스킬 · DeepSeek Harness 플러그인 — 16 페이지

思维导图模式（dsh-mindmap）：把课件（PPT/PDF/Word）与电子书按「组胚思维导图」范例整理成打印级 HTML 复习思维导图——A3 横向、每主干知识点一页、大括号式横向布局、宋体大字不溢出、右侧留白笔记区、封面总览 + 交互式测试题。附带 mindmap-builder skill 与 mm_generate 工具。

Mobile bridge for DeepSeek Harness: forwards dsh/notify events (AI task start/done, scheduler, reminders) to Android system notifications via a queue file the native layer watches — works in background

OrbStack VM sandbox v0.4.0: 在 v0.3(安全/可靠性)基础上新增 A1 交互终端、A3 场景化一键创建、A4 删除撤销+完成通知、A5 配额一眼可见、A6 协作分组、B1 安全基线 vm_harden、B2 密钥库 vm_secret、C1 增强指标+阈值告警 vm_alert、D1 vm_scp/vm_logs/vm_env/vm_withdraw、D2 调度 UI+用量报表 vm_report、D3 导出分片/远端、D4 累计配额+创建排队。

JSONL durable session persistence backend for the DeepSeek Harness

Browser control: drives Edge/Chrome via the Chrome DevTools Protocol so the AI can automate the web (navigate, click, type, screenshot, evaluate JS). Settings live in the 'browser-control' namespace with a /api/browser status surface

Model-facing clipboard tools: clipboard_read and clipboard_write over the OS clipboard (PowerShell Get-Clipboard/Set-Clipboard on Windows)

Computer-use for DeepSeek Harness: control the Windows PC via Windows-MCP, provisioned with a bundled uv and an isolated Python runtime under $DSH_HOME/runtime

Deliver AI artifacts to the user: model-facing send_file tool copies a produced file into <files>/deliver and emits dsh/notify (kind=deliver) so the mobile native layer can offer one-tap save to Download/DeepSeekHarness

Model-facing file_name_search tool: fast recursive filename (glob substring) search under a directory, ignoring node_modules/.git

Long-term memory for DeepSeek Harness: remember/recall/list/forget tools plus a memory skill, persisted under $DSH_HOME/memory/memory.jsonl

Task notifications + scheduler for DeepSeek Harness: Windows notifications when the AI starts/finishes a task, plus user-defined repeating scheduled tasks with optional commands, driven by the `notify` settings namespace

Phone control for DeepSeek Harness mobile: model-facing tools let the AI read the current screen's interactive elements and tap / swipe / type / press keys / scroll / open apps through the native accessibility service (local HTTP bridge at 127.0.0.1:3090)

Model-facing remind tool: schedule a delayed desktop notification (remind me in X minutes) bridged through the dsh/notify event

Shared snippet library: model-facing snippet_save/list/get/delete tools plus /api/snippets for the UI picker — one store for the user and the AI

Usage & balance for DeepSeek Harness: replays session events to estimate CNY spend (DeepSeek deepseek-chat pricing) and queries the live DeepSeek /user/balance, served over /api/usage for the sidebar budget bar

Multimodal vision tool for dsh: analyze images or screen captures using DeepSeek vision models

Model-facing web_fetch tool: fetch a URL and return its readable text content (scripts/styles stripped, whitespace collapsed, length-capped)

The dsh browser-surface bundle: the web patch layer over dsh-base plus the runtime glue plugin (frontend dist serving, web-surface prompt, bash runtime variables, URL line)

DeepSeek Harness 的 Docker 容器沙箱部署级插件(与 dsh-plugin-vm-sandbox 全能力对齐):39 个 docker_* 模型工具、快照/回滚、文件传输、端口转发、后台任务、审计、共享/配额/回收、网络策略、多容器并行执行与华丽原生 UI。无需 OrbStack,Linux/Windows/macOS 均可使用。

知识库筛子：把文档（md/txt/docx/pdf）构建成可审计知识包（references + SQLite FTS5），提供确定性检索（kb_query）与原文精读（kb_read）工具，可生成零脚本的 DSH skill 并动态加载。

Normify（归一化框架图构建器）：人机共读的分形项目结构图系统——模块树源数据零容忍校验/编译/渲染，以及 AI 结构数据生成器（30 个工具 + normify-gen 技能 + 渲染数据集 + 伴随开发）。0.5.3：分主题 help、项目初始化通道、批量诊断因果链、API 直连引导。适配 DeepSeek Harness 0.1.5+ / DSHEAC AIO 桌面端。

DeepSeek Harness (DSH) MCP server manager: list / create / edit / enable / disable / delete @deepseek-ai/dsh-mcp-client instances in the profile's cordis.patch.yml from the settings page, with form & JSON dual-mode editor, comments-preserving YAML write-back and same-origin JSON routes. MCP 服务器管理器：在设置页列出、新建、编辑、启停、删除 profile 的 cordis.patch.yml 里的 @deepseek-ai/dsh-mcp-client 实例，表单/JSON 双模式编辑，回写保留注释，内置同源 JSON 路由。

DeepSeek Harness (DSH) tool plugin: query Minecraft Wiki (MediaWiki API) and convert raw wiki data into clean AI-readable text. 查询 Minecraft Wiki（中文/英文）并把搜索结果与页面全文转换成可直接投喂给 AI 的干净文本（搜索/引言/全文 Markdown/随机条目）。

DeepSeek Harness (DSH) AI search provider hub: take over web_search with pluggable providers (Tavily first), with per-provider key management, search behavior, usage quota and connectivity test in one settings page. 搜索供应商集线器：以可插拔供应商（默认 Tavily）接管 web_search，各供应商的密钥管理、搜索行为、用量额度与连通性测试集中在同一设置页。