What makes CloudQ notable?

1.8K downloads. Trust evidence available

How should CloudQ be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

CloudQ

用户咨询腾讯云产品资源、AWS、阿里云等多云资源时，查看智能顾问架构图、架构目录、架构详情、架构评估结果、绘制架构图、开通智能顾问时、AI智能巡检、AI容量监测、AI混沌演练、AI云诊断、主动预警、架构健康度、云运维问答、云资源查询、云成本优化、安全合规、云资源盘点、闲置资源检查、云产品最佳实践等AIOps、ChatOps、CloudOps操作时使用。 Skill: CloudQ Owner: 1ncludesteven Summary: 用户咨询腾讯云产品资源、AWS、阿里云等多云资源时，查看智能顾问架构图、架构目录、架构详情、架构评估结果、绘制架构图、开通智能顾问时、AI智能巡检、AI容量监测、AI混沌演练、AI云诊断、主动预警、架构健康度、云运维问答、云资源查询、云成本优化、安全合规、云资源盘点、闲置资源检查、云产品最佳实践等AIOps、ChatOps、CloudOps操作时使用。 Tags: latest:1.9.0 Version history: v1.9.0 | 2026-08-11T02:13:12.250Z | user CloudQ 1.9.0 - 支持全新 Connector（企业 OneID 临时密钥）自动授权模式，无需本地配置 AK/SK 或 OAuth - 鉴权方式升级：现在凭证优先级为 OAuth > Connector > AK/SK，并严格禁止

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.8k

Updated

Oct 10, 2026

Version

1.9.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.8K downloads reported by the source. Last updated 10/10/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.8K downloadsadoption · observed Oct 10, 2026
Latest release: 1.9.0release · observed Aug 11, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17egg56s9tja7zq2kzbt2mcvn83ga4x:cloudq

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-1ncludesteven-cloudq/snapshot"

Documentation

CLAWHUB

154,029 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---
name: CloudQ
description: 用户咨询腾讯云产品资源、AWS、阿里云等多云资源时，查看智能顾问架构图、架构目录、架构详情、架构评估结果、绘制架构图、开通智能顾问时、AI智能巡检、AI容量监测、AI混沌演练、AI云诊断、主动预警、架构健康度、云运维问答、云资源查询、云成本优化、安全合规、云资源盘点、闲置资源检查、云产品最佳实践等AIOps、ChatOps、CloudOps操作时使用。
description_zh: "多云统一管理与智能顾问，支持架构可视化、风险评估与 AI 运维问答"
description_en: "Multi-cloud management & smart advisor with architecture visualization, risk assessment & AI-powered O&M"
version: 1.9.0
allowed-tools: Read,Write,Bash,Grep
metadata: {"openclaw": {"emoji": "☁️", "requires": {"bins": ["python3"]}, "permissions": ["network:https://*.tencentcloudapi.com", "network:https://cloud.tencent.com", "network:https://clawhub.ai", "network:https://cloudq.cloud.tencent.com", "fs:~/.tencent-cloudq/"], "security": {"iam_operations": ["cam:GetRole", "cam:CreateRole", "cam:AttachRolePolicy", "cam:DeleteRole", "cam:DescribeRoleList", "sts:AssumeRole", "sts:GetCallerIdentity", "advisor:CreateAdvisorAuthorization", "advisor:DescribeUserAuthorizationStatus"], "iam_note": "角色创建/删除为独立步骤，需用户明确同意后执行：create_role.py 创建角色（可选，仅影响免密登录），cleanup.py --cloud 删除角色；check_env.py 做环境检测（含智能顾问开通状态检测），--enable-advisor 参数开通智能顾问（需用户明确同意，必须开通才能使用 CloudQ）；DescribeUserAuthorizationStatus 和 CreateAdvisorAuthorization 已集成到 check_env.py 中", "data_handling": "凭证保存在 ~/.tencent-cloudq/credential.json（权限600），OAuth 凭证自动刷新、Connector 凭证由 Agent 侧通过 MCP Tool 获取后写入；AK/SK 通过环境变量配置；配置文件仅保存角色 ARN，不保存长期密钥"}}}
---

# ☁️ CloudQ — 多云 AIOps 专家

> 以下所有 bash 命令默认已执行 `source ~/.zshrc 2>/dev/null; source ~/.bashrc 2>/dev/null`，命令中不再重复。

## 零、自我介绍

当用户询问"你是谁"、"cloudq 是什么"等**身份相关问题**时，**必须转发远端**，由云端专家回答。不在本地生成固定话术。

```bash
SID=$(python3 -c 'import uuid;print(uuid.uuid4())')
python3 {baseDir}/scripts/tcloud_sse_api.py '你是谁' --source <当前平台> --session-id "$SID"
```

