deep-reading

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Deep Reading - 深度阅读协作系统

Deep Reading - Collaborative Deep Reading System

深度阅读协作系统,通过多层次的 AI agents 协作,帮助你将文章从"读过"到"读懂"再到"读透",最终转化为可执行的行动计划。

This collaborative deep reading system uses multi-layered AI Agents to help you transform articles from "read" to "understood" to "mastered", and finally convert knowledge into actionable plans.

使用场景

Usage Scenarios

使用本 skill 当用户需要:

深度理解一篇复杂的文章、论文或长文
将阅读笔记系统化整理
批判性思考文章内容
发现隐藏的逻辑问题和假设
将知识转化为行动计划

Use this Skill when you need to:

Deeply understand complex articles, papers, or long-form texts
Systematically organize reading notes
Think critically about article content
Discover hidden logical issues and assumptions
Convert knowledge into actionable plans

核心功能

Core Features

系统包含三层协作架构:

The system has a three-layer collaborative architecture:

🔍 内化层(读薄) - 顺序执行

🔍 Internalization Layer (Condense the Content) - Sequential Execution

整理者: 生成结构化的 Markdown 笔记
转述者: 使用 SCQA + 费曼技巧通俗化解释

Organizer: Generates structured Markdown notes
Explainer: Uses SCQA + Feynman Technique to explain content in plain language

🎯 拓展层(读厚) - 并行执行

🎯 Expansion Layer (Enrich the Content) - Parallel Execution

诊断引擎: 批判性分析 + 逻辑剖析 (后台)
苏格拉底: 引导性提问,不给答案 (前台)

Diagnosis Engine: Critical analysis + logical dissection (background process)
Socratic Questioner: Guides with probing questions, no direct answers provided (front-end interaction)

🚀 产出层(行动)

🚀 Output Layer (Actionization)

规划师: 将认知转化为具体的行动计划

Planner: Converts cognitive outcomes into specific actionable plans

Response Pattern

当用户请求深度阅读分析时:

接收输入:

- 检查是否提供了文章路径和草稿笔记路径
- 如果没有,询问用户或请求粘贴内容
- 解析可选参数 (--internalize-only, --expand-only, --no-action)

确认配置:

- 确认要启用的层次 (默认全部启用)
- 确认输出目录 (默认 outputs/[timestamp]/)
- 显示即将执行的流程

执行处理流程:

步骤 3.1: 内化层 (如果启用)
- 调用 Task tool, subagent_type: "general-purpose"
  - Agent 1: 读取 references/agents/organizer.md
  - 输入: 原文 + 草稿
  - 输出: organized-notes.md

- 调用 Task tool, subagent_type: "general-purpose"
  - Agent 2: 读取 references/agents/explainer.md
  - 输入: organized-notes.md
  - 输出: explained-notes.md

步骤 3.2: 拓展层 (如果启用, 并行执行)
- 并行调用两个 Task tools:
  - Agent 3: 读取 references/agents/diagnosis.md
    输入: organized-notes.md + explained-notes.md
    输出: diagnosis-report.json

  - Agent 4: 读取 references/agents/socratic.md
    输入: diagnosis-report.json
    输出: socratic-questions.md

步骤 3.3: 产出层 (如果启用)
- 调用 Task tool, subagent_type: "general-purpose"
  - Agent 5: 读取 references/agents/planner.md
  - 输入: 所有前序分析结果
  - 输出: action-plan.md

整合输出:

- 创建时间戳目录 (如 outputs/2026-01-21-14-20/)
- 保存所有生成的文件
- 生成汇总报告 SUMMARY.md
- 向用户报告:
  ✓ 文件列表
  ✓ 输出目录路径
  ✓ 关键发现摘要

可选: 交互式对话:

如果用户请求,基于 socratic-questions.md 进行深度对话

When a user requests deep reading analysis:

Receive Input:

- Check if article path and draft notes path are provided
- If not, ask the user or request content pasting
- Parse optional parameters (--internalize-only, --expand-only, --no-action)

Confirm Configuration:

