large-document-reader

Intelligently splits long academic or technical documents into chapters, generates structured JSON summaries for each, and creates a file system with a globa...

Security Scan

The skill's documentation promises chapter-splitting plus JSON summaries and a master index, but the included code only performs local chapter extraction and contains hard-coded user-specific file paths — this mismatch and embedded absolute paths are concerning and need remediation before trusting or running the skill.

Purpose & Capability

SKILL.md claims splitting, per-chapter JSON summaries, and a MASTER_INDEX.md. The shipped Python scripts only extract chapter boundaries and write chapter files; there is no implementation of summary generation or index creation. Also, the scripts use absolute paths specific to a developer's machine (/Users/chenkuan/...), which is inconsistent with a generic document-processing skill.

Instruction Scope

The runtime instructions describe taking a user-provided document path and producing ./chapters/ and ./summaries/. The actual code ignores an external input and reads a hard-coded file from the developer's Desktop, then writes a chapters_info.json into a hard-coded workspace path. This is scope creep and unexpected file access not described in SKILL.md.

Install Mechanism

No install spec is provided (instruction-only plus two scripts). Nothing is downloaded or executed from remote URLs, which reduces supply-chain risk.

Credentials

No environment variables or credentials are requested (appropriate). However, the code directly accesses absolute local filesystem paths (a specific user's Desktop and home .openclaw workspace), which could inadvertently read sensitive local files if those paths exist in the runtime environment.

Persistence & Privilege

The skill is not always-enabled and does not request elevated platform privileges. It writes files to disk (chapters_info.json and chapter .md files) within paths referenced in the scripts; it does not attempt to modify other skills or global agent settings.

What to consider before installing

Do not run this skill as-is. The package contains developer-specific absolute paths and does not implement the summary/index functionality claimed in the README. Before using: (1) Review and edit scripts to accept a user-supplied file path (avoid hard-coded paths), (2) change output locations to a safe, documented directory (relative to the current working directory), (3) verify there are no network calls or other unexpected I/O, and (4) test in a sandboxed environment with non-sensitive documents. If you don't want to edit code yourself, ask the author for a corrected release that implements summaries and index generation and removes hard-coded paths. The behavior looks like sloppy packaging rather than overtly malicious, but the inconsistencies and absolute paths are a privacy and operational risk.

Literature Structuring Expert

Automatically decompose long documents (papers, reports, books) into a structured, AI-friendly knowledge base. Splits by chapter, generates machine-readable summaries, and builds a navigable index to overcome context limits.

When to Use This Skill

Use this skill when the user:

• Has a document that is too long for the AI's context window.
• Needs to perform cross-chapter analysis or get a high-level overview of a long text.
• Wants to build a reusable, queryable knowledge base from a PDF, Markdown, or text file.
• Asks: "How can I get my AI to read this whole book/paper?"

Quick Reference

Situation	Action
User provides a long document	1. Analyze and split it into chapters.<br>2. Generate a JSON summary for each chapter.<br>3. Create a master index file.
User asks a high-level, cross-chapter question	Provide the content of the MASTER_INDEX.md file to the AI.
User asks a detailed, chapter-specific question	Provide the corresponding single file from the ./chapters/ directory to the AI.
Task completed	Present the generated file tree and MASTER_INDEX.md preview to the user.

Core Workflow

Phase 1: Intelligent Splitting

1. Analyze Input: Receive the long document text or file path.
2. Identify Structure: Automatically analyze the document to identify heading hierarchies (e.g., #, ##, 1., 1.1) to determine chapter boundaries. Prioritize user-specified splitting preferences.
3. Execute Split: Split the document into independent plain-text files by chapter.
   • Naming Convention: {sequence_number}_{chapter_title}.md (e.g., 01_Introduction.md).
   • Storage Location: All chapter files are saved in the ./chapters/ directory.

Phase 2: Summary Generation & Structuring

1. Generate Summary per Chapter: For each file in ./chapters/, generate a corresponding JSON summary file.
   • Structured Fields (JSON format):

     {
       "chapter_id": "Unique identifier matching the filename, e.g., 02_1",
       "chapter_title": "Chapter Title",
       "abstract": "Core summary of the chapter, 200-300 words.",
       "keywords": ["Keyword1", "Keyword2", "Keyword3"],
       "key_points": ["Key point one", "Key point two"],
       "related_sections": ["IDs of other chapters strongly related to this one"]
     }
     

   • Storage Location: JSON summary files are saved in the ./summaries/ directory (e.g., 01_Introduction.summary.json).

Phase 3: Create Global Index

1. Aggregate Information: Collect data from all JSON files in ./summaries/.
2. Generate Index: Create a global index file, MASTER_INDEX.md.
   • Content: Lists all chapters' IDs, titles, a short abstract preview, and keywords in a Markdown list or table.
   • Purpose: Provides a "bird's-eye view" for quick navigation and high-level Q&A.

Final Deliverables & File Structure

Upon completion, the following file tree is generated:

Project_Root/
├── chapters/           # 【Source Repository】Contains all split chapter texts (.md files)
│   ├── 01_Introduction.md
│   ├── 02_1_Experimental_Methods.md
│   └── ...
├── summaries/          # 【Summary Repository】Contains all structured JSON summaries
│   ├── 01_Introduction.summary.json
│   ├── 02_1_Experimental_Methods.summary.json
│   └── ...
└── MASTER_INDEX.md     # 【Global Navigation】Core document summary index

Usage Instructions for the User

For Global, Cross-Chapter Queries (e.g., “What is the paper's main thesis?”):

• Provide the content of the MASTER_INDEX.md file to the AI. This is token-efficient.

For Specific, In-Depth Queries Within a Chapter (e.g., “What were the parameters in the 'Methods' section?”):

• Provide the corresponding single chapter file from the chapters/ directory to the AI for full context.