Plugins

DSH plugin: deterministic, offline Python/Django production-report diagnostics — traceback root cause, pytest summaries, unapplied migrations, N+1 SQL, manage.py check --deploy and Celery backlog. Does not execute Python, start subprocesses or touch the n

Live remote SSH workspaces with a resident Python RPC agent, remote shell/glob/grep execution, SSH port forwarding, ~/.ssh/config import, ProxyJump, and conflict-safe three-way cache sync.

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.

Training Lens opens a local TensorBoard scalar dashboard with selectable metrics, explicit improvement direction, optional EMA smoothing and Chinese/English UI; requires an existing Python environment with TensorBoard.

Inspects ONNX models (inputs/outputs, shapes, opset, operators, size) and benchmarks them with ONNX Runtime on the local machine or on a remote target over SSH, reporting average/P50/P95/P99 latency, FPS and the execution provider actually used, with PASS/FAIL gates for FPS, P95 latency and model size. Requires Python 3.10+ with numpy, onnx, onnxruntime, and psutil installed (pip install numpy onnx onnxruntime psutil); remote targets need python3, numpy, and onnxruntime.

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.

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.

Skill that reviews your coding-agent session transcripts (Claude Code and Codex only; DSH's own transcripts are not supported) over the last two weeks and reports which skills, hooks and rules work, need attention or go unused. Requires Python 3.

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.

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.

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.

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).

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.

Lets the model actually see a video: local ffmpeg samples timestamped stills and faster-whisper transcribes the audio track, so the agent reads real pixels frame by frame instead of trusting a text summary. Fully local, nothing uploaded; reports honestly when the audio has no speech. Windows only; needs Python 3.10+ and ffmpeg installed, and the first video_eyes_setup run downloads about 700 MB (faster-whisper and its model).

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 `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.

Keeps the /tmp cleanup daemon alive: an in-process watchdog revives it within about two minutes after Android kills it, runs the due cleanup inside dsh while it stays down, and adds a settings page for status, config, clean and dry-run. The cleaner ships inside the package (bin/tmp-clean, Python 3), so no extra install step is needed.

Author custom tools in Python from a web page, in chat, or from the dsh-go app's native panels, and register them as DSH tools without a restart; dangerous tools need built-in approval on every run, tools can be grouped into packs, and an optional unlock mode exposes them per conversation. Needs Python 3 on PATH.

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.

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.