視覚ツール · DeepSeek Harness プラグイン — 8 ページ

鲸影 DSH Video Studio：DSH 原生视频/漫剧生成插件（七段导演流水线 × 多账号额度池 × 提示词自优化 × 自我审计）

Pure React attachment atoms for the dsh web UI: draft-image rail, message image gallery, and original-image lightbox (zero cordis)

Unified OpenAI Codex subscription plugin for DeepSeek Harness: GPT models, OAuth, quota, image generation, and web search.

不装皮肤中心也能用 Claude 皮肤：把皮肤样式表按作用域契约注入页面，并用自己的路由送出皮肤自带的字体与图片。

Local PDF, Office, image, and OCR document intelligence for DeepSeek Harness.

Galgame generator for DeepSeek Harness (DSH): give it a script document plus character/background/BGM/animation assets in the workspace (img_human/, img_bg/, audio/, img_cg/, optional img_ui/) and it builds a playable visual-novel web page with a customizable title screen, configurable save slots, speaker-following multi-pose sprites, [表情]/[位置]/[退场] stage control, opening/ending/CG animations, BGM control and if-line branching. DSH Galgame 生成器：提供剧本文档 + 立绘/背景/音乐/动画素材（img_human/、img_bg/、audio/、img_cg/，可选开始界面素材 img_ui/）即可生成可玩视觉小说（可自定义开始界面、可配置存档、多表情立绘、站位/退场控制、动画、BGM、if 条件线）。

工科题解工作台：泛用读图（任意学科题图/图表/表格）、回读自检、通用求解（符号+数值）、通用可视化（单一引擎 + 学科预设）与独立视觉校核。

Role-play conversations, character-card authoring and image generation for DeepSeek Harness.

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-text V4-Pro brain can see images), any OpenAI-compatible VLM or local Ollama as alternatives, never hangs.

Local OCR provider (rapidocr fast + DeepSeek-OCR-2 deep) registered as the 'ocr' service for the llm-deepseek adapter seam. Unofficial community plugin for DeepSeek Harness.

Russian localization for DeepSeek Harness (DSH v0.1.6-alpha.1+) web UI: adds Русский as native language option. 100.0% coverage across 11,295 keys (127 namespaces). Features full DSH v0.1.6-alpha.1 core support (terminal, archive, command palette, Auto review, trajectory, PTC/Creator presets) and complete GoodAndReady plugin catalog (subscriptions, tts, image-gen, voice, key-limits, notify, commandcode, plugin-console).

VCP 视觉通感协议规范插件：消息 HTML 渲染开关 + vcp-fast 缓存/增量加速渲染引擎 + 12 款内置精选字体 + 设计规范注入（任何电脑/agent 即插即用）

DeepSeek Harness plugin that uses configured model providers for image analysis and context compaction.

Plug-in vision for text-only LLMs, powered by the free Antigravity CLI

DSH skin plugin: built-in skins + custom image skins, pure client plugin (no source patch)

FreeStyle 主题：全窗口主题工作室，实时设计、对比预览、色觉模拟、无障碍体检、12 套坐标预设、主题库、图片/一句话生成与分享码，覆盖全部 119 个 --dsw- 令牌并自适应明暗。

Provider-independent DSH document parsing powered by MinerU, with native background jobs, immutable results, and safe request coalescing.

DeepSeek Harness plugin for batch-producing e-commerce main images from PSD templates: product slots, SKU cut-out fitting, canvas fine-tune, and agent tools.

Use DeepSeek Harness directly in VS Code: secondary sidebar chat panel, @dsh built-in chat participant with @ file/session/agent mentions, multimodal image attachments, model/preset/permission/thinking controls, subagents, Cordis plugin approvals, and turn-level Git rollback (undo one turn, restore checkpoints).

为 deepseek-v4-flash-vision-exp 量身定制的大图智能识图插件：整图预检 → 本地 OCR+像素网格（文字）+ 兴趣点按比例切块（最长边 800）→ 汇总；保留全图 800x800 网格切块模式。不统计 token、不计算费用。v0.4.2：picturereader 适应性优化（共存分工引导/视觉端点复用/OCR venv 共享）。

DeepSeek Visionary native plugin for DeepSeek Harness: deepseek_vision / status / login / logout native tools plus the text-model image bridge, all backed by the visionary-server CLI (DeepSeek web vision model, no API key).

DSH 侧边栏文件活动插件：按 LRU 记录文件读取/新增/修改事件（最近访问），按绝对路径树形统计（文件统计），点击文件浮窗预览（代码高亮/Markdown/图片/PDF）。DSH web plugin: file activity tracker — LRU recent-access list plus per-file read/create/modify counts in a folder tree, with floating preview.

Upload button + drag-and-drop files into DSH conversation as local paths (works with any vision plugin)

DSH Web GUI right sidebar: VS Code-style file explorer plus source control (git status, stage/unstage/discard, commit, diff, commit graph, sync fetch/pull/push, branch/remote management, git init, multi-repo switch, color-coded file status, file-type icons, image preview) with an editable full-file diff view (hunk stage/revert), a syntax-highlighted editor (15 languages), file operations (new/move/copy/delete), a collapsible icon rail, a multi-tab bottom terminal (ConPTY), AI-generated commit messages from a host-configured model, and save.