DeepSeek Harness 플러그인 — 954 페이지

DSH 阅读舒适度:重建界面层级、按区块分区配色、给 AI 回答加说话人标识与引导留白。纯 CSS,不改布局。

DSH 本地阅读 + AI 陪读插件：导入本地 TXT、自动生成目录、按进度滚动阅读，并以「不剧透」的书友口吻陪你聊感想，把「原文摘抄—我的感想—AI 回应」写成结构化 Markdown 笔记。Local-ebook reader with a spoiler-safe AI reading companion for DeepSeek Harness (DSH).

阅读灯光

DSH 阅读板（Reading Pad）：沉浸式只读阅读面板——模型用 reading_pad_send 投递已排版 Markdown，用户在三主题/限宽排版界面阅读；better-sidebar tab 插件，Apache-2.0。

阅读时间

DSH 阅读工作台：书架、Markdown/TXT 阅读、划线批注与对话联动

README 生成：扫描项目（package.json、目录结构、技术栈、脚本、许可证），自动生成结构化 README.md

Generate a README.md for DeepSeek Harness (dsh) plugin repositories from package.json + cordis.patch.yml + source layout — deterministic, zero runtime dependencies, read-only by default. CLI + agent-callable readme_forge tool.

Turn a plugin repo's screenshots into a 6-second silent looping hero reel (transparent-background webm + gif + cover frame) for README first screens and plugin marketplace entries.

自适应 GitHub README 撰写与截图技能：先判断目标类型与截图能力——网页走浏览器截图，无网页的控制台/CLI 走终端截屏（System.Drawing / HTML 终端 / termtosvg），能则询问并自动配图，不能则走无截图模板；强调相对路径防丢图。作为 dsh 插件（cordis skill-bundle）安装后由 host 层注册 readme-writer 技能；SKILL.md 含可被插件商城索引的 name/description/keywords/category/version 元数据。

只读安全审计模式 · Read-only Security Audit Mode for DeepSeek Harness：系统级只读拦截、逐次写入审批、强制报告交付选择；适用于任意 Harness 检出 / fork。

DSH-RealFish-Pet 桌面宠物插件：在 dsh web 界面里自由游动的 3D 渲染鲸鱼宠物。任务完成/出错/待批准时播放 attention 动画与鲸吟音效；支持双击交互、原地睡觉、回家睡觉（右下角睡 5 分钟）、自由游动、拖拽与隐藏。

Provider-neutral full-duplex voice Agent capability for DeepSeek Harness.

Lightweight realtime speech-to-speech for DeepSeek Harness with Qwen and OpenAI providers.

Realtime Avatar (realtimeavatar.ai) for the DeepSeek Harness: the developer's API key held by the harness, the public docs as on-demand skills, rta_* tools over the public REST API, and a /rta command that walks a developer from no key to a live avatar call.

Orphan process and port reaper for DeepSeek Harness: find the dev servers, watchers and background processes an agent left behind, attribute them to a workspace, preview the blast radius, and reclaim the ports.

DeepSeek Harness per-model thinking-depth (reasoning effort) configurator: a settings-page section that auto-reads the configured models from llm-pi-ai and applies a per-model thinking level through the agent/request waterfall — all without modifying DSH itself.

Distill over-long model reasoning into its useful core and replay the distilled version on every later request, with a per-session cost report.

Add configurable thinking-strength (reasoning effort) levels to custom llm-pi-ai providers in DeepSeek Harness

Codex-style DeepSeek Harness model and reasoning selector with model-advertised effort levels, DSH-native themes, left-clipped radiation effects, and copy-ready reasoning-effort declaration guidance for custom-provider models.

Per-model reasoning-effort editor with embedded slider for DeepSeek Harness custom providers.

A draggable off / low / high / max reasoning-effort slider in the DeepSeek Harness composer model row, bound to the real per-session model selection.

Frontend-injected per-model reasoning-effort (thinking strength) configuration for custom pi-ai providers. Registers a per-model 思考强度 editor into the Settings -> Models provider card and persists reasoningEfforts through the settings Remote.

Codex-style reasoning-effort slider for DeepSeek Harness: turns the model menu's Effort row into a continuous, level-snapping slider.