Given the absence of local OCR tools, this skill utilizes the Agent's multimodal capabilities to view images (PNG, JPG, etc.) and transcribe content (text, tables, diagrams) into formatted Markdown.
Given the absence of local OCR tools, this skill utilizes the Agent's multimodal capabilities to view images (PNG, JPG, etc.) and transcribe content (text, tables, diagrams) into formatted Markdown.
鉴于本地 OCR 工具的缺失，本技能利用 Agent 的多模态能力来查看图像（PNG, JPG 等）并将内容（文本、表格、逻辑图）转录为格式化的 Markdown。
Category: tools (工具与实用) · Author: hugohe3 · Version: @main · License: MIT
Control Eight Sleep pods (status, temperature, alarms, schedules).
Terminal Spotify playback/search via spogo (preferred) or spotify_player.
Control Sonos speakers (discover/status/play/volume/group).
Capture frames or clips from RTSP/ONVIF cameras.
Foodora-only CLI for checking past orders and active order status (Deliveroo WIP).
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).
Category:tools