Weather

## Shared {#shared}

232 stars

byblockcell-labs

View on GitHub Installation ↓

Best use case

Weather is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

## Shared {#shared}

Teams using Weather 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

$curl -o ~/.claude/skills/weather/SKILL.md --create-dirs "https://raw.githubusercontent.com/blockcell-labs/blockcell/main/skills/weather/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/weather/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How Weather Compares

Feature / Agent	Weather	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?

## Shared {#shared}

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.

SKILL.md Source

# Weather

## Shared {#shared}

- 适合查询城市天气、今天/明天/后天预报、是否带伞、穿衣建议。
- 默认数据源使用 `wttr.in` JSON：
  - `https://wttr.in/<城市>?format=j1`
- 如果用户只说“明天天气怎么样”但没有城市，必须先问城市。
- 输出里要尽量使用明确日期，不要只写“今天”“明天”而不落具体日期。

## Prompt {#prompt}

- 城市明确时直接执行，不要因为缺少页数、格式之类无关信息而阻塞。
- 工具策略：
  1. 优先调用 `web_fetch` 获取 `wttr.in/<城市>?format=j1`
  2. 当前天气读取 `current_condition`
  3. 今天/明天/后天预报读取 `weather[0]`、`weather[1]`、`weather[2]`
  4. 如果 JSON 缺失或不完整，再降级请求 `https://wttr.in/<城市>?lang=zh`
- 结果整理要求：
  - 先回答用户真正问的时间范围
  - 再补充必要的温度、天气、降雨或风力信息
  - 如果适合，补一行穿衣或带伞建议
- 建议规则：
  - 温度低于 10C：提醒保暖
  - 温度高于 30C：提醒防暑
  - 天气描述含雨：提醒带伞
  - 紫外线较高：提醒防晒
- 不要直接输出原始 JSON，不要编造未来天气。