PDF Organizer Skill for Openclaw

An intelligent AI-driven tool that automatically analyzes, renames, and organizes PDF documents into a structured hierarchical library based on content.

yxl184
v1.0.0
Mar 17, 2026
0
760
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install skill-pdf-orgnizer

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install skill-pdf-orgnizer using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is PDF Organizer Skill?

The PDF Organizer Skill is a robust automation solution designed for developers, researchers, and professionals who manage large volumes of digital documents. By integrating Openclaw Skills with advanced AI models like GPT-3.5 or Kimi, it performs deep content analysis to extract essential metadata such as titles, authors, and journal names. This tool transforms a cluttered folder of nameless PDFs into a clean, searchable, and topic-based file system, significantly reducing the manual effort required for document archiving and library management.

PDF Organizer Skill Use Cases

  • Automatically sorting academic research papers into category-specific folders based on scientific domain.
  • Renaming generic or cryptic PDF filenames into a standardized Title_Author_Journal.pdf format for better visibility.
  • Organizing business reports and financial statements into a hierarchical folder structure by topic.
  • Maintaining a clean digital archive using incremental processing to only handle new or modified files.

How PDF Organizer Skill Works

  1. The skill scans the configured input directory for all available PDF files.
  2. It extracts a specific character count from the document header and body using a dedicated PDF reader module.
  3. Extracted text is sent to an LLM provider (OpenAI or Kimi) via API to identify the title, author, and primary category.
  4. The skill classifies the document into one of ten standard categories, such as Technology, Finance, or Science.
  5. It renames the file using a clean, underscore-delimited naming convention and moves it into a topic-based folder hierarchy.
  6. A detailed log is generated to provide statistics and track the success of the organization process.

PDF Organizer Skill Setup

Prerequisites

  • Python 3.8+
  • API key for OpenAI or Kimi (Moonshot AI)

Installation

  1. Clone the repository and install the required dependencies:
pip install -r requirements.txt
  1. Open config.json and configure your API provider and file paths:
{
  "openai_api_key": "your_api_key",
  "input_folder": "input_pdfs/",
  "output_folder": "organized_pdfs/",
  "api_provider": "openai"
}
  1. Place your PDFs in the input_pdfs/ folder.
  2. Execute the organization script:
python pdf_organizer.py

PDF Organizer Skill Data Schema & Taxonomy

The PDF Organizer Skill manages data through a structured pipeline involving metadata extraction and file system manipulation.

Component Description
Input Source Local directory containing unorganized PDF files.
Metadata Taxonomy Extracted fields include Title, Author, Journal, and Topic.
Category Mapping Files are mapped to standard categories (e.g., Business, Politics, Health).
File Convention Standardized as Title_Author_Journal.pdf.
Output Hierarchy [Output Folder]/[Category]/[Subtopic]/[Renamed_File].pdf

PDF Organizer Skill Advanced Features

  • Multi-provider support allowing users to switch between OpenAI and Kimi API integrations for content analysis.
  • Incremental processing mode which leverages Openclaw Skills logic to skip files that haven't changed, saving on API costs.
  • Dry-run capability to preview renaming and folder creation logic without making actual changes to the file system.
  • Batch processing efficiency designed to handle large volumes of documents in a single execution session.
  • Customizable topic mappings that allow power users to define specific organizational categories for their workflow.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*