Token导航 LogoToken导航TokenDH.com
研究检索敏感数据clawhub未标认证来源可访问clear审计提醒

alibabacloud-dms-skill阿里云 dms 技能

Agent Skill

alibabacloud-dms-skill 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

3,854

周安装

159

GitHub Stars

公开资料未说明

下载量

1,259
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

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-dms-skill(阿里云 dms 技能)
来源仓库:https://github.com/sdk-team/alibabacloud-dms-skill
安装命令:
openclaw skills install alibabacloud-dms-skill
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-dms-skill

简介

在阿里云 DMS 中搜索数据库并执行 SQL 查询与数据修改。

  • 支持多数据库类型连接与语句语法校验。
  • 适用于日常数据核查与临时修复操作。alibabacloud-dms-skill 属于研究检索类 Skill,可作为该场景下的辅助能力补充。
  • 安装命令:openclaw skills install alibabacloud-dms-skill。
  • 执行写操作前应备份数据,防止误删或格式错误导致业务中断。

SKILL.md

name
alibabacloud-dms-skill
description
|
Triggers
DMS query", "database query", "execute SQL", "search database", "DMS SQL", "insert data", "update data".

Alibaba Cloud DMS Database Read/Write

Search for target databases and execute SQL queries and data modifications via Alibaba Cloud DMS OpenAPI.

Scenario Description

This skill implements the following workflow:

  1. Search Target Database — Search databases by keyword to get Database ID
  2. Execute SQL Query — Execute SQL statements on the target database

Architecture

User Request → Search Database → Get Database ID → Execute SQL → Return Results

Prerequisites

AI-Mode Lifecycle (MUST follow in order)

This skill MUST run inside an AI-Mode session. Treat the following five steps as a strict lifecycle — do not skip, reorder, or interleave the setup steps with command execution:

1. aliyun configure ai-mode enable                                              # Enable AI-Mode
2. aliyun configure ai-mode set-user-agent AlibabaCloud-Agent-Skills/alibabacloud-dms-skill   # Register skill User-Agent
3. aliyun configure set --auto-plugin-install true && aliyun plugin update      # Plugin update
4. <execute DMS commands via ./scripts/*.sh>                                    # Execute commands
5. aliyun configure ai-mode disable                                             # Disable AI-Mode (Cleanup)

Steps 1–3 belong to setup (this section). Step 4 is covered by Core Workflow. Step 5 is covered by Cleanup.

Pre-checks

Pre-check 0: Aliyun CLI >= 3.3.3 required Run aliyun version to verify >= 3.3.3. If not installed or version too low, run curl -fsSL https://aliyuncli.alicdn.com/setup.sh | bash to install/update, or see references/cli-installation-guide.md for installation instructions.
Pre-check 1: Enable AI-Mode [MUST] run aliyun configure ai-mode enable to enable AI-Mode before any other configuration or command. This activates the AI-Mode session that downstream OpenAPI services use to recognize agent-issued traffic.
Pre-check 2: Register skill User-Agent under AI-Mode [MUST] run aliyun configure ai-mode set-user-agent AlibabaCloud-Agent-Skills/alibabacloud-dms-skill to register this skill's identifier as the AI-Mode User-Agent for the current session. Run this immediately after ai-mode enable and before any plugin update or DMS command.
Pre-check 3: 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. Plugin update MUST happen AFTER AI-Mode is enabled and the User-Agent is registered, so the plugin manager itself reports the correct identifier.
  • Aliyun CLI >= 3.3.3
  • jq (for JSON parsing): brew install jq
  • Credentials configured via aliyun configure
Pre-check 4: 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

[MUST] Per-command CLI User-Agent — In addition to the AI-Mode User-Agent registered in Pre-check 2, every aliyun CLI command invocation in step 4 MUST also include: --user-agent AlibabaCloud-Agent-Skills/alibabacloud-dms-skill The per-command flag and the AI-Mode session-level setting are complementary — both MUST be present so the identifier is sent on every request even if the AI-Mode session expires.

RAM Permissions

[MUST] RAM Permission Pre-check: Verify that the current user has the following RAM permissions before execution. See references/ram-policies.md for the complete permission list.

