dsh-skills-mcp-group-manager
DeepSeek Harness Skills & MCPs Group Manager: group skills, filter the model skill catalog, toggle MCP servers, left panel UI
275 results
DeepSeek Harness Skills & MCPs Group Manager: group skills, filter the model skill catalog, toggle MCP servers, left panel UI
Show a local image or short video inside the current DeepSeek Harness conversation card, with click-to-preview. Does not replace the official read_image model path.
DSH web UI-tweak plugin: show the provider display name next to the model name in the composer model seat, remove the chat column max-width, and more — every feature has its own switch on a dedicated Settings page. / DSH web 界面美化插件:在模型选择器显示厂商名、取消对话列最大宽度等,每个功能都在独立的「设置 → 聊天增强」页中开关。
毒蛇复盘 (viper recap): roast — or toast — the current session from its real event log. A model tool + a viperRecap projection + a 🐍 composer button and floating card.
Out-of-tree dsh plugin: a git branch selector in the chat composer, immediately left of the model seat (current branch, fuzzy search, 5-row scroll, switch with conflict toast).
DSH plugin: detect long model thinking chains, segment them, and show per-segment summaries live in the chat UI, with a settings page.
DeepSeek API balance and local token usage dashboard for DeepSeek Harness
DSH Desktop Operator: safe Windows Computer Use, desktop automation, UI Automation, and MCP tools for DeepSeek Harness
Mid-turn user steering for DeepSeek Harness: /steer (visible) and /inject (quiet context notice) slash commands, a model-facing mid-turn guidance prompt section, and an always-visible injection bar above the composer.
Animated reasoning-level slider for DeepSeek Harness model selection.
濡€崇€风拹锔藉煕娴f瑩顤傞幃顒佽癁缁?for the dsh web GUI: floating model-account balance monitor with a Plugins-settings master switch. Supports DeepSeek / SiliconFlow / Moonshot / OpenRouter balance endpoints. Zero runtime dependencies.
Vendor logo seat in the DSH web composer: shows which provider serves the current model (DeepSeek / OpenAI / Anthropic / OpenCode / ...), live from the official per-session ModelDirectory.
DSH web plugin: splits the composer model selector into two independent controls — a searchable, favorite-marking model dropdown and a reasoning-effort slider — plus Ctrl+P (cycle favorite models) and Ctrl+T (cycle reasoning effort) shortcuts.
Windows/WSL environment switcher for the DSH web UI (coexistence model; mid-column sidebar entry, collapse-aware)
DSH plugin: session-header task estimator — estimated remaining time, token usage and per-model cost (≈CNY) with an optional LLM-powered estimate. / DSH 插件:会话标题栏任务估算窗口——预计剩余时间、token 用量与按模型花费估算(≈CNY),支持 LLM 智能估算。
Skill picker for the DeepSeek Harness web UI (dsh web): choose a skill from the composer tool row like the model selector, inserting the /skill reference into the draft.
Save and switch model and reasoning-effort presets in the DeepSeek Harness composer.
GLM Coding Plan quota and usage as a conversation view tab (额度) for DeepSeek Harness web: 5-hour/weekly token windows, monthly MCP tool quota, and per-model/tool usage over the Zhipu monitor API
dsh auto-vision bridge: paste an image into a text-only model's composer and a configured multimodal model transcribes it as text, automatically.
A lightweight plugin that adds model thinking token statistics to the bottom Dock and the end of each conversation.
Windows desktop shortcut that boots `dsh web` inside your WSL distribution and opens the browser: one double-click entry point for the DeepSeek Harness Web UI in WSL, plus a wsl_launcher model tool (install / status / open / uninstall).
Model and reasoning-effort switcher: composer seat with an Off/Max effort slider over session.models / session.selectModel
AI audio generation plugin for the dsh web GUI: multi-vendor TTS/music/sound-effect channels (OpenAI-compatible, ElevenLabs, MiniMax, Stability AI and custom), per-channel model/voice catalogs, Agent tool and a sidebar AI 音频 panel.
DSH web plugin: a draggable ring-gauge dashboard pinned to the bottom-right that shows live model output speed (tok/s), with an expandable detail panel (per-step exact speed, TTFT, cache-hit rate, cache read/write, reasoning and input tokens, model, cumulative tokens).