Plugins

开发仪表盘 —— 把 control-your-development 的产品仪表盘嵌进 DSH 右侧边栏与会话页

Xiaomi Smart Storage (MINAS) NAS file tools for DeepSeek Harness: registers the minas-webdav MCP server (14 nas_* tools) as a bundle. 小米 NAS 的 WebDAV 文件工具，注册 minas-webdav MCP。

Wraps the upstream ppt-master presentation skill set as an installable DeepSeek Harness plugin: byte-for-byte vendored skills, three lifecycle tools (ppt_master_info, ppt_master_check_env, ppt_master_setup_deps), optional venv interpreter isolation, and a Plugins-page configuration card. Requires python3 ≥ 3.10 plus the pip dependencies installed via `ppt_master_setup_deps`.

Registers the domestic-China trip-planning skill: hour-level daily timelines, 12306 and Trip.com booking deep links, offline KML, and seven HTML themes. Requires Python 3.9+ on PATH (the bundled scripts are standard-library only).

Academic tools in TypeScript, no Python or MCP server: the Zotero library through its local API or zotero.org (search, annotations, full text, citation export; add by DOI / arXiv id, notes and tags when writing is turned on), starting Zotero when it is closed; paper search across arXiv, OpenAlex, Crossref, Semantic Scholar, PubMed and Europe PMC, plus CNKI and Google Scholar through a browser window; open-access full text, citations from the DOI registry, reference checking; 11 bundled skills.

Self-evolving agent framework on DeepSeek Harness (dsh): 40 Cordis plugins and 4 presets covering memory, reflection, gates, metrics and an auditable evolution loop. Not a one-command install. Clone the repo and run install/install.sh --profile=web (needs bash, Node 20+, python3, DSH 0.1.7-rc.1 or newer with an initialized profile), then restart.

Bundles 19 short-video production skills (1 entry point, 1 orchestration, 17 atomic) into the agent skill catalog: Chinese TTS pronunciation fixes, text-to-image and text-to-video, image panning, composition, covers, media verification, data review and four-platform publishing. Ships skills and scripts only, so a runnable pipeline still needs ffmpeg, Python 3 + Pillow, Node.js and playwright installed locally, your own Bilibili biliup credential and WeChat Channels / Douyin / Xiaohongshu login states, and the placeholder values under skills/*/scripts/ filled in with your own. An installer's own skill of the same name keeps precedence.

Project board, task schedule (gantt) and project memory: sessions opened from a card auto-load the latest project STATE; persisting progress without losing facts needs python3 and is unavailable on Windows.

NeatMem long-term memory plugin for DeepSeek Harness — thin REST client against a neatmem server

Python LSP configuration plugin for DeepSeek Harness using Pyright.

Cron scheduler with a sidebar UI: run shell, Python or Node scripts, skills, or agent tasks on a schedule, with push notifications and session archiving.

DSH Director Toolkit is a DeepSeek Harness plugin for 3D artists, technical designers, and creative coders. Paste a half-formed idea, a reference note, or a portfolio caption and get a compact direction pack for Blender, Three.js, Houdini, or C4D.

One shared Obsidian vault for every agent: dependency-free Python core (search/promote/adjudicate/forget), vault template, dsh plugin (memory_search/show/submit/status).

Long-term memory written by the character itself. A sorting plugin watches the workspace and, once conversations have been quiet past a threshold, opens its own session to run the bundled extraction script and turn the recent exchanges into memory files; a heartbeat plugin later re-opens sessions on a probability curve that rises with the time since the last exchange, with quiet hours and a random delay. Ships the memory templates, the sorting guide and the extraction script. Needs Python 3.8+ with zstandard, plus manual setup after install (a preset with agent-instructions, templates copied into the workspace, defaultPreset/sortPreset set to real preset ids; a wrong id fails silently with one log line). Plugin-opened sessions run with full permissions by default. Tested on DSH 0.2.0-rc.2.

