Plugins

Registers the dsh-mol stdio MCP server, built on RDKit with no network access, into a DSH profile. It exposes 12 tools: three-level SMILES validation with human-readable diagnostics and character positions, molecular properties, drug-likeness and structural alerts, structure rendering to PNG/SVG, multi-molecule grids, format conversion (SMILES, InChI, InChIKey, MOL, SDF, formula), standardisation with a per-step change log, deduplication, SMARTS substructure matching, fingerprint similarity, and batch clean-up that reports every rejected row. The patch only registers the server; the tools live in this repository's Python package and must be installed first — the README gives a `pip install` route and a from-source route, and until the package is on PyPI the from-source one is what works.

Fronts stdio MCP servers with three router tools (list_capabilities, describe_tool, call_tool) so schemas load on demand instead of riding every request; shapes every tool result through a deterministic output ladder that archives the original first (retrieve_spill reads it back); prices tool groups in tokens and can hide built-in groups per agent. Bridges to a standard-library Python router, so Python 3.9+ is required.

Compaction fallback for compaction-basic: when its LLM summary throws, comes back empty or cannot fit the window, the span is compiled deterministically with a seq pointer on every line (vendored dsh-compaction-instant compiler). Adds recall and search tools, /recall and /context commands, an idle trigger at 45% of the window and an on-disk span archive. The engine mounts as one row in the agent preset (docs/dsh-integration.md).

Real-time LSP diagnostics loop: lsp_diagnostics / lsp_workspace_errors / lsp_hover tools over headless stdio language servers (TypeScript/JavaScript + Python), plus an auto-injected post-edit diagnostics delta wired to the harness fs/observed event — Cursor-style edit → diagnostics → fix for dsh agents.

Per-project runtime environments for DeepSeek Harness: auto-adopt or create a project-local Python venv (.venv_local/python) and wire in the toolchains and env vars for the runtimes each project uses (python venv / node / go) — python & pip always resolve to the project, never silently to system Python.

Windows desktop automation for DeepSeek Harness: accessibility-first observe/act loop with 30 standard tools (element/coordinate targets, auto/a11y/event strategy routing), superseded-observations and no-replay safety semantics, persistent kill switch, RuntimeId/rect-drift stale protection, chat cards and a floating panel (live ops, frame wall, env auto-detect settings), tiled vision describe for low-res models, JSONL audit trail and a pid allowlist. Requires Windows 10+ and Python 3.9+ with uiautomation and pillow (installable from the settings page).

DSH-native uv environment manager: create, sync and run Python virtualenvs from the settings tab, with pip fallback, read-only conda visibility and a dry-run project sync preview.

macOS desk pet forked from anneheartrecord/dsh-desk-pet, in a real always-on-top window that covers fullscreen Spaces: the pose follows whatever the local DSH is doing across six states, the right-click menu is a real AppKit one carrying quiet mode and a session list, and seven skins ship with it. Two of the seven are drawn from geometry by a script in the repo rather than generated, so making a skin needs no image model and no API credits; the bundled skill still expands one photo into all eighteen poses on your own image tool and credentials. There is no Electron and nothing to install alongside it: the window is driven through ctypes on the Python that ships with macOS.

China-ready voice input for the composer. Requires a local Python bridge (pip install dashscope websockets, run bridge/voice-bridge.py) — the plugin alone does not work. Browser mic streams 16 kHz PCM to the bridge, which runs Alibaba Cloud DashScope ASR (paraformer-realtime-v2); interim text fills the draft at the cursor, silence auto-stop, optional auto-send.

Econometrics research assistant: 6 tools covering method selection, data preparation, model specification, empirical analysis with Python/R/Stata code templates, robustness checks, and result reporting.

Registers the remove-pdf-background-gray skill for DSH: whitens gray/off-white scan backgrounds in image-based PDFs while preserving resolution, page geometry, and anti-aliased text edges (lossless Flate write-back), via a single Python script (pypdf + Pillow + numpy).

