Plugins

Investment research bundle: 10 tools (search, page fetch, source audit, claim verification, numeric rigor, channel health, workflow loader, chart engine, PDF renderer, PDF gate) and 23 skills adapted from ai-berkshire. Runs a six-phase workflow where four parallel agents (Duan Yongping, Buffett, Munger, Li Lu) research a company, cross-examine each other, and ship a chart-rich PDF with cover, tables, captions and page numbers. Requires Python 3.10+; the chart and PDF tools also need python-docx and matplotlib.

Competitive-informatics senior plugin for DeepSeek Harness: companion practice, three-version C++14 reference solutions, problem explanations, real g++ compile-and-judge (g++ required), and optional solution-record archiving to the ima notebook "信奥学长-题解复盘", for GESP / CSP-J/S / NOIP / NOI.

Competitive-informatics coach plugin for DeepSeek Harness: coaching-rule prompts, learning roadmap, knowledge points, problem setting, real C++ judging with g++, and ima knowledge-base retrieval with four-notebook archiving, for GESP / CSP-J/S / NOIP / NOI teaching. Needs g++, and an ima account with ima-skill and the four notebooks configured; replies carry a WeChat-account promo and QR code by default.

Publish size check skill: verifies a deliverable's geometric specs against a target platform before publishing - pixel dimensions, aspect ratio, dpi, file size, format, physical print width and colour mode. Geometry only: it does not review content compliance (QR codes, text-to-image ratio, copyright and prohibited content are out of scope). Pure Python standard library, no third-party packages, and inputs are never modified. Python 3.8+. Covers 10 platforms and 20 slots with per-platform confidence labels - WeChat MP, Xiaohongshu, Bilibili, Zhihu, Weibo, Douyin, WeChat Channels, journal submission, print and client delivery - and resolves a platform by id, Chinese name or alias with fuzzy matching. Two trigger modes: asked directly, or as a parasitic self-check that runs by itself once an image, poster, chart or export workflow has written a file and the user mentioned a publishing target, reporting in one line when everything passes and only expanding when something is wrong. For journal submission and print it judges by physical width (pixels / dpi), which catches files whose dpi metadata passes but whose actual printed size is too small; for multi-image posts it checks whether the whole set is consistent and names the odd one out rather than listing every file.

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.

DocChain knowledge base and document conversion toolkit — filename, content and metadata search, locate-by-doc_id/name with content reading, topic listing, bulk document upload, document-to-Markdown conversion, image-similarity search, per-document image descriptions saved to a sidecar markdown, and a deep-research workflow. Every script-backed capability also ships as a native DSH tool executed in-process (doc search, content search, filename search, topic info, metadata search, upload, image search, image describe, doc2markdown). The configuration page keeps several docchain environments (each with its own address and credential), switches between them in one click, and pre-selects topics per environment. Needs a docchain service URL and API key (except doc2markdown); image descriptions additionally need an OpenAI-compatible multimodal endpoint (defaults to an internal gateway model, configurable).

Prose review for human-facing writes. The write and edit tools require a human_facing flag; the plugin reviews the text against layered PROSE.md rules in the background, stages annotations, reconciles them against the full file, and merges them through /humanize, /humanize-loop or post-compaction while the main session keeps working. /humanize-review runs a batch over git-tracked files on demand.

Manage a GitHub Pages blog from a DSH panel — browse the Markdown articles grouped by tag, edit them in a split editor with a front-matter form, and publish the changes as one commit over the GitHub REST API.

GPT-SoVITS voice output for DSH: a speak tool and /voice command, a read-aloud speaker button under each reply, and a settings tab to switch voices, tune synthesis, manage the local service and one-click install a voice pack. Windows only; needs a local GPT-SoVITS checkout with trained weights and its Python environment.

Generative background music while the model streams, plus completion, approval and attention chimes: hear whether the agent is thinking, still working, or waiting for you without watching the screen.

Two-way voice for the DSH web app: dictate with the unified composer, hear replies with speaker buttons and auto-read, on any device. Needs DSH 0.1.7+, Node 22+, Python 3 with numpy and requests, a TTS model, and a microphone.

