deep-reading

Original：🇨🇳 Chinese

Translated

Deep Reading Collaborative System: A system leveraging multi-layered AI Agents to help transform articles from "read" to "understood" to "mastered", and convert knowledge into actionable plans. Use this system when you need to deeply understand complex articles/papers, systematically organize reading notes, think critically about content, discover hidden logical issues and assumptions, or turn knowledge into action plans. Trigger keywords: deep reading, critical thinking, reading notes, article analysis, Socratic questioning, action plan

8installs

Sourcejst-well-dan/skill-box

Added on2026-02-09

NPX Install

npx skill4agent add jst-well-dan/skill-box deep-reading

SKILL.md Content (Chinese)

View Translation Comparison →

Deep Reading - Collaborative Deep Reading System

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.

Usage Scenarios

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

Core Features

The system has a three-layer collaborative architecture:

🔍 Internalization Layer (Condense the Content) - Sequential Execution

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

🎯 Expansion Layer (Enrich the Content) - Parallel Execution

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

🚀 Output Layer (Actionization)

Planner: Converts cognitive outcomes into specific actionable plans

Response Pattern

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

Detailed Documentation

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

Usage Examples

bash

# Full workflow
/deep-reading examples/sample-article.md examples/sample-draft.md

# Internalization Layer only
/deep-reading --internalize-only article.md draft.md

# Expansion Layer only
/deep-reading --expand-only article.md draft.md

# No action plan
/deep-reading --no-action article.md draft.md

Output Files

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

Dependencies

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.