← Back to Skills Marketplace
33
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install weather-advisor
Description
天气顾问。智能天气顾问。实时天气查询、未来7天预报、穿衣建议与出行活动推荐 Keywords: 天气查询, weather, 穿衣建议, 出行提醒.
README (SKILL.md)
\r \r
概述\r
\r 智能天气顾问。实时天气查询、未来7天预报、穿衣建议与出行活动推荐 适用于查看实时天气信息等场景。\r \r
适用范围\r
\r 适用场景：\r
- 查看实时天气信息\r
- 获取穿衣建议\r
- 了解极端天气预警\r \r 不适用场景：\r
- 需要实时硬件控制或低延迟响应的场景\r
- 涉及敏感个人隐私数据的未授权处理\r \r 触发关键词: 天气查询, weather, 穿衣建议, 出行提醒\r \r
前置条件\r
\r
pip install requests\r
```\r
\r
> ⚠️ 首次使用前请确认依赖已安装，否则脚本将无法运行。\r
\r
## 核心能力\r
\r
### 能力1：实时天气——温度/湿度/风力/空气质量\r
实时天气——温度/湿度/风力/空气质量\r
\r
### 能力2：穿衣建议——基于天气的着装推荐\r
穿衣建议——基于天气的着装推荐\r
\r
### 能力3：出行提醒——极端天气预警与活动建议\r
出行提醒——极端天气预警与活动建议\r
\r
\r
## 命令列表\r
\r
| 命令 | 说明 | 用法 |\r
|------|------|------|\r
| `now` | 查看天气 | `python3 scripts/weather_advisor_tool.py now [参数]` |\r
| `outfit` | 穿衣建议 | `python3 scripts/weather_advisor_tool.py outfit [参数]` |\r
| `alert` | 天气预警 | `python3 scripts/weather_advisor_tool.py alert [参数]` |\r
\r
\r
## 处理步骤\r
\r
### Step 1：查看天气\r
\r
**目标**：查看当前天气\r
\r
**为什么这一步重要**：这是整个工作流的数据采集/初始化阶段，确保后续步骤基于准确的输入。\r
\r
**执行**：\r
```bash\r
python3 scripts/weather_advisor_tool.py now --city Beijing\r
```\r
\r
**检查点**：确认输出包含预期数据，无报错信息。\r
\r
### Step 2：穿衣建议\r
\r
**目标**：获取穿衣建议\r
\r
**为什么这一步重要**：核心处理阶段，将原始数据转化为有价值的输出。\r
\r
**执行**：\r
```bash\r
python3 scripts/weather_advisor_tool.py outfit --city Beijing --activity outdoor\r
```\r
\r
**检查点**：确认生成结果格式正确，内容完整。\r
\r
### Step 3：天气预警\r
\r
**目标**：查看天气预警\r
\r
**为什么这一步重要**：最终输出阶段，将处理结果以可用的形式呈现。\r
\r
**执行**：\r
```bash\r
python3 scripts/weather_advisor_tool.py alert --city Beijing --days 3\r
```\r
\r
**检查点**：确认最终输出符合预期格式和质量标准。\r
\r
## 验证清单\r
\r
- [ ] 依赖已安装：`pip install requests`\r
- [ ] Step 1 执行无报错，输出数据完整\r
- [ ] Step 2 处理结果符合预期格式\r
- [ ] Step 3 最终输出质量达标\r
- [ ] 无敏感信息泄露（API Key、密码等）\r
\r
## 输出格式\r
\r
```markdown\r
# 📊 天气顾问报告\r
\r
**生成时间**: YYYY-MM-DD HH:MM\r
\r
## 核心发现\r
1. [关键发现1]\r
2. [关键发现2]\r
3. [关键发现3]\r
\r
## 数据概览\r
| 指标 | 数值 | 趋势 | 评级 |\r
|------|------|------|------|\r
| 指标A | XXX | ↑ | ⭐⭐⭐⭐ |\r
| 指标B | YYY | → | ⭐⭐⭐ |\r
\r
## 详细分析\r
[基于实际数据的多维度分析内容]\r
\r
## 行动建议\r
| 优先级 | 建议 | 预期效果 |\r
|--------|------|----------|\r
| 🔴 高 | [具体建议] | [量化预期] |\r
| 🟡 中 | [具体建议] | [量化预期] |\r
```\r
\r
## 参考资料\r
\r
### 原有链接\r
- [OpenWeatherMap](https://openweathermap.org/)\r
\r
### GitHub\r
- [weather-api](https://github.com/topics/weather-api)\r
\r
### 小红书\r
- [天气穿搭指南](https://www.xiaohongshu.com/explore/weather-outfit)\r
\r
## 注意事项\r
\r
- 所有分析基于脚本获取的实际数据，**不编造数据**\r
- 数据缺失字段标注"数据不可用"而非猜测\r
- 建议结合人工判断使用，AI分析仅供参考\r
- 首次使用请先安装依赖：`pip install requests`\r
- 如遇到API限流，请适当增加请求间隔\r
Usage Guidance
Review this skill carefully before relying on it. It does not show exfiltration, destructive actions, or credential access, but it also does not actually fetch weather data despite claiming real-time forecasts and alerts. If you use it, avoid sensitive location details, clear the local history file when needed, and only install dependencies you trust.
Capability Analysis
Type: OpenClaw Skill
Name: weather-advisor
Version: 1.0.0
