Plugins

Requires DeepSeek Harness 0.1.5-rc.1+ (DSH Desktop >= 2.0.7) and dsh-better-sidebar >= 0.19.0 - update both before installing or updating this plugin. Plays local Wallpaper Engine Video/Web wallpapers behind the chat, renders Scene wallpapers as extracted static frames, and adds content-rating/type filters, custom uploads and an iOS-style liquid-glass settings window.

A live iOS Simulator or USB-connected iPhone inside the conversation: 22 agent tools for booting, building, driving the UI by accessibility identity or OCR text, list-row actions and SwiftUI preview hot reload, plus a streaming sidebar panel you can tap and drag on.

Authenticated mobile gateway for DeepSeek Harness: connects the companion native iOS client over WebSocket for sessions, live events, tasks, goals, approvals, commands, and file transfers, with QR pairing and device revocation.

Runs Midscene on the models already configured in DeepSeek Harness instead of separate third-party API keys: hosts an OpenAI-compatible bridge on 127.0.0.1 (default port 8787, automatically skipping occupied ports) that proxies chat completions, streaming and non-streaming, to the DSH host model layer, so DeepSeek official routing, CodeBuddy, Codex and custom OpenAI/Anthropic endpoints all become available to Midscene agents while credentials stay inside the provider plugins and the bridge never touches them. A `/v1/midscene-env` endpoint generates the four MIDSCENE_MODEL_* environment lines with the model family inferred, and seven built-in skills — browser, desktop, Android, iOS and HarmonyOS automation plus a Vitest E2E skill and a Midscene knowledge reference — appear in the session skill catalog without `npx skills add`. Install from npm with `dsh plugin --profile web add @tnnevol/dsh-midscene`.

Use the dsh web UI on your dev machine from an Android or iOS phone, connected peer-to-peer across networks via iroh; no server to set up, with a relay fallback that only carries ciphertext.

Mobile-first UX polish for the DSH Web UI: composer auto-fold, enter-as-newline on phones, compact sidebar/header/settings, zoom and overscroll lock, plus approval/question/completion notifications via in-page cards, Web Push, and webhook — zero dsh changes.

Image generation and image reading for DSH: an Images page in the sidebar, labelled 图像 in Chinese (one row per model, 10 ratios, 1K–4K sizes, a contact sheet with detail cards, zoom, reuse and delete), three preset providers plus custom endpoints — one needs no key at all — and a vision-review skill. A pasted key is written to ~/.dsh/secrets/media-tools.env (mode 600) and only sent to the provider you picked. The page follows the harness language (Chinese or English). Requires Python 3.9+ (generation runs through scripts/generate.py); the page needs desktop DSH 0.2.1+.

DeepSeek Harness port of Claude Code Game Studios (CCGS v1.1.2, MIT): 76 skills, 49 agents, hook bridge.

AI image and video studio as a floating DSH panel, so creation runs alongside the conversation instead of replacing it: text-to-image, image-to-image and multi-image composition at 1K-4K across eight aspect ratios; text-to-video and image-to-video with first-frame control at 4-12 seconds; short-drama mode that imports a script (.txt/.md/.json), breaks it into storyboard shots for preview and batch generation; and a prompt-expert workspace. Zero runtime dependencies.

Native iOS and Android apps for remote control of DeepSeek Harness, with end-to-end encryption, workspace browsing, and real-time session updates.

Host-side connector for the DSH Mobile iOS app: dials a self-hostable WSS relay so the phone can reach the DSH sessions on this computer over 4G/5G, without a public IP or a VPN; the relay only authenticates and forwards.

Reverse-engineering preset for DeepSeek Harness: domain skills live inside one "reverse mode" and the model routes by target type (web/JS, Android, iOS). The JS domain ships three skills (AST deobfuscation, controlled iv8 execution, JSVMP recovery) and mounts the js-reverse-mcp browser forensics server as mcp__js-reverse__* tools.

