Plugins

A green interrupt button beside the send box: silently stops a running agent, which then summarizes its progress and asks for your new requirements, with a customizable interrupt prompt.

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.

Lets the conversation AI maintain a plain-language functional requirements checklist in a dedicated session view. A non-official rebuild of Songran241/dsh-req-workbench that keeps the upstream package name; do not install it alongside the upstream original.

Work-data hub for DingTalk and Yunxiao: syncs todos, logs, meeting notes, attendance, schedules, projects, requirements, commits and worklogs into local SQLite, then renders dashboards, a work calendar, project analysis and reports, with workhub_* agent tools over the same data. Requires the DWS CLI installed and logged in (`dws auth login`); the Yunxiao PAT is stored in the macOS Keychain only.

Indexes public AI-company job boards (Greenhouse, Ashby, Lever, Workable, SmartRecruiters), scores postings for AI relevance, extracts the requirements from each job description, and produces a scheduled daily Markdown digest.

Bundled Pixiv skill backed by a Python CLI: search illustrations, manga and novels, browse daily/weekly/monthly/rookie/original/AI/R-18 rankings, look up works, novel series and artists, and download originals, with multi-page works merged into PDF, ugoira converted to GIF and novel series merged into TXT; requires Python 3.9+ with requests, img2pdf and Pillow installed (pip install -r requirements.txt), and R-18 content needs your own Pixiv cookie.

Auditable mathematical proving for DeepSeek Harness: a local stdio MCP server with 23 machine-checking tools, a bundled workflow skill, and the /prove and /audit-proof commands. proven, refuted and inconclusive are never conflated, and unproven steps are reported instead of hidden. Needs Python 3.10+ with pip install -r requirements.txt on first run; the 23 tools are unavailable until then.

Bilibili autopilot run by a local Ollama model: it picks videos within per-topic quota, reads subtitles, hot comments and keyframes, decides whether a reply is warranted, then writes and posts one comment through a five-level safety gate. Triggered by dsh-schedule; write tools are not registered while commenting is disabled. v1.1 hardens the write path: revoking write access is a runtime state checked before every send, publishing is atomic, risk-control errors persist as a pause, and the final post re-checks persona style. Needs Python 3.10+ with the repo's requirements.txt installed.

Checks a bid requirement by requirement against a tender requirements pack and reports which requirements appear answered, weakly matched or not located. It reports differences; it does not judge substantive compliance.

Four-tier prompt enhancer for the composer — the system tier always emits a LangGPT-structured system prompt (# Role / Profile / Skills / Rules / Workflows / Initialization), upgrading task drafts into the system prompt of the agent that runs them, while the other tiers rewrite as a light tidy-up, a single paragraph, or a five-section brief; the iterate workbench refines an editable base under an optional requirement, with fill-back and undo. Never changes intent, never invents requirements.

Provides a specification-driven engineering workbench with versioned requirements and documents, isolated Git workspaces, independent review, verification, and explicit human acceptance. Requires Node.js 24+ and Git.

Turns PDF, Word, PowerPoint and Excel files into Markdown or plain text with heading levels preserved where the source allows it, and refuses scanned PDFs that have no text layer instead of writing an empty file, naming the OCR alternative instead. Requires Python 3.10+ and pip install -r requirements.

Four-tier prompt enhancer for the composer — a button and a global shortcut rewrite the draft as a light tidy-up, a single paragraph, a five-section brief, or an eight-section system prompt, with a before/after panel, fill-back and undo. Never changes intent, never invents requirements.

Screenshot-review skill for DeepSeek Harness: the agent opens a frontend page, screenshots it, views the screenshot itself, revises the code, then re-screenshots — iterating until the page visually matches the user's requirements. Ships as a dsh.bundle, so it installs with `dsh plugin add`.

DSH Web 任务面板插件：把需求、队列、子 agent 执行、自动复核、验收返工和定时执行做成一个可视化闭环。

Compacts a session at 70% context and appends mechanically extracted anchors — first user message, hard requirements, paths, commands, error codes and unresolved items — to the summary; it reuses DSH built-in compaction-basic and adds a /compact-status command.

Local Kingdee Cloud (金蝶云星空) business portal for DeepSeek Harness: open the operations dashboard in the sidebar with your own Kingdee account; data stays on your machine. Needs Python 3.10+ with Flask and requests (pip install -r requirements.txt) and a local clone of this repo linked into the profile; verified on Windows with DSH Desktop only.

Hand off local development tasks between Codex and DeepSeek Harness with original requirements, project agreements, workspace checks, and a relay board. Needs the Codex desktop app (or a codexBinary path in the settings); verified on macOS only.

An agent preset that adds a working mode to DeepSeek Harness: the mode text has the model analyze requirements and plan before acting, open a gate document, and reply in a fixed three-block shape. The task tree and session-start profile injection are separate companion packages in the same repository, installed from a clone with scripts/install.mjs; only the term dictionary (dsh-term-dict) comes with this package, and without the task tree the model writes its own alignment bar. Needs DSH 0.2.1-alpha.1 or later.

DeepSeek Harness plugin: a Task Instructions button beside the input box pins reusable task requirements to a session, and the instruction survives context compression.

Elysia's memory plugin for dsh. One shared, human-editable MEMORY.md across every session: two-disk mirror, history snapshots, cross-process write lock; entries tier between the main file and a searchable archive by hit frequency; retrieval is keyword co-occurrence plus BM25. Nine sections (persona, requirements, corrections, lessons, methods, requests, sessions, method library, ingested docs) plus a dedicated self-identity section for a character's own self-cognition, injected above the persona. Ships an opt-in memory pack (packs/elysia: 61,903-char identity + 2,482-char persona, distilled from 1,696 officially-confirmed voice lines and checked against a 112,175-line game-dialogue corpus) that is off by default, backs up before writing, only touches identity/persona, and can be uninstalled. Also a skills library and a sticker library (you import your own images; none are bundled) that sends a fitting sticker at the right moment. On by default: a text bubble with her avatar after each reply, which costs one extra small model request unless the agent already announced (voice.bubble: false turns it off). Opt-in voice playback needs a local GPT-SoVITS engine (about 27 GB, installed separately, NVIDIA GPU required; the plugin downloads about 200 MB of weights) and is Windows-only; the automatic second-drive mirror is Windows-only too (elsewhere set mirrorPath, otherwise there is no mirror).

Adds a requirements-discovery gate before product selection, version choices and competitive analysis: 2–3 clarification rounds with 2–4 decision-changing questions, validation of real pain points and hard constraints, comparison of original, alternative and minimum-cost routes, and a confirmation card before research and copywriting. Confirmed reports keep the Xiaohongshu-style structure, concrete steps, audited images and source links. Ordinary lookups and explicit user skips bypass the questionnaire. Host-only static prompt sections with no config, client UI or dependencies.

Elysia's memory plugin for dsh. One shared, human-editable MEMORY.md across every session: two-disk mirror, history snapshots, cross-process write lock; entries tier between the main file and a searchable archive by hit frequency; retrieval is keyword co-occurrence plus BM25. Nine sections (persona, requirements, corrections, lessons, methods, requests, sessions, method library, ingested docs) plus a dedicated self-identity section for a character's own self-cognition, injected above the persona. Ships an opt-in memory pack (packs/elysia: 61,903-char identity + 2,482-char persona, distilled from 1,696 officially-confirmed voice lines and 112,175 dialogue lines — not written by hand, measured) that is off by default, backs up before writing, only touches identity/persona, and can be uninstalled. Also opt-in voice playback through a local GPT-SoVITS engine, a skills library, and a sticker library that sends a fitting sticker at the right moment.

DeepSeek Harness plugin: Aliyun Yunxiao requirements and defects kanban by status, with detail drawer, image preview, one-click session dispatch, Req/Bug creation, and native tools for status transitions, work item creation, project member lookup, change-