---
title: "dsh-deepread"
description: "Deep-reading assistant: five modes (quick, deep, knowledge-map, Feynman, full book) to extract core claims, argument structure, and key evidence from books and articles; exports Markdown, FreeMind/XMind mindmaps, and HTM"
canonical: https://agentpluginsdirectory.com/plugins/dsh-deepread
last-updated: 2026-10-02
---

# dsh-deepread
Deep-reading assistant: five modes (quick, deep, knowledge-map, Feynman, full book) to extract core claims, argument structure, and key evidence from books and articles; exports Markdown, FreeMind/XMind mindmaps, and HTML reports.
- Slug: dsh-deepread
- Publisher: xiehuan123
- Repository: https://github.com/xiehuan123/dsh-deepread
- Manifest: plugin.json
- Version: 1.0.1
- License: MIT
- Category (editorial): research
- Skills: 1 (dsh-deepread)
- MCP servers: 0
- Stars: 57
- Repository created: 2026-08-15
- Repository last pushed: 2026-09-11
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/dsh-deepread
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What dsh-deepread does, in the publisher's words

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

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.

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

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/xiehuan123/dsh-deepread/HEAD/README.md

## Skills

- dsh-deepread: Evidence-first deep reading for books, articles, PDFs, and document sets. Extract core claims, argument structure, supporting evidence, source locations, confidence levels, knowledge maps, and recall questions. Use when the user asks to deep-read, analyze an article, extract claims, trace evidence,…

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.