Daily Pollen logo

Daily Pollen

Community
MagicCube
daily-pollen

花粉过敏指数权威发布与实时监控。当用户询问花粉浓度、过敏风险、花粉预警, 或设置每日定时推送花粉播报时使用。数据来源:花粉通(中国天气网 × 北京同仁医院)+ wttr.in 天气。 支持自定义城市,支持设置 cron 定时每日推送。 触发关键词:花粉、过敏、花粉指数、花粉预警、花粉浓度、今天花粉、每日花粉、 pollen、allergy、pollen alert、花粉播报、花粉监控、每天推送花粉。

Overview

PublisherMagicCube
Repositoryagentara
Skill namedaily-pollen
Stars
516
Forks
58
Bundled files
1
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by MagicCube on GitHub. Read the source before you install it.

Installation

Install the Daily Pollen AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/MagicCube/agentara/tree/main/user-home/.claude/skills/daily-pollen
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/MagicCube/agentara.git /tmp/agentara
mkdir -p .claude/skills
cp -r /tmp/agentara/user-home/.claude/skills/daily-pollen .claude/skills/daily-pollen
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Daily Pollen in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Daily Pollen on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Daily Pollen is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

花粉过敏指数 🌿

每日花粉浓度查询与推送,数据权威来源:中国天气网 × 首都医科大学附属北京同仁医院。

城市配置

默认城市可通过环境变量设置:

bash
export POLLEN_CITY="北京"   # 支持中文或拼音

支持花粉监测的城市: 北京、淄博、昆明、天津、烟台、广州、西宁、沧州、杭州、鄂尔多斯、包头、聊城、兰州、 长春、西安、郑州、太原、银川、哈尔滨、乌鲁木齐、海口、重庆、武汉、石家庄、泊头、 大连、济南、南充、扬州、乌海、保定等。

工作流

Step 1: 确认城市与日期

  1. 读取 $POLLEN_CITY,若未设置则默认使用「北京」。
  2. 记录当前日期(格式:M月D日)和时间。

Step 2 & 3: 并发获取天气与花粉数据

运行 $SKILL_DIR/scripts/fetch_data.py,并发调用天气和花粉 API,将结果输出为 JSON:

bash
POLLEN_CITY="${POLLEN_CITY:-北京}" python3 "$SKILL_DIR/scripts/fetch_data.py"

从 JSON 输出中提取:

  • 天气:weather.desc、weather.temp_c、weather.humidity、weather.wind_kmph、weather.today_rain / tomorrow_rain
  • 今日花粉:pollen.level_label(很低/低/中/高/很高)、pollen.concentration(粒/千平方毫米)、pollen.content(官方建议)
  • 7日趋势:pollen.weekly(按日期倒序数组,含 date/level/num)

Step 4: 解析等级与趋势

花粉浓度等级划分:

等级浓度(粒/千平方毫米)风险描述行动建议
1级≤70很低,一般无需防护正常户外活动
2级71-150低,敏感人群注意敏感人群携带药物
3级151-290中,敏感人群需防护减少户外活动时间
4级291-520高,减少户外活动尽量避免户外
5级>520很高,避免户外活动强烈建议待室内

7日趋势判断规则:

趋势描述判断标准
持续很高近7日均>500,连续多日高浓度
持续高位近7日均>300,整体处于中高浓度
今日更高今日浓度>昨日,且涨幅>20%
有所降低今日浓度<昨日,且降幅>20%
开始升高连续3天浓度上升,进入高峰期
逐渐缓解连续3天浓度下降,离开高峰期
波动较大近7天忽高忽低,不稳定

花粉来源季节参考:

  • 春季(3-5月):柏树、榆树、杨树、柳树、杏树、桃花、樱花(高峰3月中旬-4月中旬)
  • 初夏(5-6月):槐树、梧桐、桑树
  • 夏秋(8-10月):蒿草、豚草、葎草(秋季过敏主因)

Step 5: 格式化输出

使用 Markdown 列表格式输出,确保在各类终端和 IM 应用中正确渲染。

markdown
# 花粉播报 🌿 — {M月D日}

> {一句话今日总结,说明风险等级和核心建议,例如:北京今日花粉5级爆表,连续5日超安全值10倍,过敏人群务必全天待室内。}

## 🚨 今日过敏风险

- **等级**:{N}级({很低/低/中/高/很高})· 浓度 {数值} 粒/千平方毫米
- **超标**:安全值 70,{超标约N倍 / 在安全范围内}
- **主要来源**:{植物1}、{植物2}、{植物3}
- **7日趋势**:{趋势描述}({近7日数据简述,如:近5日均800,3月13日520})
- **日内峰值**:午后 14–17 时浓度最高,早晚相对较低

