用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/qualcomm/qai-appbuilder --skill weather命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
| name | weather |
| description | Query weather forecasts for any city. Uses wttr.in service, no API key required. |
| tags | weather, forecast, wttr |
| use_for | Getting current weather, checking weather forecasts, querying weather by city name |
| homepage | https://wttr.in/:help |
Use the exec tool to run the following command to get weather forecast:
Required Action: Call exec tool to run command immediately. Replace "shanghai" with the city name from the user's request (supports both English and Chinese city names).
Tool call: <tool_call> {"name":"exec","arguments":{"command":"python ${SKILL_DIR}/scripts/get_weather.py shanghai","timeout":30}} </tool_call>
DO NOT make up weather data. Call exec tool immediately with timeout set to 30, replacing "shanghai" with the city name from user's request.
Final Step: When you receive the output from the exec command, verify it contains weather data, and then present it to the user.
Shanghai Weather Forecast
==================================================
2026-03-30: 18~24C, Partly cloudy
2026-03-31: 17~23C, Sunny
2026-04-01: 19~25C, Cloudy
App Builder — generate complete, runnable fullstack WebUI applications (FastAPI backend + pure HTML/CSS/JS frontend) around on-device AI Model Packs (OCR, TTS, ASR, Super-Resolution, etc.). Use this skill when the user wants to build, generate, modify, or debug a standalone WebUI app around any installed Model Pack.
A professional programming assistant supporting code writing, debugging, review, refactoring, and performance optimization, as well as open-source repository analysis.
QAI ModelBuilder. Tools and workflows for model conversion, inspection, operator patching, quantization, and inference validation of self-converted models on Qualcomm platform. Use this skill when working with custom ONNX/PyTorch models — export to ONNX, convert to QNN/SNPE DLC, FP16/FP32/INT8 quantization, operator patching, context binary generation, and inference validation of self-built models. NOT for AI Hub prebuilt packages — use model-hub skill instead.
