Chalk Labs
Need help deploying caiyun-weather?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/zkl2333-caiyun-weather
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: backend, data, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/caiyun-weather
What's inside
- Skill name
caiyun-weather- Description
- Get weather data via Caiyun (彩云天气) API through MCP. Use when: user asks about weather, temperature, forecasts, air quality, or weather alerts for any location in China. Supports realtime, hourly (72h), daily (7d), historical (24h), and alerts. Triggers: '天气', 'weather', '气温', '空气质量', 'AQI', '降水', '预报'. NOT for: locations outside China (use weather skill instead).
- License
- MIT
- Instructions
- 86 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# 彩云天气 Skill
通过 MCP server (`caiyun-weather`) 调用彩云天气 v2.6 API,获取高精度天气数据(1km 分辨率,分钟级降水预报)。
## 前置条件
- 在你的 `mcporter.json` 里加入 server 配置(合并到 `mcpServers` 下即可):
```json
"caiyun-weather": {
"command": "uvx",
"args": ["mcp-caiyun-weather"],
"env": {
"CAIYUN_WEATHER_API_TOKEN": "YOUR_CAIYUN_API_TOKEN"
}
}
```
- 需要彩云天气 API token(环境变量 `CAIYUN_WEATHER_API_TOKEN`)
## 常用坐标
- 杭州萧山:`lng=120.26 lat=30.27`
如需其他城市坐标,用 web_search 查询或从用户获取。
## 可用工具
通过 `mcporter call` 调用,所有工具参数均为 `lng`(经度)和 `lat`(纬度):
### 实时天气
```bash
mcporter call caiyun-weather.get_realtime_weather lng=120.26 lat=30.27
```
返回:温度、湿度、风速风向、降水强度、空气质量(PM2.5/PM10/O3/AQI)、生活指数(紫外线/舒适度)。
### 小时级预报(72h)
```bash
mcporter call caiyun-weather.get_hourly_forecast lng=120.26 lat=30.27
```
返回:逐小时温度、天气现象、降水概率、风速风向。
### 天级预报(7天)
```bash
mcporter call caiyun-weather.get_weekly_forecast lng=120.26 lat=30.27
```
返回:每日温度范围、天气现象、降水概率。
### 历史天气(24h)
```bash
mcporter call caiyun-weather.get_historical_weather lng=120.26 lat=30.27
```
### 天气预警
```bash
mcporter call caiyun-weather.get_weather_alerts lng=120.26 lat=30.27
```
返回:预警标题、代码、状态、描述。
## 天气现象代码(skycon)
| 代码 | 含义 |
|------|------|
| CLEAR_DAY/NIGHT | 晴 |
| PARTLY_CLOUDY_DAY/NIGHT | 多云 |
| CLOUDY | 阴 |
| LIGHT_RAIN | 小雨 |
| MODERATE_RAIN | 中雨 |
| HEAVY_RAIN | 大雨 |
| STORM_RAIN | 暴雨 |
| LIGHT_SNOW | 小雪 |
| MODERATE_SNOW | 中雪 |
| HEAVY_SNOW | 大雪 |
| STORM_SNOW | 暴雪 |
| FOG | 雾 |
| DUST/SAND/WIND | 浮尘/沙尘/大风 |
| HAZE | 霾 |
## 使用建议
- 心跳天气检查优先用 `get_realtime_weather`(一次调用,数据全面)
- 需要判断是否带伞时用 `get_hourly_forecast` 看未来几小时降水概率
- 天气预警用 `get_weather_alerts`,有预警时主动提醒用户
- 彩云 API 有调用频率限制,避免短时间内重复请求From zkl2333/skills, MIT.
More from zkl2333/skills
- 0.502score
pr-precheck
zkl2333
Pre-submission due diligence for upstream PRs to public/large repositories.
SkillCFreshness: C★ 1Claude Code +9 - 0.437score
commit
zkl2333
Generate conventional commit messages following git-cz style by default (emoji between type and subject).
SkillDFreshness: D★ 1Claude Code +9 - 0.437score
bark
zkl2333
Send Bark (day.app) push notifications via HTTP.
SkillDFreshness: D★ 1Claude Code +9 - 0.437score
codex-cli
zkl2333
Operate OpenAI Codex CLI (terminal coding agent) to accomplish software engineering tasks.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
zread
zkl2333
Search and read GitHub repository docs via the Zhipu CodePlan MCP zread server.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
home-assistant
zkl2333
Control and query Home Assistant smart home devices via MCP.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
web-search-prime
zkl2333
Search the web via the Zhipu CodePlan MCP web-search-prime server.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
zai-mcp-server
zkl2333
Use Zhipu CodePlan MCP vision server for screenshot/UI understanding: OCR, error screenshot diagnosis, and UI→artifact conversion.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
web-reader
zkl2333
Read and extract readable content from a URL via the Zhipu CodePlan MCP web-reader server.
SkillDFreshness: D★ 1Claude Code +9 - 0.429score
amap-maps
zkl2333
高德地图 API(通过 MCP)。地理编码(地址↔坐标)、IP 定位、天气、POI 搜索、路线规划(骑行/步行/驾车/公交)、距离测量。Triggers: '高德', 'amap', '地理编码', 'geocoding', '经纬度', 'POI', '路线规划', '导航'.
SkillDFreshness: D★ 1Claude Code +9 - 0.426score
check-updates
zkl2333
检查 OpenClaw 版本更新。当用户说"检查更新"、"有没有新版本"、"update"、"升级"时使用。执行标准三步检查:当前版本、npm 最新版、GitHub 最新版,并给出更新内容摘要和是否建议更新的判断。
SkillDFreshness: D★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Feb 28, 2026 (8 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/zkl2333/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from zkl2333
- 0.502score
pr-precheck
zkl2333
Pre-submission due diligence for upstream PRs to public/large repositories.
SkillCFreshness: C★ 1Claude Code +9 - 0.437score
commit
zkl2333
Generate conventional commit messages following git-cz style by default (emoji between type and subject).
SkillDFreshness: D★ 1Claude Code +9 - 0.437score
bark
zkl2333
Send Bark (day.app) push notifications via HTTP.
SkillDFreshness: D★ 1Claude Code +9 - 0.437score
codex-cli
zkl2333
Operate OpenAI Codex CLI (terminal coding agent) to accomplish software engineering tasks.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
zread
zkl2333
Search and read GitHub repository docs via the Zhipu CodePlan MCP zread server.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
home-assistant
zkl2333
Control and query Home Assistant smart home devices via MCP.
SkillDFreshness: D★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get caiyun-weather running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
caiyun-weather skill. Agent Mart. https://agentmart.dev/skills/zkl2333-caiyun-weather (last updated 2026-10-24)