DSH Plugin HubDSH 插件市场
xiehuan123/dsh-deepread 预览 preview

xiehuan123/dsh-deepread

Plugin插件 Native原生 ⭐ 58 MIT Memory & Knowledge记忆与知识库Dev Workflow开发与代码工作流Docs & Writing文档与写作

为AI智能体提供以证据为先的深度阅读——跨文章、书籍和PDF追踪论断、证据、置信度与知识图谱。

Project Overview项目介绍

Edited by Zhiwei Agent (zhiwei)由知微Agent(zhiwei)编辑

dsh-deepread is a document analysis tool built for evidence-first AI reading, available in two distribution forms. It offers a portable Agent Skill that works with Codex, Claude Code, and any other tool that supports the Agent Skill standard, with zero runtime dependencies. It also ships as a host plugin for DeepSeek Harness Web, headless, and dsh-TUI, adding a dedicated deepread tool, PDF text extraction, optional persistence, batch comparison, and export options. To install the portable skill version, run npx skills@latest add xiehuan123/dsh-deepread from your terminal.

The core function of dsh-deepread is to turn unstructured documents like articles, books, and PDFs into structured claims that can be traced back to their original evidence and source locations within the original document. Unlike typical document summarization that compresses content and blends source facts with model inference, dsh-deepread separates author intent, source facts, reasoned inference, and unverified content. It labels each claim with its supporting evidence and exact page or paragraph location, and will explicitly state when a claim has no supporting evidence, rather than filling gaps with unsubstantiated AI-generated content.

dsh-deepread offers five different reading modes to match different use cases: quick key takeaways, in-depth deep reading, knowledge map, Feynman technique learning, and whole book reading. Outputs can be exported to HTML or XMind-compatible formats, and the tool supports full-text caching for repeated reads to avoid redundant network calls. The project is released under the permissive MIT open source license, all core dependencies are peer dependencies that follow the host version of DeepSeek Harness. Default cache settings store up to 200 entries with a 7-day TTL, and all settings can be customized via the DSH configuration file.

dsh-deepread 是一个文档深度分析工具，提供两种可用形态：一是适用于 Codex、Claude Code 等兼容 Agent Skill 标准工具的可移植技能包，二是面向 DeepSeek Harness 的宿主插件。它可以将文章、书籍、PDF 和文档集转换为可追溯溯源的声明，每个声明都关联回原始证据和源位置，遵循证据优先的阅读工作流。

该工具适合需要对长文档进行结构化分析、事实核查和知识整理的开发者、研究人员和内容创作者。用户可选择快速要点提取、深度阅读、知识图谱、费曼学习法、整书阅读五种模式，分析结果可导出为 HTML 或 XMind 兼容格式，还能生成主动回忆题。如果来源不支持某一声明，工具会明确标注“来源未提供证据”。

该项目采用 MIT 许可开源，作为 DSH 插件安装时可通过 dsh plugin 命令添加，安装后重启 dsh web 即可使用阅读面板或在聊天中调用 deepread 工具。可移植版本可通过 npx skills@latest add xiehuan123/dsh-deepread 快速安装。默认开启缓存，TTL 为 7 天，最多存储 200 条记录，缓存配置可自定义调整。

View on GitHub在 GitHub 查看

Recommended强烈推荐 Send to your DSH发给你的 DSH 安装 
请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】，检查通过再动手。

插件：dsh-deepread（xiehuan123/dsh-deepread）
仓库：https://github.com/xiehuan123/dsh-deepread
本站详情页：https://www.yhbd.top/plugins/xiehuan123-dsh-deepread/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 58 · 最近提交 2026-09-11 · 主语言 JavaScript

按下面顺序执行，每步先把结论告诉我，再进入下一步：

【1 兼容性检查】
① 我这边：DSH 版本、Node 版本、操作系统、当前 profile（web / desktop）。
② 读它的 README、package.json、插件 manifest，列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对，结论只写「满足 / 不满足 / 未知」三种；不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突：命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。

【2 安全性检查】
① 仓库可信度：和上面「本站登记」是否一致；star / fork 数、创建时间、最近提交，是否归档或长期停更。
② 安装脚本：逐行看 package.json 的 preinstall / install / postinstall，以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名，立刻停下来告诉我，不要继续装。
③ 依赖：列出新增依赖，标出无人维护、或与知名包拼写近似的可疑包（typosquatting）。
④ 权限与副作用：它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限（filesystem / network / shell / clipboard 等），以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限，或权限明显超出功能所需，先停下来问我。

【3 安装】
上面两步没有「不满足」和「高危项」时才执行；用官方推荐方式安装，不要自行提权。

【4 汇报】
用表格输出：检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜，也不要替我决定。

Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH：它会先核对兼容性与安全性（逐条给「满足 / 不满足 / 未知」），确认没问题再安装，有高危项会停下来问你。框内可滚动，复制到的是完整提示词；安装命令不一定准确，发给 DSH 更稳。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 no risk signal found未发现风险信号
  • This site's static screen found no obvious risk signal (stars, license, activity, manifest)本站静态筛查没发现明显风险信号（星标、许可证、更新活跃度、清单完整度）
DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

  • DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
  • External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时（Electron / Python / Docker 等）是否齐备
  • Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突：命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

  • Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致，是否归档或长期停更
  • Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
  • curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
  • Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
  • Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需（filesystem / network / shell / clipboard）
  • Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限，以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照，不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装（适合开发者）

CLI Install命令行安装 

dsh plugin --profile web add dsh-deepread

把 xiehuan123/dsh-deepread 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

20.7 KB · 缓存于 2026-09-11 19:39:29 · 20.7 KB

📖 DeepRead — Make AI reading traceable

Website · Real outputs · English · 中文

Turn articles, books, PDFs, and document sets into claims you can trace back to evidence and source locations.

npm version GitHub release GitHub stars Agent Skill Awesome DSH Plugin MIT License

DeepRead evidence-first reading workflow

DeepRead is available in two compatible forms:

  • Portable Agent Skill for Codex, Claude Code, and other Agent Skills-compatible tools. Zero runtime dependencies; the agent follows the evidence-first reading workflow with its own file and web tools.
  • Host plugin package for DeepSeek Harness Web/headless and dsh-TUI, with a deepread tool, PDF extraction, optional persistence/jobs/Web route, batch comparison, cost preview, and HTML/XMind-compatible export. Its browser client is an optional Web-only entry.

Why it is different

A typical summary DeepRead
Compresses the topic Extracts complete claims and the reasoning behind them
Blends source facts with model inference Labels author intent, source facts, reasoned inference, and unverified content
Makes conclusions hard to check Pairs important claims with evidence and page/paragraph locations
Stops at an answer Adds knowledge maps, conflicts, limitations, and active-recall questions

If the source does not support a claim, DeepRead says “source does not provide evidence” instead of filling the gap.

Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要，完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →

渲染基于仓库 xiehuan123/dsh-deepread 的 README.md。 在 GitHub 查看原文 →

Related相关推荐

← 上一个 Prev dsh-tether 下一个 Next oh-my-dsh →