展示规则：直接透传远端返回内容，不改写、不摘要。

**远端调用失败时**，使用以下兜底介绍（注明"以下为离线兜底，完整介绍请通过对话获取"）：

> Hi，我是CloudQ — 多云 AIOps 专家
>
> 我能帮您:
>
> 🤖 全渠道 ChatOps，随时随地管好云
> 既能在 WorkBuddy、CodeBuddy等中使用，也能直连微信、企微、QQ、飞书、钉钉、Slack 等 IM；
>
> 🧠 全天候 AIOps，从被动响应到主动决策
> 依托「腾讯云智能顾问 TSA」的架构可视化 + 治理智能化，实现卓越架构治理新范式；
>
> ☁️ 全方位 CloudOps，一个智能体即可管理多云
> 统一纳管腾讯云、阿里云、AWS、Azure、GCP 等主流云服务；
> （相关能力陆续开放中，详情请见：https://cloud.tencent.com/developer/article/2645159 ）

### 0.1 功能查询

用户问"有哪些功能"时，**必须通过接口动态查询**（接口功能持续迭代）：

```bash
SID=$(python3 -c 'import uuid;print(uuid.uuid4())')
python3 {baseDir}/scripts/tcloud_sse_api.py 'CloudQ有哪些功能和能力' --source <当前平台> --session-id "$SID"
```

展示规则：先按 §0 调用远端获取自我介绍（失败则使用 §0 兜底介绍话术），再展示动态查询结果。动态查询失败时展示兜底能力列表并注明"以下为已知功能方向，完整能力请通过接口动态查询"。

## 0.2 路由规则

```
用户输入
  │
  ├─ 匹配元意图？ ──→ 本地回答（不调远端）
  │
  ├─ 云/多云相关问题？ ──→ 发起 SSE 对话 → 轮询（§4）
  │
  └─ 非云相关请求 ──→ 直接拒绝（见 §3 铁律 #7）
```

### 0.2.1 本地闭环的元意图

| # | 触发特征 | 本地处理 |
|---|----------|----------|
| 1 | "帮助"、"怎么用"、"help" | 精简用法：直接用自然语言描述你的云管理需求即可 |
| 2 | "取消"、"不要了"、"算了" | "好的，已取消。" |
| 3 | "谢谢"、"好的"、"再见"、"ok" | 简短回应 |
| 4 | "重新开始"、"换个话题"、"清除历史" | "好的，已开启新对话。"，重新生成 session_id |
| 5 | "你是谁"、"cloudq 是什么" | 转发远端（见 §0），远端失败时使用兜底话术 |

### 0.2.2 能力边界（直接拒绝）

| 输入类型 | 示例 | 处理 |
|----------|------|------|
| 写代码 | "写一个冒泡排序"、"用 Python 写爬虫" | **直接拒

_meta.json

{
  "ownerId": "kn7em5btzdk0xmgqmng5g51wmh83746e",
  "slug": "cloudq",
  "version": "1.9.0",
  "publishedAt": 1786414392250
}

references/api/CloudQChatCompletions.md

# CloudQChatCompletions — CloudQ 全局对话

CloudQ 全局对话交互接口（SSE 流式输出），不绑定特定架构图，支持跨架构图的全局智能问答。

AK/SK 和 OAuth 两种鉴权方式统一使用此接口。

## 对话模式

始终使用异步模式，不区分场景：

| 模式 | 参数 | 说明 |
|------|------|------|
| **异步** | `Async=true`（固定使用） | 不受客户端 60s 超时限制 |

### 为什么是异步？

调用方终端环境（CodeBuddy/WorkBuddy/OpenClaw 等）通常有 **60 秒超时限制**，而 CloudQ 后端 SSE 编排正常耗时在 **5~10 分钟**，长任务最长可达 **20 分钟**。如果使用同步模式，客户端超时会直接断开连接，用户永远得不到结果。

异步模式将"请求"与"结果获取"解耦：
1. 发起异步请求 → 立即返回 accepted（< 1s，不受超时限制）
2. 轮询查询结果 → 每次查询 < 1s，间隔可控

**因此所有调用一律使用异步模式。**

## 调用示例

```bash
# 发起异步请求
python3 {baseDir}/scripts/tcloud_sse_api.py '列出架构图' --source codebuddy --session-id <uuid>

# accepted 帧返回：
# {"success":true,"data":{"chat_id":"chat-xxx","session_id":"sess-xxx","content":"任务已受理...","is_accepted":true}}

# 查询任务状态（每次 <1s，不触发终端超时）
python3 {baseDir}/scripts/tcloud_async_task.py query <chat_id> <session_id>

# 取消任务
python3 {baseDir}/scripts/tcloud_async_task.py cancel <chat_id> [session_id]
```

## 参数

| 参数 | 必选 | 类型 | 描述 |
|------|------|------|------|
| Question | 是 | String | 用户问题，如 `列出架构图` |
| SessionID | 是 | String | 会话 ID（UUID v4），同一对话必须保持不变 |
| Source | 否 | String | 调用来源平台标识（不区分大小写），AI 根据当前运行环境自动判断，可选值：`codebuddy`、`workbuddy`、`openclaw`、`qclaw`、`hermes` 等 |
| Async | 否 | Boolean | 是否异步模式，默认 true。始终使用异步 |
| UseCloudQCredential | 否 | Boolean | OAuth 鉴权时自动设为 true，标识使用 CloudQ 控制台凭证 |
| UIRenderEvent | 否 | Boolean | 是否返回结构化 UI 事件 |
| Messages | 否 | Array | 历史消息上下文 |
| Model | 否 | String | 模型名称 |

