Plugins

Replaces the add-workspace folder dialog with a path input, drive shortcuts, and the native folder picker.

Adds a knowledge-base picker and a native-attachment paperclip to the DSH composer.

End-to-end PowerPoint assistant preset for DeepSeek Harness with editable deck generation, template-preserving edits, rendering and structural quality checks. Needs Python 3.10+ with requirements.txt installed; rendering also needs LibreOffice and pdftoppm, and OCR of scanned documents needs Tesseract.

《NSCA-CSCS体能教练认证指南（第4版）》学习插件（DeepSeek Harness/dsh 版）：注册 nsca_ocr_page / nsca_use_book 工具。不含书本身，用户需自备本地扫描件。

分流对话（Plugins of Conversation Departure）：为 @deepseek-ai/dsh（DeepSeek Harness）提供的侧边栏插件，把项目上下文打包成结构化 prompt 并复制到剪贴板，配合同屏打开的 DeepSeek 网页版做项目阅读/答疑；支持 PDF/Word/PPT/Excel 文本提取与图片 OCR，自动发现本机 poppler。纯本地：不联网、不调网页接口、不操控浏览器。安装：dsh plugin add dsh-dual-bridge dsh-bett

Windows desktop control for DeepSeek Harness agents: window and UI Automation automation, local Windows OCR, direct browser reads over the Chrome DevTools Protocol (DOM text, JavaScript, selector clicks), humanised mouse and keyboard input, browser tab management, and a live control panel. It probes the machine on first run, writes its own config, and degrades gracefully when a capability is missing. Windows 10/11 only.

SACC 原格式文档翻译 CUDA

Registers one `doc_ocr_sign_fix` tool for DeepSeek Harness: on macOS it diagnoses and repairs the condition where the bundled Python cannot load native extensions (onnxruntime, cv2, pypdfium2) because of the hardened runtime and library validation, by injecting the disable-library-validation entitlement and re-signing the interpreter, then verifying the imports. Operations are idempotent and the original binary is backed up first. It never touches the enclosing application bundle.

Engineering checklists distilled from Gillespie's Fundamentals of Vehicle Dynamics: 164 cards over the book's ten chapters, one skill entry with two-level routing. Each card gives the inputs a computation needs, the procedure, the boundary conditions where the method stops being valid, and a page reference — the explanation itself stays in the book. No passage of the book's prose is reproduced; 44 defects in the source (misprints, OCR damage, internal contradictions) are documented in the cards, each carrying a review-list ID. A study aid, not a substitute for the book.

OCR for scanned, image-only PDFs into Markdown, built around the fact that a book takes about an hour: every page is checkpointed so an interrupted run resumes, a progress log reports live status, and a quality report names empty pages and low-confidence lines. Requires Python 3.10+ and pip install -r requirements; the first run downloads the OCR model.

Extract Bilibili platform/AI subtitles or external/embedded/ASR/OCR fallback and render Markdown, Word, PDF, TXT, SRT or JSON with timestamps, bilingual alignment and a quality report. Requires Python 3.10+; platform/AI subtitles need a Bilibili SESSDATA cookie; OCR/ASR/PDF need ffmpeg, faster-whisper and LibreOffice or reportlab.

Interior and exterior ballistics paper reproduction and code generation skill. Requires LibreOffice Kit for PDF rendering and a vision API key (e.g. Qwen-VL) for formula OCR.

Windows x64 translator with a dedicated sidebar entry and Workbench / Chat interface, side-by-side text and document translation, screen-region translation, recent history, and host model selection, voice input and preview. CUDA document OCR with CPU fallback; screen OCR uses CPU. Do not enable the CPU and CUDA packages at the same time.

Windows x64 translator with a dedicated sidebar entry and Workbench / Chat interface, side-by-side text and document translation, screen-region translation, recent history, and host model selection, voice input and preview. CPU OCR without NVIDIA dependencies. Do not enable the CPU and CUDA packages at the same time.

Registers two tools for DeepSeek Harness. `doc_ocr` turns scanned PDFs and images into structured text (per-page text, financial tables with a balance-sheet tie-out check, contract-clause hits) through a local RapidOCR engine or a Zhipu GLM-OCR cloud engine, and `doc_preprocess` turns a directory of raw files into an Obsidian-ready knowledge base through a seven-stage pipeline with backend routing and sha256-based incremental skipping. Numbers that fail the tie-out are reported, not invented. The local engine needs Python 3 with rapidocr-onnxruntime, pypdfium2 and Pillow (pip install -r requirements.txt); the GLM engine needs ZHIPU_API_KEY.

Structured image recognition: local sharp measurements plus a cloud vision model return description, OCR with coordinates, object locations and fine-grained attributes in one call; a fingerprint cache makes repeated images return in milliseconds without spending model quota.

Lets the agent drive Windows by sight: Windows OCR turns on-screen text into clickable targets, then clicks, drags, scrolls, types and presses keys, verifying each action with a per-pixel diff and an OCR text delta; F6+F7 is a separate emergency stop.

Requires Python 3.12+; Xiaohongshu reading needs the xiaohongshu-mcp backend and a QR sign-in (ffmpeg/OCR optional). Batch-read Xiaohongshu notes and WeChat public-account articles: per-note body, image text via local OCR, video frame text and comment samples, structured JSON/Markdown output, and the original source URL on every result. Read-only: it never publishes, likes, follows or comments.

Local OCR with nothing sent to a cloud: mounts the PP-OCRv6 Medium stdio MCP server (PaddleOCR on ONNX Runtime, CPU) as mcp__ppocr__ocr_image and mcp__ppocr__ocr_pdf for images and multi-page PDFs.

Shows oversized images to the model at readable resolution instead of one downscaled copy: before admission, a large upload is split into as many tiles as the attachment store allows (an 8000x8000 screenshot becomes 20 tiles of 2000x1600), so small text survives. Replaces the local attachment store; adds no settings of its own.

Extract text from an image or PDF, reading a born-digital text layer directly and falling through to a configured OCR engine for scans.

Pull invoice number, date, parties, tax IDs and the amount/tax/total triplet out of text, then verify that amount plus tax really equals the total and flag documents that do not reconcile.

Local OCR using Apple Vision on macOS: text from screenshots, photos, and scans, with no install, no network and no API key.

个人解决经验记忆：保存问题、做法、来源和适用条件，下次相似任务可检索复用，并支持纠正与删除。搭配 dsh-bubble 提问、dsh-look 提供现场上下文。