Token导航 LogoToken导航TokenDH.com
效率敏感数据clawhub未标认证来源可访问clear审计提醒

wind-site风场

Agent Skill

wind-site 用于补充效率相关能力,适合在 OpenClaw 中需要让 Agent 承接效率相关任务时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

20,077

周安装

845

GitHub Stars

公开资料未说明

下载量

7,030
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:wind-site(风场)
来源仓库:https://github.com/qrost/wind-site
安装命令:
openclaw skills install wind-site
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install wind-site

简介

风玫瑰图、某个地点的风速/风向;支持场地和城市风评估(仅数据;详细的 CFD 超出范围)。

SKILL.md

name
wind-site
version
1.1.1
description
Wind rose, wind speed/direction at a site; supports site and urban wind assessment (data only; detailed CFD is out of scope).
author
qrost
permissions

Wind & Site

Wind climate and current wind at a location: wind rose (direction and speed frequency) and latest wind conditions. Uses Open-Meteo (no API key). For detailed urban or building wind effects (pedestrian comfort, corner acceleration), use CFD tools; this skill provides the site wind data needed for context and input to such studies.

Dependencies

  • requests
  • numpy
  • matplotlib

Setup: OpenClaw does not install Python packages automatically. After installing this skill, run once: pip install -r requirements.txt (from the skill folder). If a script fails with ModuleNotFoundError, install the missing package.

Usage

1. Current or recent wind

Parameters: --lat, --lon, optional --days (0 = current from forecast; >0 = last N days from archive).

python3 scripts/wind_info.py --lat 31.23 --lon 121.47
python3 scripts/wind_info.py --lat 34.05 --lon -118.24 --days 7

Output: latest wind speed (m/s) and direction (°), and period mean if multiple hours.

2. Wind rose

Parameters: --lat, --lon, --days (default 30), --output (default wind_rose.png).

python3 scripts/wind_rose.py --lat 31.23 --lon 121.47 --days 30 --output wind_rose.png

Fetches hourly wind from Open-Meteo historical API and plots a wind rose (% of hours by direction and speed bins).

Sending images to Telegram

Used from the OpenClaw Telegram conversation. The wind rose is an image: run wind_rose.py with --output <path>.png. Then send that PNG to the user via the OpenClaw message/media tool. wind_info.py is text-only; use it for numbers and use the wind rose image for the visual.

OpenClaw allowed paths: The message tool can only send files from allowed directories. If you see "Local media path is not under an allowed directory", the image was saved outside them. Always use an allowed output path for the PNG:

  • ~/.openclaw/media/ (e.g. --output ~/.openclaw/media/wind_rose.png)
  • ~/.openclaw/agents/
  • The system temp dir (e.g. /tmp/wind_rose.png)

Do not use the skill install directory (e.g. ~/.openclaw/skills/windsite/) as --output; that path is not allowed and sending will fail.

Agent behavior: When the user asks for wind at a site or a wind rose (with location or lat/lon), run the script directly with exec: use wind_info.py for current/recent wind text, and wind_rose.py --output <path>.png for the diagram, where <path> must be under an allowed directory (e.g. ~/.openclaw/media/wind_rose.png or /tmp/wind_rose.png); then send the wind rose PNG and summarize the numbers. Do not ask for confirmation; execute and return the image and data.

Urban wind effect

This skill does not run CFD or pedestrian wind simulation. It provides:

  • Wind rose and wind speed/direction for the site, so you can see prevailing wind and strength.
  • Use that data as input to CFD or specialist tools (e.g. SimScale, OpenFOAM, or wind-tunnel studies) for building/urban wind effects and comfort.

Examples

User: "What's the wind like at this site?" Action: Run wind_info.py for the site lat/lon; return speed, direction, and brief interpretation.

User: "Give me a wind rose for Shanghai for the last 30 days." Action: Run wind_rose.py --lat 31.23 --lon 121.47 --days 30 --output ~/.openclaw/media/wind_rose.png (or /tmp/wind_rose.png); send that file and return a short summary.

User: "I need to assess urban wind around a new tower." Action: Run wind_rose and wind_info for the site; explain that for building/urban effects they should use CFD or wind-tunnel studies, with this data as climate input.

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

90.08%
按下载量换算6,333

安全审计

VirusTotal

可疑

ClawScan

通过

Static analysis

未展示

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills