Plugins

Eight academic skills bundled for one-command install — publication-ready academic figures designed from real data with visual review, AI-text humanization, paper polishing and rewriting, PubMed citation verification (DOI/PMID reconciliation), Chinese citation and medical-book reference checks, and WeChat medical article structuring. Three skills run fully local, five call external services only when used (NCBI E-utilities, DOI resolvers, publishing platforms), declared per skill. Zero telemetry, no install-time scripts. Skills run local Python 3.8+; the academic-figures skill also needs its pip dependencies installed.

All-media (video/audio/image) sibling of liustack/modlens: turns local media into structured evidence (timeline / transcript / layout regions) injected into the conversation so text-only models can cite concrete frames, seconds and speakers — Evidence, not imagination. One failover chain per media, recorded hop-by-hop in meta.attempts (a fallback is never silent): host-registered multimodal models first, then a configured OpenAI-compatible endpoint (comma-separated multi-key rotation), then local ffmpeg frame-sampling / a local ASR CLI, degrading to metadata-only as a last resort. Absorbs modlens battle-tested rules — cooldown keyed only on auth/quota failures and softened to chain-tail (never dropped), redact-before-clip error text, magic-byte sniff that never trusts file extensions. Optional vision-bridge registers a media-lens wrapper into the host model selector so a pure-text model gains image/audio/video sight. Registering / authenticating multimodal models and true inline audio-video upload lean on two companion plugins, declared as optional peers (absence auto-degrades, never errors): dsh-thinking-levels fronts the model config / registration surface, dsh-llm-openai-completions takes over the OpenAI-compatible transport that serializes file blocks into video_url / input_audio. Privacy: media goes to remote providers by default; strictLocalOnly keeps content on-machine. Prerequisites not shipped with the package: ffmpeg/ffprobe on PATH (frame sampling / reencode / duration probe; degrades to metadata when missing) and a user-configured local ASR CLI for the audio fallback. Hosts 0.1.7 / 0.2.0 / 0.2.1 (6 rc, exact engines.dsh enum). npm: dsh-media-lens.

Browser and desktop application control with live previews, annotations and native Hyprland support.

Game asset production pipeline: generate images, video and audio, turn a video into a coherent sprite animation, derive recoloured variants, adapt assets to an engine schema, install them into the project and verify the code actually references them. Requires ffmpeg for the video-to-sprite path, and an image/video API key (Agnes AI / OpenAI / fal) for generation.

Astronomy research workbench for DSH and Codex: NADC terms, reference library, writing, scoring, author confirmation, recommended books, FITS/XML formats, and analysis guides.

A DeepSeek Harness (DSH) plugin that lets you control Universal Robots (UR) collaborative arms directly from natural language — by default an offline, kinematics-level simulated arm, with a real-robot channel that stays off until it is explicitly enabled. Needs a Python install with numpy and paramiko (pip install -r requirements.txt). Developed by Suzhou Nonead Robot Technology Co., Ltd. based on the same logic as the company's own nUR MCP Server. (Suzhou Nonead Robot Technology Co., Ltd.)

OpenCode free models for DSH with dynamic model-list refresh, optional HTTP(S)/SOCKS proxy failover, a fail-closed tool bridge and offline agent-scoped compatibility auditing.

Community-maintained WorkBuddy and WorkBuddy AI model provider using local desktop sign-in, with model discovery and credit display. Version 0.1.12 supports per-model context-window selection and DSH 0.2.1-rc.2, rc.3 and rc.5; its CN compatibility layer differs from the functy23 fork. Derived from corrinehu/dsh-workbuddy-connect (MIT), it registers the same workbuddy / workbuddy-ai provider ids, so it cannot be enabled together with the original or other WorkBuddy bridges. Version 0.1.12 requires authenticated Host owner access for status and control routes.

Brings the free models of a locally installed OpenCode CLI into DSH: starts or reuses a local opencode serve, discovers the live catalog and refreshes it every five minutes, and bridges the session event stream to OpenAI-compatible SSE through a loopback-only shim that validates Host and Origin.

Claude Design System theme for DeepSeek Harness: warm-grey surfaces and a clay accent, refined composer, sidebar, code blocks and Markdown, localized edit/write cards with workspace-relative paths, and an ASCII ocean on the blank-session page with three whale colour modes.

Replaces the composer's model and reasoning-effort selector with a two-level menu and six slider skins.

The real ComfyUI editor as a sidebar tab in DeepSeek Harness, with per-session tools that read and edit the graph on screen and a panel that can start, stop and restart ComfyUI without installing anything into it.

Next-prompt suggestions: after each answer it predicts your next message as grey ghost text in the composer. Tab fills it without sending, and the prediction model is selectable.

Long-term memory for DSH stored as plain Markdown. Real user/assistant exchanges are captured into daily session files without a model call; an LLM pass then distils them into memories that are injected into the system prompt each turn. Retrieval is local (CJK bigram + BM25) in three levels — index, summary, full text — so the model only pays for the detail it asks for. Memories carry priorities; P0 and user-written entries are never changed automatically, and forgetting marks an entry stale instead of deleting it, so the whole chain stays auditable in status.md. Six tools cover recall, write, status, extract, feedback and the skill library; when a cluster of memories is ready to become a skill, a card appears at the end of the turn, writes the SKILL.md on click, and installs it only after you approve. Learning is on by default and follows the conversation model; turning the master switch off stops the LLM entirely while capture keeps working. Failures are surfaced in the prompt and in status.md instead of being swallowed. Pure JavaScript, no third-party runtime dependencies beyond the harness packages.

Interactive character for Harness Desktop with task expressions, rice feeding, an iron-basin hat, dragging, and time-based greetings.

Plugin index inside DSH that lists over 10,000 third-party plugins checked against the dsh.bundle manifest in their package.json rather than by star count, with one-click install and a companion website.

Desktop notification and sound when a turn completes, the agent asks a question, or an approval is requested, each independently toggleable, plus an activity ball that lists live sessions and jumps back to one.

Browse, preview and install public Agent Skills from inside the DSH web GUI, aggregating five sources (claudeskills.info, skillsmp.com, the awesome-claude-skills repository list, the official anthropics/skills repo, and skill packs shipped by installed DSH plugins). Skills install pinned to a commit rather than a branch name, so what you previewed is what lands; the panel reports provenance, whole-tree update checks and a trash instead of deleting. Before writing anything it validates the skill name and frontmatter against the rules the harness silently enforces, lists files that SKILL.md references but the fetch did not bring, flags partial fetches, and offers overwrite, rename or skip when a name is taken.

Pulls GitHub repo content into DSH conversations at start and writes extracted long-term memory back with SHA-locked multi-file commits at conversation end; per-file read/write permissions, native settings page, turn indicators and global change notices.

Preview conversation context and selectively keep, summarize, or omit exchange groups before applying persistent compaction through Harness session services.

A plugin to completely delete sessions and clean up the associated files in the .dsh/sessions directory.

Set an earlier automatic-compaction threshold per model on DeepSeek Harness: /autocompact writes a session-only override keyed by exact provider/model (off falls back to the backend defaults, default clears it), a Settings → Autocompact page manages the persisted per-model thresholds every session inherits, and a composer status entry shows the current reading.

A Neon Genesis Evangelion-inspired skin for DeepSeek Harness: Title Card (light) and Central Dogma (dark) modes over one removable override layer, 55 measured color tokens, a wallpaper paint layer whose two surface alphas are solved against a WCAG contrast budget, a boot mask and a brand mark. It also rewrites the sidebar identity line, replaces the new-session heading, hides six official entries, and reshapes the composer control row. Unofficial fan work, non-commercial: the background pictures are fetched from third-party URLs at paint time, not shipped in the repository.

Per-turn session cost chip in the composer stats row: each turn's spend with the model it used, the conversation total split into cache-hit and cache-miss (CNY), priced from an official price table that refreshes on demand.