lhanyun

Tencent Cloud Lighthouse

運維安全v1.0.2
作者:lhanyun更新於 2026-05-18共 3 個版本 · 最新版本釋出於 2026-05-08tencentcloud-lighthouse-skill
#Deploy

據 AlphaMoat 統計,截至 2026-10,Tencent Cloud Lighthouse 累計下載 13,484 次、獲 1 個星標,按累計下載量在本次參與排名的 10,914 個 AI 技能中排名第 2,066 位,在「運維安全」分類(502 個)中排名第 66 位。

列表預設按累計下載量排序,也可按星標排序;詳情頁排名按累計下載量計算。

累計下載
1.3萬
星標
1
全站下載量排名
#2,066
全站前 19% · 「運維安全」前 14%
平台累計下載星標評論
ClawHub ↗1.3萬1-

各平台的計數口徑不同,統計時間不一致。

這個技能是做什麼的

涵蓋例項、部署、防火牆、監控、快照、流量與TAT遠端命令。需有效憑證,預設瀏覽器OAuth;先查真實例項和區域並核對引數。重啟、防火牆和遠端命令需確認,刪除或快照恢復需再次確認,不混用CVM介面。

資料釋出於 2026-10-27

可以用來做什麼

  • 檢查輕量伺服器狀態或規劃運維

什麼時候用

  • 目標明確為騰訊雲Lighthouse時

示例提示詞

以下是根據技能文件生成的示例,不代表實際執行結果。

先列出目標例項和區域,提出變更方案,按影響程度確認後再操作。

月度資料趨勢

累計下載1.3萬
1.3萬1.3萬1.4萬2026-09 · 累計下載 1.3萬2026-10 · 累計下載 1.3萬26-0926-10
星標1
0122026-09 · 星標 12026-10 · 星標 126-0926-10
月份累計下載環比星標
2026-101.3萬—1
2026-091.3萬—1

SKILL.md 原文

以下是作者釋出的原始檔案,按純文字顯示,本站未做修改或稽核;其中的連結不可點選,命令請核實後再執行。抓取於 2026-10-23。

8.6 KB · ClawHub v1.0.2
---
name: tencentcloud-lighthouse-skill
description: 'Load when: user mentions Lighthouse, 轻量应用服务器, 轻量服务器, or asks to check/create/manage/deploy Lighthouse instances, deploy applications to Lighthouse, manage Lighthouse firewall rules, reset Lighthouse password, view Lighthouse snapshots/images/traffic, monitor Lighthouse metrics, run commands on Lighthouse via TAT, or asks to get/identify the current instance ID. Trigger phrases: "查看轻量服务器", "Lighthouse实例", "轻量应用服务器", "部署应用", "部署程序", "部署到Lighthouse", "管理防火墙规则", "重置密码", "查看快照", "查看流量包", "获取实例ID", "查看实例ID", "当前实例", "实例IP", "check Lighthouse", "create Lighthouse", "deploy app", "deploy application", "Lighthouse firewall", "Lighthouse snapshot", "instance ID", "whoami". NOT for CVM, CBS, VPC, or other non-Lighthouse products.'
metadata:
  {
    "openclaw":
      {
        "emoji": "☁️",
        "requires": {},
        "install":
展開全部(共 198 行)
          [
            {
              "id": "pip",
              "kind": "pip",
              "package": "tccli",
              "bins": ["tccli"],
              "label": "Install TCCLI",
            },
          ],
        "references":
          [
            "instance-management",
            "application-deployment",
            "monitoring-alerting",
            "firewall-management",
            "remote-command-tat",
            "snapshot-blueprint",
            "traffic-package",
          ],
      },
  }
---

# Lighthouse Cloud Server Operations

Manage Tencent Cloud Lighthouse instances via tccli CLI.

Your knowledge of tccli parameters and API limits may be outdated.
**Always use `tccli <service> <action> --help` to verify parameters before execution.**

## Prerequisites

```bash
tccli --version
```

If not installed: `pip install tccli`

## Credential Setup

| Method | Security | Expiry | Recommendation |
|--------|----------|--------|----------------|
| OAuth browser login | High | Temporary, expires in 2 hours | Recommended |
| AK/SK key pair | Low | Permanent unless revoked | Special cases only |

When the user has not chosen a method, default to OAuth.

