Near-native image understanding for DeepSeek Harness

Official Extensions for DevGlobe. Show up on a 3D globe in real time while you code, with automatic time tracking and coding metrics.

A Swift library for macOS automation — mouse, keyboard, screenshots, image recognition, and AI-powered agents.

Generate images directly in DeepSeek Harness chats

DeepSeek Harness 语音朗读插件：沉浸式听朗读，用豆包 TTS 自然音色读 AI 回复（BYOK · 点读/暂停/继续）

:rocket: The Ultimate Image Uploader for Efficient Creators. Supports Obsidian, Typora, VS Code etc. and 60+ image hosting services (S3, GitHub, Cloudflare R2, Imgur, Aliyun OSS...). Paste, upload, done.

Prompt as Code | GPT-Image2 工业级提示词引擎与模板库，530+ 个案例逆向工程，20+ 套工业级模板，并提炼出Skills，持续更新中

Turn one topic into a finished Vox-style paper-collage explainer/ad video — automated end to end on Atlas Cloud + ffmpeg. An agent skill.

DeepSeek brain + automatic image transcription for DeepSeek Harness: a deepseek-vision provider route that transcribes attached images to text before delegating to the text-only DeepSeek adapter. Official deepseek-v4-flash-vision-exp by default (a pure-te

DeepSeek Harness 外置视觉模型插件：inspect_image 把本地图片或 http(s) 图片 URL 发给任意 OpenAI 兼容端点，视觉模型看图的文字回答直接带回对话；附 Web UI 设置栏。

TongFlow — Multimodal GenAI Studio

Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness with source-preserving evidence.

:zap:The ultimate image uploading engine. Both CLI & API supports.

DeepSeek Harness 本地音乐 + AI 讲书插件：Host 扫描音乐目录并以 HTTP 流式提供音频、解析 .txt 小说结构并经 MiMo TTS 合成朗读，浏览器侧提供播放条/播放面板/章节目录跳转/多声音选择/实时频谱，并注册 music_play 模型工具

Give text-only DeepSeek Harness agents video understanding: scene-aware frame sampling + VLM + optional ASR transcript fused into timeline evidence. / 给纯文本模型的视频理解插件（场景感知抽帧 + VLM + 可选语音转录）

DSH 对话分享插件，分享单轮或多轮对话，可导出为图片或 Markdown。Share DSH Q&As or selected conversation groups as PNG or Markdown.

Local NotebookLM for Claude Code via Google Antigravity (agy / Gemini 3.x): /agy:notebook turns a folder of documents into per-doc summaries + a relevance index + a cited synthesis + Q&A. Plus audio/video transcription, deep web research with citations & branded HTML reports. 13 commands, no Node runtime.

dsh-shorts-wall — docked-first vertical shorts wall for DSH: YouTube Shorts + Bilibili carousel

Wallpaper Engine library as the DSH web GUI background — video/web/still wallpapers, rotation lists, search, resource monitor, bilingual UI.

Animated and video live wallpaper for the DeepSeek Harness Web GUI — GIF, animated WebP/APNG and static PNG/JPEG images, plus MP4/WebM video backgrounds, with auto format detection, a dim slider, and UI chrome tone matching.

为纯文本模型"看图“设计更好的视觉工具箱和技能，支持多图理解，图片问答，前端UI还原、GUI 自动化等，并可选无缝接入多个主流agent，直接识别粘贴图片｜ A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode

Precision PPT design skill for OpenCode/Claude Code/Codex, with 40,000+ styles, pixel-perfect build-mode control, and AI image generation

The fastest way to put Volcengine Ark in your terminal and your AI agent — go from prompt to generated media, multimodal answer, or deployed endpoint in a single command, no API glue code.

Give text-only models eyes: an analyze_image tool for DeepSeek Harness, backed by free Chinese vision APIs (GLM-4V-Flash / Qwen-VL) or any OpenAI-compatible vision endpoint. 给纯文本模型装上眼睛。