Eleven game-development agent presets cut by workflow stage — concept, design, build, art and audio, QA, release, narrative, level, engine — plus one orchestrator that delegates across them, carrying 37 bundled skills. Regroups the 48 agent prompts of Claude Code Game Studios (MIT) by stage so each preset loads only the skills its stage needs. Installs with dsh plugin add; run node install.mjs once afterwards to deploy the skills the presets reference.

Enterprise AI resource platform as a 22-plugin cordis bundle: org/account/role IAM, OIDC provider and App SSO, MCP server management with the platform itself exposed as an MCP server, NAS asset storage, skill hub, agent and app registries, SaaS connector management, enterprise portal data channel, department agent workbench panel, DingTalk group bridging for message and approval push, one-click remote dsh enrollment with tool proxying, usage metering, wallet billing, model gateway, audit with alerts, self-update, and a reviewed third-party plugin marketplace — 70+ ops tools become callable by the dsh agent.

Rings your phone over CallKit: `call_me` and `text_me` tools, plus optional turn-end and approval calls whose spoken answer is transcribed back into the session.

Expert roster for DeepSeek Harness: 636 experts across 22 divisions with full Chinese names and bios, summoned as subagents from the @ menu or by the model through list_t_experts / summon_t_expert / summon_t_experts, plus custom experts and a skill on/off switch.

Brain-inspired cognitive plugin: episodic, semantic, procedural and emotional memory with reinforcement-learning signals, a goal stack with time triggers, curiosity-driven autonomous web research and proactive initiatives.

AI can write resume text, but templates may still look wrong, pages may overflow, whitespace may remain, and small edits can destabilize the layout. dsh-resume provides an end-to-end DSH workflow for truthful content refinement, template selection, A4 layout tuning, visual review, and tailored resume versions for different job-search scenarios.

Finance data toolkit for DSH agents: number and currency formatting (incl. Chinese wan/yi units), return and CAGR math, valuation and profitability ratios, PV/FV, risk metrics, and a data-quality checklist.

Use DSH from iPhone/iPad: an explicit-opt-in LAN reverse proxy (Host/Origin rewrite through the loopback trust fence, WebSocket upgrades included), iOS PWA chrome (home-screen icon, standalone meta, viewport-fit), and touch/mobile CSS (safe areas, keyboard lifting, composer row fit).

Observe and operate a connected physical iPhone with the iPhone-use CLI.

Multi-channel push notification plugin supporting Bark (iOS) and ntfy (Android/iOS/Web/Desktop) for turn completion, approvals, questions, and quota halts.

Bundles five TIA Portal skills (Siemens PLC docs lookup, ladder-logic generation, SimaticML-to-PNG rendering, scan-cycle simulation with PASS/FAIL scenarios, and a TiaLink gateway skill for driving a real TIA Portal project) and wires five MCP endpoints. Requires TiaLink (paid; Windows + TIA Portal V19/V20 + Openness) for real-project work, API keys for the four cloud services (100 free calls each, then paid; rendering is billed per call even on failure), Node 22+, and network access; program snippets are uploaded to tia.hubwiz.com.

Layered long-term memory for DeepSeek Harness: each turn injects a persona frame plus a relevance-ranked memory index while full transcripts stay on disk and are expanded on demand, so the vault never floods the context window. Facts are slot-keyed, so a changed mind retires the old value instead of recalling two contradictory answers. The persona frame is derived from memory by the model itself, behind three anti-pollution gates (rejecting development chatter, blocking echoes of its own injection, and merging restatements by shared content words). Periodic consolidation merges near-duplicates, rolls long topics into digests, and archives low-value old entries by tagging only — raw text is never deleted. The append-only store is compacted in place (measured 4.7 MB to 355 KB). Zero third-party dependencies, no build step. Note: per-turn injection inevitably lowers prompt-cache hit rates, so this plugin is not recommended for work scenarios.