Model Switcher：在 DeepSeek V4 Pro 与 V4 Flash 间切换会话模型
Model Switcher（@user_346b2eef/deepseek-model-switcher，v1.0.0）是 SkillHub 社区 ai-agent 类 Skill，通过 SKILL.md 指导 Agent 在用户说「切 Pro/Flash」等意图时，用 session_status 在当前会话切换 deepseek/deepseek-v4-pro 或 deepseek-v4-flash，不改 default_model。requires_api_key=false。安装：skillhub install deepseek-model-switcher --namespace user_346b2eef --dir 对应 Agent skills 目录。适用于支持 session_status 的 DeepSeek Agent 环境。
Read More免费大模型 Skill：发现、对比、配置与切换
SkillHub 社区技能「免费大模型」（@user_ad872d55/free-model，v3.1.1）面向在 Cursor、Claude Code 等环境中频繁试用免费大模型的开发者。它提供发现与对比、多维排名评分表、按场景推荐最佳模型，以及配置与一键切换，并用自然语言触发（如免费模型、切换模型、模型排名等）。安装需按 skillhub.cn 文档使用 skillhub CLI，并将技能装到对应 Agent 的 skills 目录；标签 requires_api_key=false。本文依据 SkillHub 官方页面与安装文档整理步骤与适用注意，不编造未公开的配置细节。
Read Moredsh-model-quickslots：在 DSH 输入框上方一键切换模型预设
MoruTeaven 维护的客户端插件 @moruteaven/dsh-model-quickslots，在 DeepSeek Harness 的 conversation.input.dock 插槽于 Composer 上方展示模型预设按钮。每个预设保存 provider、model 与 reasoning effort；左键切换当前会话，右键编辑，支持自定义标签，下拉来自实时模型目录，失败时按钮变红，数据存于 localStorage。推荐通过 pnpm add 加入 dsh.profile.bundles 或在 Settings → Plugins 安装。MIT 许可，适合频繁切换模型配置的开发者。
Read Morexiaolongxia-model-switcher：在主流大模型之间切换且保持龙虾记忆
xiaolongxia-model-switcher 是 SkillHub 社区 ai-agent 技能（v1.0.0，@user_8e65e202/claw-converter），简介称支持主流大模型之间相互转换且龙虾记忆不变，标签 requires_api_key=false。文章说明其定位、可核实功能，并给出按 skillhub.md 安装到 Cursor、Claude Code、Codex 等 skills 目录的步骤与注意事项，不编造未公开的模型列表与用法示例。
Read Moredsh-provider-toggle: One-Click Toggle for DSH Model Providers
The `dsh-provider-toggle` plugin provides DeepSeek Harness with a one-click feature to enable or disable model providers, eliminating the need for tedious manual configuration changes. It adds a toggle in the “Settings → Models” interface, allowing users to quickly switch model sources without modifying core files. After installation, turning the toggle off hides the provider, while turning it on restores its display. To install the plugin, fully exit DSH and restart it to load the feature.
Read MoreDSH Model Controller: Switch Models, Adjust Reasoning Intensity, Favorite Models, and Reorder Providers
The DeepSeek Harness plugin (DSH) adopts a plugin-based architecture and takes over the model slot to enhance model selection. Its core features include searching, filtering by provider, favoriting frequently used models, and adjusting thinking intensity. The thinking intensity level has per-model memory and automatically restores the corresponding level when switching models. For installation, download the `.tgz` file and install it via the host; the plugin will automatically take over the official selector. It supports integration with Magpie and has fallback interface configuration capability. Data is stored locally on the client; preferences are retained after uninstalling and reinstalling. It is compatible with DSH 0.1.7-rc.2 and Cordis 4.0.4.
Read Moredsh-model-switch: Toggle Model and Thinking Strength with a Single Key Press
The DSH global plugin dsh-model-switch allows users to map any physical key (such as F13–F24 or a Bluetooth numpad) to a specific model and thinking intensity combination, addressing the inconvenience of frequent switching. It supports visual entry, real-time key monitoring, synchronization with the official model list, and includes built-in diagnostic tools. Once installed, users can trigger switching directly via peripheral keys without any pop-up interruptions. Currently, data is stored only in memory, with persistence planned for the future.
Read Moredsh-client-ui-model-switcher: One-Click Provider and Model Switch Plugin for DeepSeek Harness
This plugin is specifically designed for the DeepSeek Harness (DSH) Web GUI to address the inefficiency of frequently switching models. By adding a slider button to the session title bar and offloading model selection logic to the client side, it enables one-click switching. Core features include two-level cascading selection of providers and models, configuration filtering (displaying only providers with configured keys), state synchronization, and error notifications. The plugin relies on pure browser-side technology, subscribes to the `modelDirectories` state to stay consistent with DSH’s internal state, and automatically disables the switching feature in sub-agent sessions. The install command is `dsh plugin --profile web add github:2275803244-cpu/dsh-model-switcher`.
