Aliyun Resource Ops logo

Aliyun Resource Ops

Community
yzstory
aliyun-resource-ops

阿里云资源运维管理工具。支持 ECS/RDS 等多产品的资源创建、删除、启动、停止、重启、释放等运维操作。支持与 optimizer 联动执行优化建议。所有操作都经过 OpsClaw 框架的权限控制和审计。触发词:启动实例、停止实例、重启实例、释放实例、创建 ECS、执行优化动作

Overview

Publisheryzstory
Repositorypomeloclaw
Skill namealiyun-resource-ops
Stars
59
Forks
4
Bundled files
2
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by yzstory on GitHub. Read the source before you install it.

Installation

Install the Aliyun Resource Ops AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/yzstory/pomeloclaw/tree/main/workspace/skills/finops_skills/aliyun-resource-ops
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/yzstory/pomeloclaw.git /tmp/pomeloclaw
mkdir -p .claude/skills
cp -r /tmp/pomeloclaw/workspace/skills/finops_skills/aliyun-resource-ops .claude/skills/aliyun-resource-ops
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Aliyun Resource Ops in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Aliyun Resource Ops on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Aliyun Resource Ops is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Aliyun Resource Ops - 云资源运维管理

多产品云资源的运维管理工具,提供资源的生命周期管理能力。

核心特性

1. 基础运维操作

  • ECS 云服务器:创建、删除、启动、停止、重启、批量操作
  • RDS 数据库:启动、停止、重启、释放

2. optimizer 联动执行

  • 从 optimizer 导入优化建议到 Action Store
  • 查询待执行的优化动作
  • 执行优化动作(释放/降配)
  • 跳过不需要的优化建议

何时使用此 Skill

当用户表达以下意图时,应该调用此 skill:

基础运维场景

  • 查询资源:"查看 ECS 实例"、"列出 RDS"、"有哪些服务器"
  • 启动资源:"启动实例"、"开机"、"启动服务器"
  • 停止资源:"停止实例"、"关机"、"停止服务器"
  • 重启资源:"重启实例"、"重启服务器"、"reboot"
  • 创建资源:"创建 ECS"、"新建实例"、"开一台服务器"
  • 删除/释放资源:"释放实例"、"删除 ECS"、"销毁服务器"

成本优化联动场景

  • 导入优化建议:"把 optimizer 的分析建议保存到 Action Store"
  • 查询待执行动作:"有哪些待执行的优化动作"、"列出可以优化的资源"
  • 执行优化动作:"执行这个优化建议"、"释放这台闲置机器"
  • 跳过优化建议:"跳过这条建议"、"这个资源需要保留"

注意:标签相关操作(打标签、查标签)请使用 aliyun-tag-foundation / aliyun-tag-automation skill。

功能列表

ECS 实例

操作工具函数风险等级说明
查询实例列表ops_ecs_list_instancesLOW列出 ECS 实例
查询实例详情ops_ecs_describe_instanceLOW获取实例详细信息
启动实例ops_ecs_start_instanceMEDIUM启动已停止的实例
停止实例ops_ecs_stop_instanceMEDIUM停止运行中的实例
重启实例ops_ecs_restart_instanceMEDIUM重启实例
创建实例ops_ecs_create_instanceHIGH创建新的 ECS 实例(产生费用)
释放实例ops_ecs_release_instanceCRITICAL释放按量付费实例(不可恢复)
批量启动ops_ecs_batch_start_instancesHIGH批量启动多个实例

RDS 实例

操作工具函数风险等级说明
查询实例列表ops_rds_list_instancesLOW列出 RDS 实例
启动实例ops_rds_start_instanceMEDIUM启动 RDS 实例
停止实例ops_rds_stop_instanceMEDIUM停止 RDS 实例
重启实例ops_rds_restart_instanceMEDIUM重启 RDS 实例
释放实例ops_rds_release_instanceCRITICAL释放按量付费实例(不可恢复)

optimizer 联动

操作工具函数风险等级说明
导入优化建议ops_import_optimizer_actionsLOW从 optimizer 结果导入可执行动作
查询待执行动作ops_list_pending_actionsLOW列出待执行的优化动作
执行优化动作ops_execute_actionMEDIUM执行单条优化动作(需确认)
跳过优化动作ops_skip_actionLOW标记动作为已跳过
获取统计信息ops_get_action_statsLOW获取 Action Store 统计

