skills.rest
wayne930242
wayne930242COMMUNITY
Explore all skills by this author โ†’
WebsiteGitHub

init-doc

Initialize a document translation project from a PDF with Python scripts.

Updated Feb 23, 2026
Search Tags:#document processing#pdf#translation#glossary#website generation#terminology management
One-click install
npx skills add https://github.com/wayne930242/beneath-cursed-moon --skill init-doc
Or copy as Structured Prompt for Agentโ–ผ
Please help me install this Agent Skill.
Skill: init-doc
Source: https://github.com/wayne930242/beneath-cursed-moon/tree/main/.claude/skills/init-doc
Command: npx skills add https://github.com/wayne930242/beneath-cursed-moon --skill init-doc

SYSTEM DOCUMENTATION & REQUIREMENTS

๐Ÿ’ก This Skill requires python, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill streamlines the process of initializing a document translation project, including building a glossary and structuring chapters from PDF sources.

Core Features & Use Cases

  • PDF Content Extraction: Extracts text and images from PDF files.
  • Visual Theme Configuration: Allows customization of website appearance (dark/light mode, background images, color palettes).
  • Glossary and Terminology Management: Identifies key terms, manages proper noun translation policies, and builds a glossary for consistency.
  • Content Structuring: Splits extracted content into manageable chapters and configures the website's sidebar navigation.
  • Use Case: A game developer needs to translate their rulebook PDF into multiple languages. This Skill automates the initial setup, extracts content, helps define consistent terminology, and structures the translated documents for a website.

Quick Start

Initialize the document translation project by running the init-doc command.

Frequently Asked Questions about init-doc

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I initialize a document translation project from a PDF file?โ–ผ

To initialize a document translation project, this Skill extracts text and images from a specified PDF file, cleans sample data, splits content into chapters, and generates a structured website with sidebar navigation.

How do I manage terminology and proper nouns when translating a PDF document?โ–ผ

Managing terminology and proper nouns involves identifying key terms, configuring translation policies, and updating a glossary.json file to ensure consistent vocabulary across all extracted and translated chapters.

Can I configure visual themes for a generated website from extracted PDF content?โ–ผ

Yes, you can configure visual themes for the generated website by customizing appearance settings, including dark or light modes, background images, and color palettes via a style-decisions.json file.

Do I need Python to extract PDF content and generate website structure?โ–ผ

Yes, you need Python installed, as this Skill leverages Python scripts for PDF content extraction, image handling, and generating the final website structure.

What is the best way to split PDF content into chapters for website generation?โ–ผ

Splitting PDF content into chapters for website generation is handled automatically during project initialization, organizing extracted text and images into manageable sections with configured sidebar navigation.

Related Skills

Explore More Content & Communication Skillsโ†’
youhei-ushioyouhei-ushio
1

pdf

Extract text and structured data from PDF documents using Python libraries.

Community
Intermediate
teamniteoteamniteo
5

section-docs

Add a structured documentation section to an existing Astro website.

Official
Advanced
DaleSeoDaleSeo
129

style-guide

Enforce consistent Korean writing style across business, academic, and technical documents.

Community
Advanced
cnbisoncnbison
1

ljg-read

Translate texts between English and Chinese with structural annotation and critical questioning.

Community
Intermediate