Read MoreDSH Model Presets: Save and Switch Models and Reasoning Effort in DeepSeek Harness
DSH Model Presets is a DeepSeek Harness plugin maintained by Zding89, designed to eliminate the repetitive manual adjustments of model and reasoning-intensity combinations. The plugin uses local storage to save configurations, allowing users to save frequently used combinations as presets and switch to them with a single click or a keyboard shortcut (Alt+1–9) at the top of the model list. Core features include adding, renaming, reordering, deleting presets, and searching for models. It supports up to 50 presets, stores them only in the current browser, and is compatible with DSH 0.1.0-rc.7 or later.
Read MoreDeepSeek Harness Peak-Hour Automatic Model Switching Plugin
The `dsh-peak-avoidance` plugin aims to address high inference costs during DeepSeek Harness (DSH) peak periods. It uses a scheduled automatic switching mechanism to activate more cost-effective alternative models before peak periods and restore the official model afterward. The plugin supports dual routing, multiple time slots, and dynamic retrieval of model lists, while also providing manual control and safe recovery features. The author notes that the code has not been audited, and installation steps must be tested independently.
Read Moredsh-smart-router: DeepSeek Harness Smart Model Routing Plugin
The `dsh-smart-router` plugin implements intelligent routing via a virtual model, automatically switching to configured models based on request complexity and visual requirements without manual intervention. Core features include difficulty-based routing (hard, normal, and easy tiers), automatic image detection to invoke a vision model, and two classification modes: heuristic or LLM-based. Configuration requires specifying the model for each tier and the visual mode (replacement or pass-through), and it is recommended to use models from the same provider to optimize caching. The plugin supports a fail-open fallback mechanism and can coexist with existing vision plugins.
Read Moredsh-nl-model-switch: Switch DSH session models with a single sentence in the conversation.
# Introduction In DSH, switching models is done natively by typing `/model` and selecting from a popup. While this workflow is acceptable on desktop, it interrupts the flow in two scenarios: first, when you chat with the model via an IM bot on your mobile device, you lack a panel to click on; second, when you are in the middle of a discussion and want to hand off the remaining task to another model without leaving the chat interface. `dsh-nl-model-switch` fills this gap: simply say "switch to deepseek-v4-flash" in the chat, and the current session's model switches immediately, preserving the context so the new model continues processing your previous request. # What is this `dsh-nl-model-switch` is a DSH host plugin created by passi.
Read Moredsh-plugin-model-switcher: Switch models and reasoning levels in DSH using keyboard shortcuts
# Introduction During agent development, frequent comparison between different models is often required: running a task with the current model and then switching models to compare results, or adjusting reasoning levels based on task complexity. Manually opening the model selector, selecting a model, and adjusting levels repeatedly is quite tedious. DSH's philosophy is "everything is a plugin," making high-frequency, small operations ideal for plugins. The `dsh-plugin-model-switcher` introduced below is exactly that: it adds two sets of keyboard shortcuts to the DSH web client—one for switching models and one for switching reasoning levels—accompanied by toast notifications to confirm each action. # What is this `dsh-plugin-model-switcher` by Mrlilil
Read Moredsh-model-preset: One-click model combination switching above the DSH Web input box
# Introduction When developing agents using DSH (DeepSeek Harness), switching models requires confirming three dimensions: provider, model, and reasoning effort. In daily operations, I often toggle between "fast results" and "deep reasoning" configurations, requiring the opening of the built-in model selector and manual re-selection of items each time. If common combinations could be fixed as buttons, a single click would complete the switch, saving this repetitive operation. The `dsh-model-preset` introduced below does exactly that. # What is this? `dsh-model-preset` is maintained by kaixinbaba (repository: kaixinbaba/dsh-model-preset), licensed under MIT, current version...
Read Moredsh-model-switch: Selecting appropriate models for DSH sub-agents and plan execution
dsh-model-switch is an MIT-licensed plugin for DeepSeek Harness (DSH) designed to address the tedious process of model switching across main sessions, sub-agents, and plan execution phases. This plugin allows users to retain the current model of the main session while separately configuring suitable models for sub-agents or plan execution, supporting two modes: "Follow Main Model" and "Custom" (including reasoning effort). By saving default settings, it reduces the manual switching cost prior to tasks; in the plan approval panel, users can directly confirm or modify the execution model, which is automatically restored to the main session model upon completion. The plugin displays detailed information such as the sub-agent's model, context window, and reasoning effort. Installation requires adding it to the web profile via a specific command and restarting DSH, requiring DSH version 0.1.1-rc.2 or higher and a specified Node.
Read More