Bundle
Unified image understanding plugin for DeepSeek Harness (DSH). Visual twin adapter for native thumbnails + auto-analysis on any text-only model (incl. pi-ai providers); privacy/smart/strict routing; local tools (scan/OCR×4 engines (windows/macos/paddle/rapid)/crop/palette/compare/batch); document-to-image (pdf/word/excel/ppt); local photo editing (image_edit: resize/rotate/filter/composite/watermark/background-remove/upscale etc, pure CPU); optional external VLM bridge.
Bundle
Scientific writing & document integrity guard for AI-assisted research - prompt-guided argument economy with deterministic scientific, delivery, journal, and Word integrity checks.
Bundle
Claude Code-style focus view for the dsh web GUI: the conversation's condensed reading surface — tool calls folded into expandable metric summaries, chat 1:1 row chrome, and streaming think rows
Bundle
Deep reading & summarization for DSH: books/papers/videos/web → structured Obsidian notes. Plugin parsers, MapReduce deep-read, JSON Schema output, idempotent cache.
Bundle
Free image reading (vision) and image generation skills for DeepSeek Harness (rc.7/rc.8/v0.1.1-rc.1) — GLM-4V-Flash free reading with DeepSeek-V4-Flash-Vision-Exp / SenseNova / Gemini failover, SiliconFlow Kolors for generation.
Bundle
DeepSeek Harness plugin (Cordis toolset) for reading, searching, and editing a local Obsidian vault, with optional Local REST API integration.
Bundle
Composer mic for DeepSeek Harness Web: tap-to-monitor live transcription and hold-to-talk, with host Edge TTS reply reading that streams while the model generates, echo-pause during reading, and tap-to-stop.
Bundle
A document-first reader profile bundle for DeepSeek Harness: curated, ordered, searchable, translatable reading of DSH's own documentation over dsh-base + dsh-web-app.
Bundle
DSH 侧边栏里的「全局文档」：全局 Markdown 笔记，任何工作区随时可读。（依赖 dsh-better-sidebar）
Bundle
Workspace-bound arbitrary file upload, reading, OCR, and rendering for DeepSeek Harness.
Bundle
代码研读教练（Code Reading Coach）— 交互式引导研读论文对应开源代码的 Agent 预设插件。五段研读法：锚定论文主张 → 地形扫描 → 入口追踪 → 核心映射 → 闭环验证。
Bundle
Focus Mode for the dsh web GUI: a full-screen reading overlay that hides chrome and folds the AI tool-call flow into summaries, reusing the official Markdown / image primitives.
Bundle
Codex-style message timeline navigation for DSH web clients: a vertical rail of ticks on the conversation edge — hover to preview, click to jump, and the current reading progress stays highlighted.
Bundle
DSH plugin: vision_read — route image reading to a dedicated vision model (e.g. Kimi K3) so text-only agents can see images
Bundle
X (Twitter) connector for DeepSeek Harness: OAuth 2.0 credential binding, posting tweets with per-post cost estimation, and reading/summarizing related posts. Ships a settings card in the Web plugin page.
Bundle
A DeepSeek Harness bundle for local PDF reading, durable paper records, traceable evidence, and cross-paper synthesis.
Bundle
AI老师 (ai-teacher) agent preset for the dsh web GUI: a full-capability teaching agent focused on reading PDF documents and helping the user master them. The preset files are synced into ~/.dsh/.agent-presets on host startup.
Bundle
微信读书 (WeChat Reading) integration for DeepSeek Harness: connect the official WeRead Skills Agent Gateway with a wrk- API key, then browse your bookshelf, export highlights & thoughts, query reading stats, and send highlights to flomo — agent tools plus a web settings panel
Bundle
DeepSeek Harness (DSH) WebGIS Plugin: Map reading, map manipulation, and 3D world comprehension.
Bundle
Plug-and-play image reading for text-only models: admits pasted images, projects them as [Image #N], and provides a first-class read_image tool backed by a configurable vision model, with a 读图 settings page (设置 → 读图) bridged over typert Remote.
Bundle
Private local file attachments for DeepSeek Harness with native images and bounded document reading.
Bundle
A calmer reading view for DeepSeek Harness: native process details, live reasoning, and clean final answers.
Bundle
DeepSeek Harness plugin: content-aware PDF reading tools for vision models (pdf_scan / pdf_read_page / pdf_render_region). Detects figures (vector+raster), tables, math, and two-column layout per page, then routes text pages to extraction and figure/table/math pages to high-DPI region crops rendered for read_image — avoiding DeepSeek's ~800x800 whole-page token ceiling. Backed by PyMuPDF; returns a clear warning (with the exact install command) when Python or a dependency is missing.
Bundle
AI-for-Science research workflow skill bundle for DeepSeek Harness: multi-angle literature review with per-angle files, anchored experiment design with a caveat list, figures, paper reading; cross-verification briefs.