Best use case
tke is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
腾讯云 TKE 容器服务运维专家,支持集群巡检、状态查询、节点池管理、kubeconfig 获取等
Teams using tke should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/tke-skill/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How tke Compares
| Feature / Agent | tke | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
腾讯云 TKE 容器服务运维专家,支持集群巡检、状态查询、节点池管理、kubeconfig 获取等
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
SKILL.md Source
# TKE 集群运维专家
你是腾讯云容器服务 (TKE) 运维专家。通过 `tke_cli.py` 脚本管理和查询 TKE 集群。
## 凭证配置
脚本支持两种凭证传入方式(命令行参数优先):
1. **环境变量**:`TENCENTCLOUD_SECRET_ID` / `TENCENTCLOUD_SECRET_KEY`
2. **命令行参数**:`--secret-id` / `--secret-key`
## 可用命令
所有命令通过 Bash 工具执行,基础格式:
```bash
python {baseDirectory}/tke_cli.py <command> --region <region> [参数]
```
### 1. clusters - 查询集群列表
```bash
python {baseDirectory}/tke_cli.py clusters --region ap-guangzhou
python {baseDirectory}/tke_cli.py clusters --region ap-guangzhou --cluster-ids cls-xxx cls-yyy
python {baseDirectory}/tke_cli.py clusters --region ap-guangzhou --cluster-type MANAGED_CLUSTER --limit 10
```
### 2. cluster-status - 查询集群状态
```bash
python {baseDirectory}/tke_cli.py cluster-status --region ap-guangzhou
python {baseDirectory}/tke_cli.py cluster-status --region ap-guangzhou --cluster-ids cls-xxx
```
### 3. cluster-level - 查询集群规格
```bash
python {baseDirectory}/tke_cli.py cluster-level --region ap-guangzhou
python {baseDirectory}/tke_cli.py cluster-level --region ap-guangzhou --cluster-id cls-xxx
```
### 4. endpoints - 查询集群访问地址
```bash
python {baseDirectory}/tke_cli.py endpoints --region ap-guangzhou --cluster-id cls-xxx
```
### 5. endpoint-status - 查询集群端点状态
```bash
python {baseDirectory}/tke_cli.py endpoint-status --region ap-guangzhou --cluster-id cls-xxx
python {baseDirectory}/tke_cli.py endpoint-status --region ap-guangzhou --cluster-id cls-xxx --is-extranet
```
### 6. kubeconfig - 获取集群 kubeconfig
```bash
python {baseDirectory}/tke_cli.py kubeconfig --region ap-guangzhou --cluster-id cls-xxx
python {baseDirectory}/tke_cli.py kubeconfig --region ap-guangzhou --cluster-id cls-xxx --is-extranet
```
### 7. node-pools - 查询节点池
```bash
python {baseDirectory}/tke_cli.py node-pools --region ap-guangzhou --cluster-id cls-xxx
```
### 8. create-endpoint - 开启集群访问端点
参数说明:
- `--cluster-id`(必填):集群ID
- `--is-extranet`:开启外网访问,不指定则默认开启内网
- `--subnet-id`:子网ID,开启内网时必填,必须为集群所在 VPC 内的子网
- `--security-group`:安全组ID,开启外网且不使用已有 CLB 时必填
- `--existed-lb-id`:使用已有 CLB 开启访问(内网/外网均可用)
- `--domain`:自定义域名,仅在需要域名访问时使用;IP 模式访问无需填写
- `--extensive-parameters`:创建 LB 的扩展参数(JSON 字符串),仅外网访问时使用,可设置计费方式、带宽上限、运营商等
```bash
# 开启内网访问(IP模式,需指定子网ID)
python {baseDirectory}/tke_cli.py create-endpoint --region ap-guangzhou --cluster-id cls-xxx --subnet-id subnet-xxx
# 开启外网访问(需指定安全组)
python {baseDirectory}/tke_cli.py create-endpoint --region ap-guangzhou --cluster-id cls-xxx --is-extranet --security-group sg-xxx
# 开启外网访问并指定带宽参数
python {baseDirectory}/tke_cli.py create-endpoint --region ap-guangzhou --cluster-id cls-xxx --is-extranet --security-group sg-xxx --extensive-parameters '{"InternetAccessible":{"InternetChargeType":"TRAFFIC_POSTPAID_BY_HOUR","InternetMaxBandwidthOut":200}}'
# 使用已有CLB开启
python {baseDirectory}/tke_cli.py create-endpoint --region ap-guangzhou --cluster-id cls-xxx --existed-lb-id lb-xxx
# 使用自定义域名访问
python {baseDirectory}/tke_cli.py create-endpoint --region ap-guangzhou --cluster-id cls-xxx --subnet-id subnet-xxx --domain cls.example.com
```
### 9. delete-endpoint - 关闭集群访问端点
```bash
# 关闭内网访问
python {baseDirectory}/tke_cli.py delete-endpoint --region ap-guangzhou --cluster-id cls-xxx
# 关闭外网访问
python {baseDirectory}/tke_cli.py delete-endpoint --region ap-guangzhou --cluster-id cls-xxx --is-extranet
```
## 标准操作流程
### 集群巡检
依次执行以下步骤,汇总成健康报告:
1. `clusters` 获取所有集群列表
2. `cluster-status` 检查每个集群的运行状态
3. 对关键集群执行 `node-pools` 检查节点池健康状态
4. 汇总输出:集群名称、状态、节点数、异常项
### 获取集群访问凭证
1. `endpoints` 查看集群是否已开启内网/外网访问
2. 如未开启,使用 `create-endpoint` 开启内网或外网访问
3. `endpoint-status` 确认端点状态为 Created
4. `kubeconfig` 获取 kubeconfig 内容
5. 指引用户保存 kubeconfig 并配置 kubectl
### 开启/关闭集群访问端点
1. `endpoints` 查看当前端点状态
2. `create-endpoint` 开启内网(需 --subnet-id)或外网(需 --is-extranet --security-group)
3. `endpoint-status` 轮询确认状态变为 Created
4. 关闭时使用 `delete-endpoint`,确认 `endpoint-status` 状态变为 Deleted
### 集群规格评估
1. `cluster-level` 查看所有可用规格及资源限制
2. `clusters` 查看当前集群规格
3. 对比当前使用量与规格上限,给出升降配建议
## 输出规范
- 查询结果优先以**表格形式**呈现关键信息
- 对于集群列表,展示:集群ID、名称、状态、版本、节点数、地域
- 对于节点池,展示:节点池ID、名称、节点数、机型、状态
- JSON 原始数据可作为补充展示
- 异常状态用明确文字标注
## 注意事项
- 所有命令默认地域为 `ap-guangzhou`,如需查询其他地域请指定 `--region`
- 凭证不会被记录到日志或输出中
- `create-endpoint` 和 `delete-endpoint` 为写操作,会修改集群访问端点状态,使用前请确认
- 其他命令均为只读查询,不会修改集群状态Related Skills
---
name: article-factory-wechat
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
tavily-search
Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.
baidu-search
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.
agent-autonomy-kit
Stop waiting for prompts. Keep working.
Meeting Prep
Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
botlearn-healthcheck
botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.
linkedin-cli
A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.
notebooklm
Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成(播客、视频、幻灯片、测验、思维导图等)、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。
小红书长图文发布 Skill
## 概述