Meeting notes for dsh: one meeting per conversation, transcribed and speaker-separated on the machine itself, with points, assignments, handwritten notes, reviews and monthly scores in the same panel. Exports SRT/Markdown/Word and packs a meeting into a portable zip another dsh can import; confirmed assignments go to DingTalk/WeCom in one click, following your robot settings. Recognition models are swappable (a stronger local model can be imported from a file), and cloud recognition is off by default with no request made before consent. Word export needs Python and python-docx; the first run downloads a recognition model (28 or 77 MB).

Requires macOS and AirPods with head tracking. Answer DSH permission prompts and questions with AirPods head gestures — nod to allow or confirm, shake to reject or shift the selected option — and install the companion macOS menu-bar app from a card inside the session.

Windows x64 only, 0.5.4 preview: two scoped tools (dragon_browser and dragon_desktop) that drive a visible browser through the DOM or CDP and Windows apps through UI Automation, with per-origin and per-executable read/control scopes, batch steps, a physical-Esc emergency stop and a redacted action log. 0.5.4 only widens the DSH compatibility range to 0.2.0-rc.2 through 0.2.1.x, because 0.5.3 pinned it to an exact DSH version and was silently skipped on DSH Desktop 0.2.1. Two long-lived native processes remove the per-action process spawn, so a single key step takes about 0.7 s on the same machine; when another window steals the foreground the step is aborted instead of typing into the wrong place. The browser side ships its own Edge/Chrome launcher and CDP client, so it no longer needs another browser plugin or the Electron runtime. It is not an OS sandbox; logins, admin windows and secure desktops stay with the user.

Installs the codex-cua skill so DeepSeek Harness can use Codex computer use: drives Chrome and native macOS apps through the runtime bundled with the ChatGPT/Codex desktop app, ships a persistent session client and a doctor self-check. Requires the ChatGPT/Codex desktop app with its Chrome extension, Python 3.9+, and macOS.

Registers one `workpaper_gate` tool for DeepSeek Harness: it audits a workpaper set for completeness, covering both the target design or template itself and the instance-versus-template structure, with the rule list, template list and core-table list all configurable in one spec file. Findings come back as blocker, warning and info, and the workpapers are only read, never modified. Requires Python with openpyxl.

Registers one `valuation_service` tool that reads a workpaper tree of 01/02/04 JSON and returns one unified schema: six ratio groups, forecast ratios, DCF input slots with explicit missing markers, comparable PS/PE and IRR. Deterministic and local: missing WACC, growth, capex, D&A or working-capital inputs stay blank instead of being guessed, and assumption differences are flagged for review.

Registers one `context_extract` tool for DeepSeek Harness: it compresses a long raw document (financial report, contract, ledger) into dense structured Markdown plus JSON — key metrics, tables, numbered clauses, entities and cross-check alerts — so a downstream pipeline can work from the compressed form instead of re-reading the raw document. Financial statements, legal contracts and business ledgers are detected and handled differently; balance-sheet and cash tie-outs are run and mismatches are flagged as alerts rather than silently fixed. Read-only; never modifies the source file. Requires Python with openpyxl and python-docx.

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.

Deliverables registry for DeepSeek Harness: agents register the final artifacts of a task (reports, pages, documents, sheets, images, datasets) into one settings section and manager page that store paths only, never copies, and remove recoverably; a standalone CLI (add, list, stats, check, remove, restore) reads and audits the same registry outside the app.

Composes tools, skills and MCP servers into switchable per-session sets, shrinking the resident tool surface and the system prompt on demand.

Requires Claude Code installed and signed in on this machine. Delegates coding tasks to the local Claude Code agent through the Claude Agent SDK, reports which files changed, supports one-command revert, and adds a Claude Mode toggle to the composer.

Run Python on the local NVIDIA CUDA GPU from DeepSeek Harness: device status, foreground and detached jobs, durable logs, and a measured peak-VRAM figure per run.

Turns a Minecraft Java save into a Blender cover or animation: scans the .mca region files for flat open ground, exports the terrain to OBJ, and drives Blender headless with MCprep materials, the BPS character rig and three-point lighting. After each render it reviews the frame with OpenCV for facing, ground contact, exposure, lighting and composition, then re-renders with adjusted parameters when a check fails. Requires Blender 4.2 LTS or newer and Python 3.10+ with opencv-python and numpy; the first run assembles the Minecraft assets with the bundled setup command.