AI companion skill for DeepSeek Harness: persona configuration (8 presets + custom), six-type long-term memory, emotion recognition and feedback, and multi-turn emotional conversation with tone post-processing. The skill body must be placed in the agent's skills directory (~/.dsh/skills/love-companion/SKILL.md), and the persona/memory pipeline runs on a local Python 3 (standard library only).

Zotero skill for DeepSeek Harness: page-anchored Q&A, full-text translation and close reading, native highlights and Chinese notes, bilingual PDF and paragraph Markdown, evidence comparison tables, and reviews with citation tracking; finds papers on OpenAlex or Crossref, imports Chinese CNKI export files, classifies the library into research-direction folders, surfaces research gaps, and runs a ranked daily digest of new papers. Python-based (basic library management uses the standard library; the reading workflow downloads its PDF/OCR components on first use); writes need a one-time Zotero authorization, and daily scheduling is Windows-only. Adapted from the OpenAI MIT Zotero plugin.

Long-term memory for dsh via a local Hindsight service: each turn is retained with local timestamps and relevant memories (time-aware, reranked) are recalled into context before replies; each workspace binds to one memory bank, several workspaces can share a bank, and banks can have Chinese names; what gets retained is configurable (default: user messages and AI replies); history is imported only when you choose to; includes a three-step setup page with one-click local deployment (uv + Python 3.12), a sidebar status card and a panel to browse and search memories. Needs a SiliconFlow API key for the default embedding and reranker models; only Linux is verified so far.

Make your dsh ready for serious coding. (Tools x Schemas)^REPL. `skill://`, `ctx://`, `agent://`, `dvc://`, `dsh://`, IPython REPL, Context as Variables, cross compactions recallable, full context revive. `hash-edit`, `dvc://browser`, subagent as function, workflow as function.

Make your dsh ready for serious coding. (Tools x Schemas)^REPL. `skill://`, `ctx://`, `agent://`, `dvc://`, `dsh://`, IPython REPL, Context as Variables, cross compactions recallable, full context revive. `hash-edit`, `dvc://browser`, subagent as function, workflow as function.

macOS desk pet that lives outside the DSH page: a real always-on-top window that clears fullscreen Spaces, six states driven by local DSH, a native right-click menu with quiet mode and a session list, and a bundled skill that turns one photo into a full eighteen-pose skin on your own image tool and credentials; system Python and ctypes, no Electron and no dependencies.

Code intelligence for the DeepSeek Harness IDE workbench: local and semantic completion, go to definition, find usages, hover and signature help, plus the TypeScript, Python, Java/JDTLS and YAML language servers with their memory budget. Requires the dsh-ide-workbench plugin.

Read PLC projects inside DSH — decode CoDeSys .project and Delta .dvp (both need Python 3.9+ on PATH) and Siemens S7-200 SMART .smart/.smartlib into readable reports and structured data, plus project diff, address audits, element-level read/write analysis and ladder-logic reconstruction.

Bilibili live-room danmaku for DSH: read live chat, send messages only after explicit confirm, hang out in a room in the background, optionally let the model decide whether to reply, and optionally transcribe stream audio to text; no video understanding. Setup needs a Python 3 venv with the bundled requirements plus Bilibili cookies; transcription additionally needs ffmpeg and a Whisper engine.

Connects DeepSeek Harness to a local SolidWorks install through an MCP server, with a read-only default mode and per-call confirmation for high-risk operations. Windows 10/11 x64 only; needs Python 3.10+ x64 and a local SolidWorks desktop (README: 2020-2026, verified on 2026) started at least once; npm run setup builds a local .venv with the Python packages and registers the pywin32 COM components. On start, if the Python interpreter it finds lacks mcp or pywin32, it creates a plugin-local .venv and runs pip install for them automatically inside that .venv (Tsinghua PyPI mirror, pypi.org as a second index) unless pythonPath is set.