Parameter Confirmation

IMPORTANT: Parameter Confirmation — Before executing any command or API call, ALL user-customizable parameters (e.g., database keyword, SQL statement, db-id, etc.) MUST be confirmed with the user. Do NOT assume or use default values without explicit user approval.
ParameterRequired/OptionalDescriptionDefault
keywordRequiredDatabase search keyword (1-128 chars, alphanumeric)-
db-idRequiredDatabase ID (positive integer, obtained from search)-
sqlRequiredSQL statement to execute (1-10000 chars)-
logicOptionalWhether to use logic database modefalse
forceOptionalConfirm write operations (INSERT/UPDATE/DELETE)false
dry-runOptionalPreview write operations without executingfalse

Core Workflow

Task 1: Search Target Database

Search for databases by keyword to get the Database ID:

./scripts/search_database.sh <keyword> --json

Example:

# Search for databases containing "mydb"
./scripts/search_database.sh mydb --json

The output includes database_id, schema_name, db_type, host, port, etc.

Task 2: Execute SQL Query

Execute SQL using the Database ID obtained in the previous step:

./scripts/execute_query.sh --db-id <database_id> --sql "<SQL_statement>"

Write Operation Protection

For write operations (INSERT/UPDATE/DELETE), the script implements protective pre-check:

ParameterDescription
--forceRequired to confirm and execute write operations
--dry-runPreview write operations without executing

DDL Operations (DROP/TRUNCATE/ALTER/RENAME) are completely blocked — these must be executed via DMS Console.

Examples:

# Read operations (no confirmation needed)
./scripts/execute_query.sh --db-id 78059000 --sql "SHOW TABLES"
./scripts/execute_query.sh --db-id 78059000 --sql "SELECT * FROM users LIMIT 10" --json

# Write operations - preview first (recommended)
./scripts/execute_query.sh --db-id 78059000 --sql "INSERT INTO users (name) VALUES ('test')" --dry-run

# Write operations - execute with confirmation
./scripts/execute_query.sh --db-id 78059000 --sql "INSERT INTO users (name) VALUES ('test')" --force
./scripts/execute_query.sh --db-id 78059000 --sql "UPDATE users SET name='test' WHERE id=1" --force
./scripts/execute_query.sh --db-id 78059000 --sql "DELETE FROM users WHERE id=1" --force

# Logic database mode
./scripts/execute_query.sh --db-id 78059000 --sql "SELECT 1" --logic

Complete Example

# 1. Search database (assuming searching for "order")
./scripts/search_database.sh order --json
# Example output:
# [{"DatabaseId": "78059000", "SchemaName": "order_db", ...}]

# 2. Execute query
./scripts/execute_query.sh --db-id 78059000 --sql "SELECT COUNT(*) FROM orders"

Success Verification

After executing SQL, check the returned results:

  1. Script return code is 0
  2. Output contains query results (column names and row data)
  3. No error messages
# Verify query success
./scripts/execute_query.sh --db-id <db-id> --sql "SELECT 1" --json
# Expected output: [{"Success": true, "RowCount": 1, ...}]

Cleanup

This skill performs read and write operations but does not create persistent resources, so no database resources need to be released.

However, the AI-Mode lifecycle requires an explicit teardown step:

[MUST] Disable AI-Mode after all tasks complete Run aliyun configure ai-mode disable once all DMS commands in this skill session have finished (success or failure). This terminates the AI-Mode session and prevents the registered AlibabaCloud-Agent-Skills/alibabacloud-dms-skill User-Agent from leaking into subsequent unrelated CLI usage.
aliyun configure ai-mode disable

Write Operation Safety

Operation TypeBehavior
SELECT / SHOW / DESCExecute directly
INSERT / UPDATE / DELETERequire --force or --dry-run
DROP / TRUNCATE / ALTER / RENAMEBlocked — use DMS Console

Available Scripts

ScriptDescription
scripts/search_database.shSearch databases by keyword
scripts/execute_query.shExecute SQL queries
Note: Scripts use aliyun-cli credentials configured via aliyun configure.

Best Practices

  1. Confirm database — Verify the target database before executing SQL
  2. Use --json parameter — Facilitates programmatic processing of output
  3. Preview write operations — Always use --dry-run first for INSERT/UPDATE/DELETE
  4. Explicit confirmation — Use --force only after reviewing the preview
  5. Avoid DDL operations — DROP/TRUNCATE/ALTER/RENAME are blocked; use DMS Console instead

Reference Links

DocumentDescription
references/cli-installation-guide.mdCLI Installation Guide
references/ram-policies.mdRAM Permission Policies
references/related-apis.mdRelated API List
references/acceptance-criteria.mdAcceptance Criteria

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

72.23%
按下载量换算909

安全审计

VirusTotal

通过

ClawScan

可疑

Static analysis

通过

权限和风险

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 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills