Plugins

A skill picker beside the composer that lists installed skills under Chinese categories, searches them by name or purpose, and suggests up to three skills matching the draft you are typing.

Imports skills from a local Hermes Agent installation into DSH. It scans the Hermes home directories and each profile below them, lists every skill with its description, file count and size, and copies a selected skill into the DSH global skills root or into one project, keeping the original folder name. Only a frontmatter name that DSH would reject is rewritten, an existing skill of the same name is never overwritten without a choice, and several skills can be imported in one batch with a per-item report.

Model-facing skill_manage tool that saves, replaces, or deletes Harness skills at user or project scope, with a standing system-prompt section that asks the model to evaluate skill retention before ending a reusable task.

Self-contained DSH profile plugin that bridges the cua-driver 0.46.1 Windows kit into DSH as about 63 cua_* background desktop and browser automation tools (UIA observation, PostMessage input without focus stealing, CDP browser control, agent-cursor overlay, recording and diagnostics), with a bundled /cua-driver skill. Windows x64 only; bundles the prebuilt cua-driver.exe and starts it with --grant existing-profile, so the tools can attach to your already-running Edge or Chrome profile and act in its logged-in sessions.

Running panel for dsh for skill management and visualizing skill calls: live skill and tool calls, the skill-catalog token budget against a line that follows the model's context window, a skill loadout window that enables and disables skills in bulk with dry run and undo, goals and ideas, and saved conversation excerpts. Applying a loadout moves skill folders between ~/.agents/skills and ~/.agents/skills-parked, which other apps share (dry run first, undo available); automatic translation, goal inference and idea collection call your default model only after you opt in on first open.

dsh bundle for TSM / DLR: MCP semantic gateway to tsm-core-dlr, the scenario-independent paradigm skill, the TSM status overlay, and the agent rules (AGENTS.md). Assembly face = preset-dlr.

Onmyoji game helper with five tools: shikigami and soul lookup, skill text, crit and panel math, NetEase Dashen guide search, and intro card paths.

Inspect plugins and Skills in the running DSH profile, preview updates, record verifiable snapshots and offer recovery only when replay evidence is available. Requires Node 22+ and DSH 0.2.2-rc.1 or a later declared-compatible host. Restoring a plugin version does not restore configuration, its complete dependency tree or agent presets.

Community fork of l246804/dsh-pstack (cannot be installed alongside it: same plugin ids and tool names) that ports the pstack workflow system to dsh: 58 skills, five presets, a bundled script runner that works without node on PATH, a doctor for script prerequisites, and a translation layer for the remaining Cursor vocabulary.

Compose two skill contracts into a traceable, unverified draft with declared gaps and preserved constraints; the composition engine runs locally with no model call.

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.

Per-workspace skill visibility: each workspace binds one named switch table, so which skills the model may call on its own follows the project instead of every installed skill being listed every turn. Cannot be installed together with dsh-skill-scope.

Paper reading in a DSH sidebar tab: the PDF keeps its original layout and fonts, a selection becomes a highlight, a note or a question in the current chat, and annotations plus paper-level notes are mirrored to Markdown in a per-paper folder that also holds the parsed text and the linked open-source code. Ships a `vibe_reading` tool and a reading skill so the agent can build that record itself.

Adds the MathWorks MATLAB Agentic Toolkit skills and the MATLAB MCP Server tools to DeepSeek Harness. Needs a local MATLAB R2021a or later. Installs from the plugin's own prebuilt release archive. A DSH restart is usually unnecessary: the market mounts the plugin live, and a page refresh shows the MATLAB settings page; restart only when the market reports that the live mount failed. By default (autoProvision) it downloads the MathWorks MCP Server binary and installs the newest Agentic Toolkit release on first use. With the China download region or a configured GitHub prefix, both are fetched through the fastest measured acceleration prefix first (the plugin's own, DSH's market setting, or the built-in gh-proxy.com and ghfast.top routes) and then directly. The downloaded server binary is verified against the SHA-256 digest GitHub publishes for its release asset when the release metadata can be read, and a mismatch refuses the install; if api.github.com cannot be reached the digest is read through the same mirror, so the check then only catches a corrupted or truncated download. MathWorks telemetry is disabled by default; set disableTelemetry to false to re-enable it.

Chinese accounting and tax knowledge base for DSH agents, served by the hosted Quaesto service at api.accountingllm.site (needs network access; no account or API key, but your queries leave the machine): answers questions on CAS enterprise accounting standards, the small-enterprise accounting standards, CSA auditing standards and tax law with original articles, decision procedures, applicability checks and tax-accounting differences, exposed through 10 MCP tools and a china-accounting-standards skill.

Per-session control of which skills and MCP tools/servers the model can see (built-in tools are untouched): default shows everything, auto asks the model each turn what to keep, smart picks from your saved groups, or tick groups by hand, with a switcher under the composer and fail-open to full visibility on any error. The default state is auto, which adds one model call per turn (the session model unless judgeModel is set).

Registers a battle-tested development delivery rulebook as a skill family - one core skill (clarification, delivery checklist, navigation) plus nine focused skills (layered architecture, evidence-driven debugging, minimal changes, impact-graded verification, migration feature parity, async UI feedback, sizing rules, CLI safety and cleanup, project notes). Only the skills matching the current task are loaded, trivial tasks (small reversible single-file edits) are exempted outright, so each session pays tokens just for the rules it actually uses.

Context control for DeepSeek Harness: inspect token usage across request and conversation; switch skills, MCP servers and plugins between loaded, brief and hidden per session; toggle prompt sections and tools; compact on demand or at a configurable 5–95% threshold.

A WeCom WeDrive picker for the DeepSeek Harness composer: a draggable floating window with list, column and gallery views, search, sorting and multi-select inserts selected files, documents and folders as official `@` reference chips. Data comes from a local wecom-cli with the official doc.weixin.qq.com selector as fallback, and a bundled wecom-wedrive-ref skill routes the chips to the matching wecomcli-* document readers.

Closes the gap in batch-searching CNKI (知网) literature with an agent: the academic research preset reads CNKI Space metadata, maps each link to the openable kns.cnki.net record page server-side (no login state and no browser redirect script; full text depends on institutional access), and adds arXiv, PubMed / Europe PMC and Semantic Scholar for English literature; the download-paper skill turns the results into one topic directory with an offline HTML index, XLSX table, BibTeX, RIS and an arXiv batch-download script. Requires DSH 0.2.2-rc.1+, uv and Node.js. Requires DSH 0.2.x, uv (the CNKI, arXiv and Semantic Scholar MCP servers start through it) and Node.js (PubMed starts via npx).

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.

Manage Claude Code, Codex and Grok CLIs inside dsh and dispatch tasks to them as headless subagents, with dsh models, skills and tools bridged into each task, resumable CLI subsessions, and a hierarchical task board in the right sidebar (the board tab requires the separate DSH-better-sidebar plugin; without it the tab is not registered).

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.

Skill that switches the displayed reasoning to Simplified Chinese: it enables the built-in experimental reasoning translation, pins provider bing and target language zh, then verifies and troubleshoots the result. The same repository also ships an optional one-install preset plugin for users who want the same setup without running the steps. Requires the DSH 0.2.1 line with the experimental reasoning-translation bundle and a Web or Desktop GUI; the default provider is bing, so expanded reasoning text is sent to Bing.