Plugins

Gives agents the DSH (Cordis) plugin authoring contract and the dsh plugin market submission process, from the bundle manifest and entry module to the pull request.

Sorts every loaded skill into one or more user-owned workspaces in a right-sidebar tab: each workspace is its own category list plus where every skill sits, categories are created, renamed, reordered and deleted in place, and skills are dragged or picked between them. A first run can let the profile model build the first classification, or place skills into categories the user built first; clicking a row copies its /skill-name and hovering unfolds the description the skill ships.

Skill panel for the DSH Web GUI: lists every installed skill with Chinese annotations and eight category filters, runs pinyin and fuzzy search, ranks by pin and recency, and manages each skill in place (pin, disable, reveal, uninstall with undo). Ships its own maintenance skill.

A fork of Microsoft's official .NET/C# skills for AI coding agents, additionally packaged as a DeepSeek Harness plugin — covering development, testing, diagnostics, migration, and AI integration.

Shows which skills each turn invoked and installs, updates or removes skills inside the app.

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.

Tag-based skill filtering: attach tags to DSH skills, then hand each workspace or conversation only the subset its boolean tag expression selects (for example `pdf + docx` or `aegis * plugin`). Excluded skills are deny-shadowed out of the model catalog rather than merely hidden in the settings UI; skills outside the expression can still be added by hand or force-disabled, and the bundled `tagging-skills` teaches the agent to derive a tag set from the machine it is running on.

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.

Write, check, and publish a Chinese Quarto Book: nine-step chapter writing, structure/link/figure checks, a consistent theme, and render acceptance. Loads only in type: book repositories; requires Quarto CLI and Python 3.

Reads assistant replies aloud with Microsoft Edge neural voices and highlights the sentence being spoken, so you can follow along while listening. The highlight is yours to style: background colour, text colour and opacity are each adjustable in settings. Also adds a sound-wave play button to every reply, pause plus previous and next sentence, adjustable speed, and an auto-read toggle.

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.

Local offline prosody analysis for DeepSeek Harness: reports how something was said — speed, pitch, pauses, energy — alongside the transcript.

Search public-domain libraries (Project Gutenberg, Wikisource, Internet Archive, Standard Ebooks) by title, author, character or half-remembered plot, or import EPUB / PDF / TXT / DOCX / Markdown, and listen in the sidebar with Microsoft Edge neural voices, offline Kokoro or the device voices; keeps your position, takes voice notes anchored to what you just heard, and discusses the book with your DSH model.

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.

Adds a visible-browser Agent preset (persona and toolset for navigating, filling forms, clicking and screenshotting through the Playwright MCP toolset) plus a gate that refuses every browser tool call in other presets until the user approves that Session through the bundled browser_access tool. The bundle mounts the Playwright MCP provider itself, and both a settings page in the Plugins view and the browser_source tool switch the browser at runtime between Microsoft Edge (default), the Chromium shipped with Playwright, and a CDP endpoint. Requires keeping the shared browser-use registration row in the profile (one provider per process).

A persistent translate button lives in every page the browser opens: click it and every visible text node is replaced in place, click again to restore. Hold to drag, drop it near an edge and it tucks into a small handle; it is re-injected automatically after navigation. The host LLM service does the translation — the plugin holds no API key.

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.

Adds a logon autostart switch for the DeepSeek Harness desktop app on Windows. It manages a single shortcut in the user Startup folder: no registry writes, no admin rights, no extra background process.

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 `principles_audit` tool for DeepSeek Harness: it reviews a principle library for principle_id collisions and legacy ids, missing causal statements, boundaries, counter-examples or evidence, duplicate and near-duplicate principles, status-versus-confidence inconsistencies, long-stale entries and dimension-coverage gaps. Findings are severity-ranked and a hard gate turns them into pass, warn or fail, where every critical finding must be covered by a valid, unexpired exemption. The library is only read.

Registers one `office_audit` tool for DeepSeek Harness: it recalculates formulas with the bundled LibreOffice Kit and then audits the recalculated values — formula errors, broken sheet references, formula-consistency, hardcoded constants, number-format and unit mismatches, balance-sheet balance, retained-earnings roll-forward, cash tie-out, cash-flow subtotals, ratio-table conventions and data-cleaning issues. Findings are severity-ranked with the offending cell, and an optional findings sheet can be written into a copy. The source workbook is never modified. Requires Python with openpyxl and the bundled LibreOffice Kit.

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.