支持的资源类型

  • ecs:instance - ECS 云服务器
  • rds:instance - RDS 数据库
  • optimizer:action-store - 优化动作存储(联动用)

使用前提

  1. 已通过 copaw ops credential add 配置 AKSK 凭证
  2. 在 config.json 中启用 ops.enabled = true
  3. 凭证具有相应的 RAM 权限

区域参数

所有工具都支持 region_id 参数,默认为 cn-hangzhou。

常用区域 ID:

  • cn-hangzhou - 华东 1(杭州)
  • cn-shanghai - 华东 2(上海)
  • cn-beijing - 华北 2(北京)
  • cn-shenzhen - 华南 1(深圳)
  • cn-hongkong - 香港

安全说明

  • 所有操作都会被审计记录
  • 高风险操作(如释放实例)需要审批
  • 敏感信息(如 AccessKey)会被自动脱敏

典型使用场景

基础运维场景

场景 1:用户要求"查看 ECS 实例"
python
ops_ecs_list_instances(region_id="cn-hangzhou")
场景 2:用户要求"重启实例 i-xxx"
python
ops_ecs_restart_instance(instance_id="i-xxx", region_id="cn-hangzhou")
场景 3:用户要求"创建一台测试服务器"
python
ops_ecs_create_instance(
    region_id="cn-hangzhou",
    instance_name="test-server",
    instance_type="ecs.t5-lc1m2.small"
)

optimizer 联动场景

重要执行流程:当用户要求"执行优化动作"、"执行优化建议"、"释放/降配上面分析出的资源"时,必须按以下流程执行:

  1. 先调用 ops_list_pending_actions 从 Action Store 查询待执行动作
  2. 向用户展示待执行动作列表(包含 action_id、resource_id、策略、预计节省等)
  3. 用户确认后,使用查询到的 action_id 调用 ops_execute_action 执行

禁止:直接从上下文或历史报告中提取资源 ID 执行操作,必须从 JSON 文件查询。

场景 4:从 optimizer 导入优化建议
python
# 假设 optimizer_results 是 optimizer 分析返回的 JSON 字符串
ops_import_optimizer_actions(
    optimizer_results_json=optimizer_results,
    region_id="cn-hangzhou",
    analysis_id="report_20260321",
    supported_products=["ECS", "RDS"],
    replace_pending=False  # 不替换现有的 pending 动作
)
场景 5:查询待执行的优化动作
python
# 列出所有待执行动作
ops_list_pending_actions(limit=50)

# 过滤 ECS 的释放动作
ops_list_pending_actions(product="ECS", strategy="Release", min_saving=100)
场景 6:执行优化动作
python
# 干运行模式(只验证不执行)
ops_execute_action(action_id="act_xxx", confirm=True, dry_run=True)

# 实际执行(需要审批)
ops_execute_action(action_id="act_xxx", confirm=True, dry_run=False)
场景 7:跳过优化建议
python
# 标记为已跳过
ops_skip_action(action_id="act_xxx", reason="业务高峰期需要保留")

Action Store 数据流转

optimizer 分析 → 提取可执行动作 → Action Store → resource-ops 执行
     ↓                                    ↑
  生成报告                          查询/执行/跳过

Action Store 存储路径: ~/.copaw/data/optimization_actions.json

动作有效期: 默认 7 天(过期后自动标记为 expired)

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Aliyun Resource Ops AI skill do?

阿里云资源运维管理工具。支持 ECS/RDS 等多产品的资源创建、删除、启动、停止、重启、释放等运维操作。支持与 optimizer 联动执行优化建议。所有操作都经过 OpsClaw 框架的权限控制和审计。触发词:启动实例、停止实例、重启实例、释放实例、创建 ECS、执行优化动作

Why use Aliyun Resource Ops on TypingMind?

Because you install it once and use it with any model. Aliyun Resource Ops is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Aliyun Resource Ops in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/yzstory/pomeloclaw/tree/main/workspace/skills/finops_skills/aliyun-resource-ops. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Aliyun Resource Ops?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Aliyun Resource Ops?

As many as you like. As long as a model supports skills, you can use Aliyun Resource Ops with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Aliyun Resource Ops AI skill free?

It is published on GitHub by yzstory. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