---

## 🛡️ 今日行动指南

### 必须做

1. {强制建议1}
2. {强制建议2}
3. {强制建议3,视等级增减}

### 建议做

- {推荐建议1}
- {推荐建议2}

### 禁止做

- ❌ {禁忌1}
- ❌ {禁忌2}

---

## 📊 天气参考

- **今日**:{天气描述} · {温度} · 湿度{湿度} · 风速{风速}
- **花粉影响**:{晴天无雨说明扩散条件好;有降雨则说明预计浓度下降}

---

## 📌 温馨提示

{2–3句个性化提示,结合当前等级和趋势给出最实用的一条行动建议,以及今明两日花粉走势预判。
例如:今天全天晴朗,是近期花粉最猛的一天,建议上午尽量不出门。如果必须出门,N95 是底线。
明日天气相似,花粉不会缓解,药不要停。}

📱 更精准数据:微信搜索「花粉健康宝」小程序

等级对应的行动建议内容:

  • 1–2级(很低/低)

    • 必须做:过敏史者随身携带抗过敏药
    • 建议做:可正常户外运动,注意观察症状变化
    • 禁止做:无特别限制
  • 3级(中)

    • 必须做:① 减少户外活动时间 ② 回家后洗手洗脸
    • 建议做:外出佩戴口罩;服用抗过敏药物
    • 禁止做:❌ 花粉峰值期(14–17时)户外剧烈运动
  • 4级(高)

    • 必须做:① 尽量避免户外活动 ② 外出必须佩戴N95口罩 ③ 回家立即洗脸漱口换衣
    • 建议做:提前服用抗过敏药;关闭门窗开启空气净化器
    • 禁止做:❌ 开窗通风 ❌ 晾晒衣物
  • 5级(很高)

    • 必须做:① 强烈建议全天待室内 ② 关闭门窗开启空气净化器 ③ 外出必须佩戴N95口罩 ④ 外出后立即洗脸漱口换衣
    • 建议做:提前服用抗过敏药持续规范用药;关注「花粉健康宝」精确数据
    • 禁止做:❌ 开窗通风 ❌ 晾晒衣物 ❌ 户外运动

关键规则

  • 必须使用 Python 脚本:数据获取必须运行 Step 2 & 3 中的 async Python 脚本,严禁使用 agent-browser 或 WebFetch 工具直接抓页面。
  • 依赖自动安装:脚本首次运行会自动 uv pip install aiohttp,无需手动安装。
  • 数据兜底:若 pollen.error 字段存在(城市不支持或数据暂无),直接告知用户并提示支持城市列表;若脚本报错,提示用户稍后重试。
  • 使用列表,不用表格:推送内容使用 Markdown 列表格式,确保在各类 IM 应用中正确渲染
  • 中文全角标点:推送内容中使用中文全角标点(,、:!)
  • 超标计算:超标倍数 = (浓度 - 70) / 70,保留整数
  • 降雨影响:若今夜或明早有降雨预报,需在天气提示中注明「预计降雨后花粉浓度将明显下降」
  • 数据时效:花粉数据通常每天更新一次,推送时注明数据发布时间

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Daily Pollen AI skill do?

花粉过敏指数权威发布与实时监控。当用户询问花粉浓度、过敏风险、花粉预警, 或设置每日定时推送花粉播报时使用。数据来源:花粉通(中国天气网 × 北京同仁医院)+ wttr.in 天气。 支持自定义城市,支持设置 cron 定时每日推送。 触发关键词:花粉、过敏、花粉指数、花粉预警、花粉浓度、今天花粉、每日花粉、 pollen、allergy、pollen alert、花粉播报、花粉监控、每天推送花粉。

Why use Daily Pollen on TypingMind?

Because you install it once and use it with any model. Daily Pollen is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Daily Pollen in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/MagicCube/agentara/tree/main/user-home/.claude/skills/daily-pollen. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Daily Pollen?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Daily Pollen?

As many as you like. As long as a model supports skills, you can use Daily Pollen with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Daily Pollen AI skill free?

It is published on GitHub by MagicCube. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