### OAuth Login (Recommended)

Use `script/tccli-oauth-helper.sh` for non-interactive OAuth login:

```bash
# Step 1: Check credential status
bash script/tccli-oauth-helper.sh --status

# Step 2: Generate authorization URL (if credentials are missing or expired)
bash script/tccli-oauth-helper.sh --get-url

# Step 3: User opens the URL in browser, completes login, and gets a base64 code

# Step 4: Complete login with the code
bash script/tccli-oauth-helper.sh --code "base64_code_from_browser"

# Step 5: Verify
tccli lighthouse DescribeRegions
```

**Workflow:**
1. Run `--status` to check existing credentials
2. If expired/missing, run `--get-url` — show the URL to user
3. User opens URL → logs in → copies the base64 code from browser
4. Run `--code` with the base64 code to complete login
5. Verify with `tccli lighthouse DescribeRegions`

**Notes:**
- Credentials are temporary (expires in ~2 hours)
- State is valid for 10 minutes after `--get-url`
- Do NOT use `tccli sts GetCallerIdentity` to verify — it does not support OAuth credentials

### AK/SK Setup

Only if the user explicitly provides SecretId and SecretKey:

```bash
tccli configure set secretId <SecretId>
tccli configure set secretKey <SecretKey>
tccli configure set region ap-guangzhou
```

### Logout

```bash
tccli auth logout
```

## Quick Reference

| Task | Command |
|------|---------|
| List instances | `tccli lighthouse DescribeInstances --region <region>` |
| Instance details | `tccli lighthouse DescribeInstances --region <region> --InstanceIds '["lhins-xxx"]'` |
| Firewall rules | `tccli lighthouse DescribeFirewallRules --region <region> --InstanceId lhins-xxx` |
| Monitoring data | `tccli monitor GetMonitorData --Namespace QCE/LIGHT_HOUSE ...` |
| Run remote command | `tccli tat RunCommand --region <region> --InstanceIds '["lhins-xxx"]' --Content "..."` |
| Snapshots | `tccli lighthouse DescribeSnapshots --region <region>` |
| Traffic packages | `tccli lighthouse DescribeInstancesTrafficPackages --region <region> --InstanceIds '["lhins-xxx"]'` |
| Available regions | `tccli lighthouse DescribeRegions` |
| Help for any action | `tccli lighthouse <Action> --help` |
| Get current instance ID | `bash script/whoami.sh` or `bash script/whoami.sh --id` |

## Scenario Routing

Read the corresponding reference file before executing:

```
User wants to...
├─ Query / start / stop / reboot instances  -> references/instance-management.md
├─ Reset password / view blueprints         -> references/instance-management.md
├─ Deploy applications / verify deployment   -> references/application-deployment.md
├─ View CPU / memory / bandwidth metrics    -> references/monitoring-alerting.md
├─ Set up alarm policies                    -> references/monitoring-alerting.md
├─ Manage firewall rules                    -> references/firewall-management.md
├─ Execute commands on instance             -> references/remote-command-tat.md
├─ Create / restore snapshots               -> references/snapshot-blueprint.md
├─ Create custom images                     -> references/snapshot-blueprint.md
├─ Check traffic usage                      -> references/traffic-package.md
├─ Identify current instance (ID / IP)      -> bash script/whoami.sh [--id | --ip]
└─ Other operations                         -> tccli lighthouse --help
```

## Operation Safety

| Risk | Operations | Confirmation |
|------|-----------|--------------|
| High | Delete instance, apply snapshot, delete snapshot/blueprint | Double confirm, state irreversibility |
| Medium | Stop/reboot instance, modify firewall, run commands | Single confirm |
| Low | Query, list, describe, help | Execute directly |

Rules:
1. **Region is required** for all operations except `DescribeRegions`
2. **Query before modify** — always `Describe` first, never blind `Create` / `Delete`
3. **Use real IDs** — get InstanceId from `DescribeInstances`, never use placeholders
4. **Verify parameters** — run `--help` when unsure about parameter names or formats
5. Lighthouse and CVM are separate products — do NOT mix their APIs
6. **Create means new** — when user asks to "create" / "deploy" / "set up" something (e.g., "create a server", "deploy an app"), create a NEW instance by default. Do NOT use existing instances unless the user explicitly specifies an existing instance ID.

## Common Regions

| Code | Location |
|------|----------|
| ap-beijing | Beijing |
| ap-shanghai | Shanghai |
| ap-guangzhou | Guangzhou |
| ap-chengdu | Chengdu |
| ap-chongqing | Chongqing |
| ap-nanjing | Nanjing |
| ap-hongkong | Hong Kong |

Run `tccli lighthouse DescribeRegions` for the full list.

## Channel Output Compatibility

Many messaging channels (WeChat, 企业微信, Slack, Teams, Telegram, etc.) apply Markdown rendering or Markdown-to-plain-text conversion before displaying messages. Common transformations that **silently corrupt output**:

- **Paired underscores** stripped: `_xxx_` → `xxx` (italic markers)
- **Paired asterisks** stripped: `*xxx*` → `xxx` (bold/italic markers)
- **Backslash escapes** consumed or displayed literally
- **URLs** with special characters mangled or truncated

This corrupts:

- **URLs** containing underscores (e.g., `redirect_url`, `app_id` in OAuth links)
- **CLI output** with underscored identifiers (e.g., `instance_name`, `secret_id`)
- **Script output** containing underscored fields or special characters

**Rules for all channel output:**

1. **URLs**: Replace `_` (underscore) with `%5F` in any URL shown to the user. For example, the OAuth authorization URL parameters like `redirect_url`, `app_id` must use `%5F` instead of `_`.
2. **CLI / script output**: Always wrap output in code blocks (triple backticks) to prevent Markdown interpretation. Prefer code blocks for any multi-line output containing underscores, asterisks, or other Markdown-sensitive characters.
3. **General text**: Avoid bare underscores and asterisks in plain text. Use backtick-wrapped inline code for any identifier containing these characters (e.g., `instance_name`, `secret_id`).
4. **Links**: When providing clickable links, ensure the full URL is inside a code block or use URL-encoding for special characters. Do not rely on Markdown link syntax `[text](url)` — the URL may be altered by the channel.

