key to enforce valid value formats
  4. Least privilege: Create a dedicated RAM role for tag management with only the required permissions
  5. Throttling retry: Use exponential backoff when encountering Throttling errors
  6. Pagination: ListDataAssetTags and ListDataAssets default to 10 per page, max 100 — use TotalCount to calculate total pages
  7. ListDataAssets serialization: Tags and Ids query parameters must be JSON-serialized strings (use json.dumps())
  8. ListDataAssets sort: Default sort is CreateTime Desc; also supports ModifyTime and HealthScore

Reference Documents

DocumentDescription
cli-installation-guide.mdAliyun CLI installation and configuration guide
ram-policies.mdRAM permission policies required by this Skill
related-commands.mdAPI command reference
verification-method.mdStep-by-step success verification
acceptance-criteria.mdAcceptance criteria with correct/incorrect examples

平台分布

OpenClaw

90.94%
按下载量换算929

安全审计

VirusTotal

未展示

ClawScan

可疑

Static analysis

通过

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills