技能列表

把迁移方案整理成 runbook，补齐切换窗口、前置检查、回滚与验收信号。；use for migration, runbook, rollback workflows；do not use for 执行数据库改动, 忽略回滚条件.

Generate and edit images via Google Gemini API. Supports Gemini native generation, Imagen 3, style presets, and batch generation with HTML gallery. Zero dependencies — pure Python stdlib.

OpenClaw skill for Facebook Graph API workflows focused on Pages posting, comments, and Page management using direct HTTPS requests.

Connect and control Midea devices through the Midea cloud with a local cached account/device config. Use when a user wants to connect a Midea account, list discovered Midea devices, or power on/off a named Midea air conditioner through cloud APIs. Triggers include requests like “连接美的设备”, “配置美的账号”, “列出我的美的设备”, “打开儿童房空调”, and “关闭主卧空调”.

|

Queries csfloat.com for data on skins

Audio tagging service for environmental sound recognition. Use when user needs to identify environmental sounds in audio files (water sounds, snoring, etc.) or analyze audio content for sound classification.

Send test or generated images directly to Telegram chats using the message tool with Picsum.photos URLs or custom media. Use when the user requests to 'send photo', 'generate image here in TG', or show/test images in Telegram (e.g., 'пришли фото', 'покажи картинку').

Developed by Xiaomi and Shanghai Jiao Tong University. Transform text into high‑quality audio scenes with speech, SFX, music, and ambiance. Demo: https://nieeim.github.io/Dasheng-AudioGen-Web/

Run an autonomous Open Ralph Wiggum coding loop using OpenCode Zen with free models and automatic fallback.

>-

|