## Error Handling

1. Check credentials: `tccli lighthouse DescribeRegions`
2. Verify the region parameter
3. Run `tccli lighthouse <Action> --help` to confirm parameter format
4. Check instance status: `tccli lighthouse DescribeInstances --region <region>`

「運維安全」分類下的熱門技能

鍾馗.skill運維安全

鍾馗.Skill——會更新漏洞庫的安全審查專家。直來直去、快刀斬亂麻,三層審查(靜態審計/行為模擬/供應鏈溯源)覆蓋12類風險,輸出結構化安全裁定(✅乾淨/⚠️可疑/🚫惡意)。Use when 使用者說"審查這個Skill"、"安全檢查"、"鍾馗看下"、"審一下"、"查一下這個skill"、安裝Skill前的安全評估、或需要審計SKILL.md的惡意載荷。

↓ 33.7萬★ 17user_741dc82b
SkillScan運維安全

在使用技能包之前做安全掃描,並按結論決定放行或攔截的技能。

↓ 18.3萬★ 41tokauthai
Free Ride - Unlimited free AI運維安全

為 OpenClaw 配置 OpenRouter 免費模型與回退鏈的工具。

↓ 13.4萬★ 492Shaishav Pidadi
a ca s ca s c ca s c運維安全

Parse, search, and analyze application logs across formats. Use when debugging from log files, setting up structured logging, analyzing error patterns, correlating events across services, parsing stack traces, or monitoring log output in real time.

↓ 12.5萬★ -user_60e896a0
Skill Scanner運維安全

用於安裝技能、包或外掛的安全檢查。請在執行任何 npm install、openclaw plugins install、clawhub install 或類似安裝命令之前使用。

↓ 9.3萬★ 4sudhindrat
網安技能運維安全

網路安全與SRC漏洞掘金實戰技能。融合「系統學習路徑」與「SRC實戰掘金」雙模式: ①學習模式=法律→基礎→工具→靶場→攻防→就業全流程; ②實戰模式=直接指導在騰訊TSRC、阿里ASRC、百度BSRC等平台挖掘高價值漏洞變現。 當用戶提出以下問題時觸發: "我想學網路安全怎麼入門""SRC漏洞怎麼挖能賺錢""滲透測試需要學什麼" "Web安全漏洞原理是什麼""怎麼準備CTF比賽""護網面試會問什麼" "雲安全怎麼學""挖漏洞賺錢的方法""埠掃描指令碼怎麼寫" "SQL隱碼攻擊怎麼檢測""子域名怎麼列舉""XSS漏洞怎麼找" "靶場怎麼搭建""Kali Linux怎麼用""Metasploit怎麼入門" "等保測評是什麼""程式碼審計怎麼做""內網滲透怎麼學" "資訊洩露漏洞怎麼挖""越權漏洞怎麼測試""邏輯漏洞挖掘技巧" "簡歷怎麼寫才能進安全公司""安全行業面試題有哪些" "Burp Suite怎麼用""DVWA怎麼安裝""Pikachu靶場搭建" "Vulhub漏洞復現""網路安全法有什麼規定""CTF奪旗賽怎麼參加" "AWD比賽是什麼""應急響應怎麼做""攻擊溯源怎麼搞" "資料安全怎麼保障""公有云安全怎麼防護""私有云攻防怎麼做" "雲原生安全是什麼"。

↓ 8萬★ 16user_d2cc4baf
人人都能成為駭客v2.0(Lvan)運維安全

這個技能特別簡單——你只需要呼叫它,給一個網站域名,它就會自動幫你跑一遍滲透測試,找出這個網站存在哪些安全漏洞。 不需要你配環境、不用你手動發包,一切自動化。測完直接出結果,告訴你哪裡有問題、怎麼修。 它的願景是:讓每個人都能成為白帽駭客——只要輸入一個域名,就能知道自己的網站安不安全。一切只為授權測試,只為發現漏洞、修復風險,讓網際網路更安全。

↓ 5.7萬★ 37user_a730098d
skill-vetter運維安全

Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.

↓ 5.4萬★ -user_814dbe54

資料月份:2026-10 · 下載/星標數聚合自公開技能註冊庫(ClawHub、SkillHub),按月更新。口徑說明見資料方法。