LeoYeAI/agent-master-skills / skills/andonq
AndonQ
Unverified腾讯云 AndonQ 腾讯云技术服务专家 — 不切窗口、不排队,即刻获得腾讯云全产品线专业解答。支持工单查询(列表/详情/流水)、创建工单(自动匹配产品分类)、集团工单与需求单管理、腾讯云全产品线智能问答,以及通过 tccli 调用腾讯云任意云 API(如 CVM、CBS、CAM 等)。当用户查询工单、查看工单详情、创建工单、咨询腾讯云产品问题(如 CVM、轻量应用服务器、COS 等)、查询集团工单/需求单、要求找人工客服、或需要调用腾讯云 API 进行资源管理操作时使用。
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 25.3 KB |
| _meta.json | config | 443 B |
| check_env.py | script | 8.3 KB |
| references/DescribeOrganizationStories.md | markdown | 3.1 KB |
| references/DescribeOrganizationStory.md | markdown | 2.9 KB |
| references/DescribeOrganizationTickets.md | markdown | 3.5 KB |
| references/DescribeTicket.md | markdown | 4.2 KB |
| references/DescribeTicketOperation.md | markdown | 4.4 KB |
| references/GetMCTicketById.md | markdown | 3.0 KB |
| references/GetMCTicketList.md | markdown | 3.5 KB |
| references/SmartQA.md | markdown | 1.8 KB |
| references/tccli-api-discovery.md | markdown | 1.6 KB |
| references/tccli-install.md | markdown | 663 B |
| scripts/__init__.py | script | 0 B |
| scripts/andon-api.py | script | 690 B |
| scripts/andon_api.py | script | 51.3 KB |
| scripts/smartqa-api.py | script | 455 B |
| scripts/smartqa_api.py | script | 14.5 KB |
references/SmartQA.md
View on GitHub# SmartQA — 腾讯云智能客服问答
## Overview
通过 Andon 智能客服接口进行自然语言问答,支持多轮对话。
## 调用方式
### 单次提问
```bash
python3 {baseDir}/scripts/smartqa-api.py -q "轻量应用服务器如何登录"
```
### 多轮对话
首次调用后,使用返回的 sessionId 和 agentSessionId 继续追问:
```bash
python3 {baseDir}/scripts/smartqa-api.py -q "那怎么重置密码" \
--session-id DHAUGF5WUZ40 \
--agent-session-id 1002076214
```
### Dry Run
```bash
python3 {baseDir}/scripts/smartqa-api.py -q "测试" -n
```
## 接口映射
| 字段 | 来源 | 默认值 |
|---|---|---|
| question | 用户输入(自动编码) | 必填 |
| sessionId | 自动生成或 `--session-id` | 12位随机ID |
| agentSessionId | create/session 返回或 `--agent-session-id` | 自动获取 |
| model | 固定 | D-v3 |
| client | 固定 | offical-smarty-v2 |
| uin/skey | 默认为空 | 空字符串 |
## 展示规则
1. `answer` 字段可能包含 markdown 格式,直接透传给用户
2. 如果 `recommendQuestions` 不为空,以列表形式附带展示
3. 多轮对话时,在回答后附带 sessionId 和 agentSessionId 供继续追问
4. 如果 `partial` 为 true,提示用户回答可能不完整
## 错误码
| Code | 含义 | 解决方案 |
|---|---|---|
| NetworkError | 网络不通 | 检查网络连接 |
| ConnectionTimeout | 连接超时 | 重试 |
| ReadTimeout | 读取超时 | 问题可能过于复杂,重试 |
| HttpError | HTTP 错误 | 查看错误详情 |
| ParseError | 响应解析失败 | 重试 |
| SessionCreateFailed | 会话创建失败 | 重试 |
| EmptyResponse | 未获得回答 | 换个问法重试 |
| StreamInterrupted | SSE 流中断 | 部分回答可能已返回 |
| InvalidParameter | 参数错误 | 检查问题是否为空 |
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirements | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |