skills.rest
TomazWang
TomazWangCOMMUNITY
Explore all skills by this author →
Website𝕏@tomazwangGitHub

doc-converter

Convert PPTX, PDF, DOCX, HTML, and Confluence exports into Markdown.

Updated Feb 5, 2026
Search Tags:#pdf#markdown#pandoc#pptx#conversion#docx#document-conversion
One-click install
npx skills add https://github.com/TomazWang/agent-toolkit --skill doc-converter
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: doc-converter
Source: https://github.com/TomazWang/agent-toolkit/tree/main/plugins/kb-analysis/skills/doc-converter
Command: npx skills add https://github.com/TomazWang/agent-toolkit --skill doc-converter

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Convert documents into AI-readable Markdown to enable efficient content analysis and knowledge extraction.

Core Features & Use Cases

  • Supports PPTX, PDF, DOCX, HTML, and Confluence exports.
  • Preserves structure and enables downstream AI processing for knowledge bases and archives.
  • Use Case: Convert a batch of slides or reports into a searchable Markdown repository for quick review.

Quick Start

Provide a file or directory path to convert and check kb/sources/docs/ for the resulting Markdown files.

Frequently Asked Questions about doc-converter

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

FAQPage Schema
How do I convert PDF and PPTX files to Markdown for AI analysis?▼

You can convert PDF and PPTX files to Markdown by providing a file or directory path to the converter. The tool processes the documents using Pandoc and Python-based converters, outputting AI-ready Markdown files to the kb/sources/docs/ directory.

What document formats can be converted to Markdown for knowledge extraction?▼

Supported document formats include PPTX, PDF, DOCX, HTML, and Confluence exports. The conversion process preserves the original document structure to enable seamless downstream knowledge extraction and AI processing.

Does Pandoc need to be installed to convert DOCX and HTML files to Markdown?▼

Yes, the converter relies on Pandoc and Python-based converters to process DOCX, HTML, and other formats into Markdown. These dependencies handle the structural preservation and format translation required for AI-ready output.

Can I batch convert Confluence exports into a searchable Markdown repository?▼

Yes, you can batch convert Confluence exports by providing a directory path. The converter processes the files and outputs them as structured Markdown into kb/sources/docs/, creating a searchable repository complete with source metadata for traceability.

What is the best way to preserve document structure when converting PDF to Markdown?▼

Using a converter that explicitly preserves structure during PDF to Markdown conversion is the best approach. This Skill retains document formatting and outputs source metadata alongside the Markdown files, ensuring the content remains structured for AI analysis.

Why does the Markdown conversion output include source metadata files?▼

The Markdown conversion includes source metadata to ensure traceability of the converted documents. This metadata tracks the original file origin and format, which is essential for maintaining context when building AI knowledge bases from converted archives.

Related Skills

Explore More Content & Communication Skills→
Razaib-khanRazaib-khan

working-with-documents

Create, edit, convert, and extract DOCX, PDF, and PPTX documents.

Community
Advanced
mathiasbourgoinmathiasbourgoin
2

kb-reindex

Build or incrementally update a LanceDB semantic search index over markdown KB files.

Community
Intermediate
jchildreejchildree
1

llm-wiki

Automate setup and maintenance of an Obsidian markdown knowledge base with an LLM.

Community
Advanced
AidenSbVevoAidenSbVevo
1

pdf

Extract text and tables from PDF documents and fill forms.

Community
Advanced