- Confirm which layers to enable (all enabled by default)
- Confirm output directory (default: outputs/[timestamp]/)
- Display the upcoming execution process

Execute Processing Flow:

Step 3.1: Internalization Layer (if enabled)
- Call Task tool, subagent_type: "general-purpose"
  - Agent 1: Read references/agents/organizer.md
  - Input: Original article + draft notes
  - Output: organized-notes.md

- Call Task tool, subagent_type: "general-purpose"
  - Agent 2: Read references/agents/explainer.md
  - Input: organized-notes.md
  - Output: explained-notes.md

Step 3.2: Expansion Layer (if enabled, executed in parallel)
- Call two Task tools in parallel:
  - Agent 3: Read references/agents/diagnosis.md
    Input: organized-notes.md + explained-notes.md
    Output: diagnosis-report.json

  - Agent 4: Read references/agents/socratic.md
    Input: diagnosis-report.json
    Output: socratic-questions.md

Step 3.3: Output Layer (if enabled)
- Call Task tool, subagent_type: "general-purpose"
  - Agent 5: Read references/agents/planner.md
  - Input: All previous analysis results
  - Output: action-plan.md

Integrate Output:

- Create a timestamped directory (e.g., outputs/2026-01-21-14-20/)
- Save all generated files
- Generate a summary report SUMMARY.md
- Report to the user:
  ✓ List of files
  ✓ Output directory path
  ✓ Summary of key findings

Optional: Interactive Dialogue:

If requested by the user, conduct in-depth dialogue based on socratic-questions.md

详细文档

Detailed Documentation

完整工作流程: 参考
```
references/workflow.md
```

Agent 提示词:

```
references/agents/organizer.md
```
- 内容整理专家
```
references/agents/explainer.md
```
- 费曼技巧转述者
```
references/agents/diagnosis.md
```
- 批判性诊断引擎
```
references/agents/socratic.md
```
- 苏格拉底式提问者
```
references/agents/planner.md
```
- 行动规划师

Complete Workflow: Refer to
```
references/workflow.md
```

Agent Prompts:

```
references/agents/organizer.md
```
- Content Organization Expert
```
references/agents/explainer.md
```
- Feynman Technique Explainer
```
references/agents/diagnosis.md
```
- Critical Diagnosis Engine
```
references/agents/socratic.md
```
- Socratic Questioner
```
references/agents/planner.md
```
- Action Planner

使用示例

Usage Examples

bash

undefined

bash

undefined

完整流程

Full workflow

/deep-reading examples/sample-article.md examples/sample-draft.md

仅内化层

Internalization Layer only

/deep-reading --internalize-only article.md draft.md

仅拓展层

Expansion Layer only

/deep-reading --expand-only article.md draft.md

无行动计划

No action plan

/deep-reading --no-action article.md draft.md

undefined

/deep-reading --no-action article.md draft.md

undefined

输出文件

Output Files

所有输出保存在

outputs/[timestamp]/

```
organized-notes.md
```
- 结构化笔记
```
explained-notes.md
```
- 通俗化解释
```
diagnosis-report.json
```
- 诊断报告
```
socratic-questions.md
```
- 苏格拉底式问题
```
action-plan.md
```
- 行动计划
```
SUMMARY.md
```
- 汇总报告

All outputs are saved in

outputs/[timestamp]/

```
organized-notes.md
```
- Structured notes
```
explained-notes.md
```
- Plain language explanations
```
diagnosis-report.json
```
- Diagnosis report
```
socratic-questions.md
```
- Socratic questions
```
action-plan.md
```
- Action plan
```
SUMMARY.md
```
- Summary report

依赖

Dependencies

Claude Code CLI
Task tool (用于调用 sub-agents)
文件系统访问权限

提示: 首次使用建议先查看

examples/

目录下的示例文件,了解输入格式。完整架构设计参见项目根目录的

architecture-design.md

。

Claude Code CLI
Task tool (for calling sub-agents)
File system access permissions

Tip: For first-time use, it is recommended to check the sample files in the

examples/

directory to understand the input format. The complete architecture design can be found in

architecture-design.md

in the project root directory.