Bridges the harmonyos-dev-mcp Python MCP server into DSH: HarmonyOS device discovery, build/install/run/uninstall, UI automation (click/input/keys/swipe/screenshot), E2E UI-tree inspection, and log/crash analysis as 18 mcp__harmonyos__* tools.

Unreal Engine .uasset inspection (resolve/registry/load) and restricted Blueprint node editing through built-in UE Python.

Desktop (native) control for dsh as a stdio JSON-RPC bridge over a Python core: capture the screen, inject pointer/keyboard input, drive accessibility-tree actions, and gate high-risk operations behind required confirmations.

Tempguard temperature watchdog tools for DeepSeek Harness

Native DSH support for context-mode (mksglu/context-mode), intercepting large tool outputs with SQLite FTS5 indexing, BM25+RRF search, and session continuity. On by default: tool outputs over 4 KB are replaced with a short preview while the full text is indexed into ~/.context-mode/context.db, and a section is added to the system prompt. Its ctx_execute and ctx_batch tools run shell, Node, Python, PowerShell or cmd commands with DSH's own permissions and environment (not sandboxed), and ctx_index reads any local file path or fetches any http(s) URL it is given.

DeepSeek Harness web panel for creating, evaluating, repairing, and installing skills, delegating generation to the official generic and Huawei Cloud skill creators. Needs git, bash and python3, and network access to gitcode.com (the creators and reference data are pulled from there); the creator runs shell commands with danger-full-access by default.

Bilibili course notes for DSH: turns the videos and subject knowledge maps recorded by dsh-video-coursemap into same-name Markdown + Word notes with the video link on top, and delivers them in a new session through dsh-memory-evolve. Requires both plugins (with memory-evolve session orchestration turned on), Python with python-docx for the Word file (the DSH bundled runtime works), and Windows.

Download watermark-free Douyin and Xiaohongshu videos, transcribe them with local or cloud speech recognition, proofread the text against a term list, and export Markdown, DOCX, SRT, VTT and other formats from a settings panel or agent tools. Needs Python 3.10+ with pip packages (playwright, python-docx, numpy, and sherpa-onnx for the default local SenseVoice engine, which also downloads a ~228 MB model on first use), ffmpeg on PATH, and Chrome or Edge.

Turn the Edifier Halo PixelBar desktop pixel display into a DSH tool: push short text, switch scenes, set screen color, ambient light and volume over HID, and restore the clock on demand. USB-connected device only; tested on Windows only; needs Python 3.8+ with hidapi (pip install hidapi).

Codex conversation panel for DeepSeek Harness: lists local Codex threads, renders their history, and sends messages back to the original thread through the Codex CLI. Needs the Codex CLI and Python installed locally.

Doubao video workshop: a gated pipeline from storyboard to finished cut. Locked art direction, shot validation, character-card vs reference-image separation, first/last-frame continuity and clip dedup; model-aware duration caps (Mini/Fast 10s, 2.0 15s, 2.5 40s). Uses ffmpeg for frame extraction, concatenation and subtitles; speech synthesis calls a separately installed local TTS plugin, and ASR subtitles need Python with faster-whisper.

Math-modeling contest workbench for DeepSeek Harness: a sidebar P0–P7 progress board and traceable facts ledger, one-click render/check/layout/compile, PDF preview, and human sign-off; paired with the math-modeling-cumcm skill. Requires the math-modeling-cumcm skill's scripts (set skillDir), Python 3.10+ and XeLaTeX with ctex/xeCJK; fully verified only on Windows 11 + MiKTeX.

Knowledge-planet (zsxq) knowledge base skill: sync posts and attachments, extract docx/PDF text, guide topic category, summary and quote enrichment, rebuild the index, and search. Requires Python ≥3.10 with the packages in requirements.txt plus your own zsxq account cookie.