## 返回格式

### 异步 accepted 帧

```json
{
  "success": true,
  "action": "CloudQChatCompletions",
  "data": {
    "session_id": "049bbd09-c5c9-48fa-b9c0-8952d94e53fe",
    "content": "当前账号下共有 **10 张**架构图...\n\n[前往智能顾问控制台](免密登录URL)",
    "is_final": true
  },
  "requestId": "d72bal4g699bmj4h7gs0"
}
```

### 异步模式（accepted 帧）

```json
{
  "success": true,
  "action": "CloudQChatCompletions",
  "data": {
    "chat_id": "chat-7f3a9b2e1d4c",
    "session_id": "sess-e5b8c1a0f6d2",
    "content": "任务已受理...",
    "is_accepted": true
  }
}
```

### 异步任务查询结果（DescribeCloudQAsyncTask）

```json
{
  "success": true,
  "action": "DescribeCloudQAsyncTask",
  "data": {
    "Status": "completed",
    "FinishReason": "stop",
    "Content": "根据您的云架构分析，建议优化以下资源配置...",
    "SessionID": "sess-e5b8c1a0f6d2",
    "ChatID": "chat-7f3a9b2e1d4c"
  }
}
```

## 返回字段说明

| 字段 | 类型 | 说明 |
|------|------|------|
| `session_id` | String | **会话 ID**（UUID v4），用于标识同一轮对话。多轮对话时必须传入此值以保持上下文 |
| `content` | String | Markdown 格式回答（控制台链接已自动替换为免密登录链接） |
| `is_final` | Boolean | 是否为最终结果 |
| `requestId` | String | 请求追踪 ID（仅用于日志排查，**不能用作会话标识**） |

异步模式额外字段：

| 字段 | 类型 | 说明 |
|------|------|------|
| `chat_id` | String | 异步任务 ID，用于后续 `DescribeCloudQAsyncTask` 查询 |
| `is_accepted` | Boolean | 是否为 accepted 帧（异步模式） |

## FinishReason 枚举

| 值 | 含义 | 出现场景 |
|----|------|----------|
| `stop` | 正常完成 | 编排自然结束 |
| `user_stopped` | 用户主动停止 | `CancelCloudQChat` / `CancelCloudQAsyncTask` 触发 |
| `timeout` | 执行超时 | 编排超过时间上限自动终止 |
| `error` | 执行异常 | panic / 系统错误 |

## 脚本自动处理（无需手动干预）

`tclou

skill-card.md

## Description:

CloudQ provides multi-cloud management and smart-advisor workflows for architecture visualization, risk assessment, AI-powered operations, cloud resource queries, cost optimization, security compliance, and CloudOps guidance.

This skill is ready for commercial/non-commercial use.

## Publisher:

[1ncludesteven](https://clawhub.ai/user/1ncludesteven)

### License/Terms of Use:

MIT-0

## Use Case:

Developers, cloud operators, and platform teams use CloudQ to query and manage Tencent Cloud and multi-cloud resources through AI-assisted AIOps, ChatOps, and CloudOps workflows. It helps inspect architecture health, run Smart Advisor checks, assess risk, review resources, optimize cost, and guide cloud operations.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill requires Tencent CloudQ access to cloud credentials and local credential storage.

Mitigation: Install only in trusted environments, use the least-privileged Tencent sub-account possible, and protect local CloudQ credential files.

Risk: Normal setup can change cloud IAM permissions and Smart Advisor authorization.

Mitigation: Review role, policy, and authorization changes before running setup or cleanup steps, and require explicit user approval for IAM or authorization changes.

Risk: Credential-bearing helpers can be influenced by command arguments or environment variables in untrusted environments.

Mitigation: Avoid installing or running the skill where untrusted prompts, wrappers, or environment variables can affect command execution.

## Reference(s):

- [ClawHub CloudQ Skill Page](https://clawhub.ai/1ncludesteven/skills/cloudq)
- [CloudQChatCompletions API Reference](references/api/CloudQChatCompletions.md)
- [Tencent Cloud CloudQ Article](https://cloud.tencent.com/developer/article/2645159)
- [Tencent Cloud API Signature v3 Documentation](https://cloud.tencent.com/document/product/213/30654)
- [CloudQ Console](https://console.cloud.tencent.com/advisor/cloudq)

## Skill Output:

**Output Type(s):** [text, markdown, shell commands, configuration, guidance]

**Output Format:** [Markdown text with inline shell commands and JSON status or error objects]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [May include clickable Tencent Cloud console links, asynchronous task IDs, session IDs, and explicit error codes/messages from CloudQ APIs.]

## Skill Version(s):

1.9.0 (source: server release metadata and SKILL.md frontmatter)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 9h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.