The skill bundle is a basic weather advisor template that logs command execution to a local JSON file. While the documentation (SKILL.md) suggests installing the 'requests' library, the provided Python script (weather_advisor_tool.py) does not actually perform network requests or fetch real weather data; it merely records the inputs and returns a success message. There are no signs of data exfiltration, malicious execution, or prompt injection.
Capability Tags
Capability Assessment
Purpose & Capability
The documentation promises real-time weather, 7-day forecasts, air quality, clothing advice, and alerts, but the Python functions only save command arguments and return generic success messages with reference URLs; no weather API call or actual weather data retrieval is present.
Instruction Scope
The workflow tells the user/agent to confirm complete data and produce a report based on actual data, which is not supported by the tool's actual outputs and may encourage over-trust in unsupported weather or alert advice.
Install Mechanism
SKILL.md asks the user to run `pip install requests`, but there is no install spec and the included script does not import or use `requests`. This is user-directed and common, not automatic execution, but it is unnecessary as provided.
Credentials
The script writes a local JSON history file under the skill's data directory. The write is scoped and not transmitted, but the stored command arguments may include locations or activities.
Persistence & Privilege
There is local persistence of command history, but no evidence of background workers, autostart behavior, privilege escalation, broad file reads, credential access, or network exfiltration.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install weather-advisor - After installation, invoke the skill by name or use
/weather-advisor - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of weather-advisor.
- Provides real-time weather queries, 7-day forecasts, outfit recommendations, and travel activity tips.
- Supports commands: now (current weather), outfit (dressing advice), alert (weather warnings).
- Includes detailed workflow instructions, validation checklist, and sample output format.
- Designed for use in scenarios like checking weather, outfit advice, and understanding weather alerts.
- Requires requests package; no handling of sensitive personal data.
Metadata
Frequently Asked Questions
What is Weather Advisor?
天气顾问。智能天气顾问。实时天气查询、未来7天预报、穿衣建议与出行活动推荐 Keywords: 天气查询, weather, 穿衣建议, 出行提醒. It is an AI Agent Skill for Claude Code / OpenClaw, with 33 downloads so far.
How do I install Weather Advisor?
Run "/install weather-advisor" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Weather Advisor free?
Yes, Weather Advisor is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Weather Advisor support?
Weather Advisor is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Weather Advisor?
It is built and maintained by SKY-lv (@sky-lv); the current version is v1.0.0.
More Skills