Sunset Bot (国内火烧云预报)

v1.0.0

查询中国国内火烧云预报(sunsetbot.top)。当用户询问某城市的火烧云/晚霞预报,或需要设置定时火烧云通知时使用此 skill。

0· 150·1 current·1 all-time
byFrankMei@neverland83

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for neverland83/sunsetbot-monitor-cn.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Sunset Bot (国内火烧云预报)" (neverland83/sunsetbot-monitor-cn) from ClawHub.
Skill page: https://clawhub.ai/neverland83/sunsetbot-monitor-cn
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install sunsetbot-monitor-cn

ClawHub CLI

Package manager switcher

npx clawhub@latest install sunsetbot-monitor-cn
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description (查询火烧云预报 + 定时通知) match the provided code and SKILL.md: the script navigates to https://sunsetbot.top, extracts page values, writes local logs, and sends notifications via a messaging channel. Required resources (browser support, an optional Feishu OpenID in config) are appropriate for that purpose.
Instruction Scope
SKILL.md keeps scope to fetching forecast pages and sending notifications. It instructs use of OpenClaw's browser() and cron. Two notes: (1) the script injects user-supplied strings (city, date types) into inline JS passed to browser.evaluate — this is a robustness/input-sanitization concern (could break or behave unexpectedly for maliciously-crafted inputs), and (2) the instructions advise enabling headless Chrome with no-sandbox in OpenClaw config, which increases runtime risk for the overall environment (explained in guidance). The skill does not instruct reading unrelated files or env vars.
Install Mechanism
No install spec is present (instruction-only with code included), so nothing is downloaded or installed by an install hook. The included headless Chromium guide references downloading Chrome from an official Google URL and Playwright commands — those are normal for enabling the browser tool but are not executed by the skill itself.
Credentials
The skill does not declare or require any environment variables or secrets. It does rely on an OpenClaw-provided messenger function (feishu_im_user_message) and a local config file (config/config.json) containing a userOpenId; these are proportional to notification functionality. There is no request for unrelated credentials. Ensure that your OpenClaw instance's messaging integrations (Feishu tokens) are intentionally configured.
Persistence & Privilege
always is false and the skill does not request permanent platform-level privileges or modify other skills. It writes logs under its own data/ directory only.
Assessment
This skill appears to do exactly what it says: scrape sunsetbot.top in a headless browser, log results locally, and optionally send messages via Feishu. Before installing: 1) Confirm you trust the external site (https://sunsetbot.top) that the skill visits. 2) If you enable cron and notifications, configure the Feishu/OpenClaw messaging integration carefully — the skill will call feishu_im_user_message via OpenClaw, so ensure tokens/OpenIDs are correct. 3) Review the headless-Chrome guide: it recommends disabling the Chrome sandbox (noSandbox), which weakens process isolation on the host — only do this in environments where you accept that risk. 4) If you will accept free-form city inputs from untrusted sources, review/escape inputs because city values are interpolated into inline JS passed to the browser evaluate call (could break or cause unexpected behavior). 5) Check the data/ directory for logs (sunsetbot-monitor.log) and ensure retention/permissions meet your policy.

Like a lobster shell, security has layers — review code before you run it.

latestvk974wpy4z5erff0vhtrqq32ptd835ymg
150downloads
0stars
1versions
Updated 1mo ago
v1.0.0
MIT-0

Sunset Bot - 火烧云预报(国内版)

⚠️ 重要:调用方式

本 Skill 必须在 OpenClaw 会话环境中执行,不能直接用 node 命令运行。

依赖的全局工具

  • browser() - 浏览器自动化(OpenClaw 内置)
  • 消息通道 - 发送火烧云通知需要有效的消息通道。默认使用飞书(依赖 feishu_im_user_message() 函数),用户也可在 scripts/check.js 中实现其他消息通道

❌ 错误调用

node scripts/check.js              # 报错:browser is not defined
exec node -e "handler({...})"      # 报错:browser is not defined

✅ 正确调用

  1. 对话查询:spawn subagent 执行(见下文"使用方式")
  2. 定时监控:通过 cron 配置,由 OpenClaw 自动执行

快速开始

1. 环境要求

本 Skill 需要浏览器支持:

  • 本地环境:通常已有浏览器,无需额外配置
  • 云服务器:需安装 Headless Chromium,详见附录

2. 配置(定时通知必须)

创建 config/config.json

{
  "notifyChannel": "feishu",
  "userOpenId": "你的飞书Open ID"
}
参数说明
notifyChannel通知渠道:feishu / telegram / none
userOpenId飞书 Open ID(飞书开发者后台获取)

💡 对话测试时无需配置,定时通知时必须配置。


使用方式

对话查询

当用户询问火烧云预报时,spawn subagent 执行

  1. 读取 SKILL.mdscripts/check.js
  2. Spawn 一个 subagent
  3. 在 subagent 中调用:
    handler({ city: '深圳', dates: ['明天日出', '明天日落'], source: 'GFS' })
    

定时监控

通过 cron 自动运行,有火烧云时发送通知:

openclaw cron add \
  --name "sunsetbot-morning" \
  --cron "0 9 * * *" \
  --tz "Asia/Shanghai" \
  --message "读取 skills/sunsetbot-monitor-cn/scripts/check.js,调用 handler({ city: '深圳', dates: ['明天日出', '明天日落'], source: 'GFS', needNotify: true })" \
  --no-deliver

参数说明

参数说明默认值
city城市名称深圳
dates日期类型数组:今天日出今天日落明天日出明天日落["明天日出", "明天日落"]
source数据源:GFSECGFS
needNotify是否发送通知并记录日志false
dryRun干运行模式,只查询不通知不记日志false

技术细节

  • 使用 JavaScript evaluate 直接操作 DOM
  • 日期类型映射:今天日出=rise_1今天日落=set_1明天日出=rise_2明天日落=set_2
  • 日志格式:JSONL,存储在 data/sunsetbot-monitor.log
  • 火烧云等级判定:<0.2 无烧,0.2-0.5 小烧,0.5-1.0 中烧,1.0-2.0 大烧,>2.0 世纪大烧

附录

Comments

Loading comments...