process-faq

Convert raw FAQ documents into RAG-ready Markdown and Excel files with keywords.

28|4|Updated Dec 31, 2025

Search Tags:#markdown #rag #excel #faq #data-processing #knowledge-base #keyword-extraction

One-click install

npx skills add https://github.com/joneqian/claude-skills-suite --skill process-faq

Or copy as Structured Prompt for Agent▼

Please help me install this Agent Skill.
Skill: process-faq
Source: https://github.com/joneqian/claude-skills-suite/tree/main/process-faq
Command: npx skills add https://github.com/joneqian/claude-skills-suite --skill process-faq

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, openpyxl, python-docx, PyPDF2, jieba, and includes scripts (resource) components.

What problem does it solve?

Transform raw FAQ documents (Excel, Word, PDF, TXT) into a RAG-optimized, searchable knowledge base. This skill combines Claude-driven content expansion with automated formatting and keyword extraction to scale FAQ inventories from small sets to comprehensive, consistent knowledge bases, reducing manual editing time and improving retrieval accuracy.

Core Features & Use Cases

Smart expansion: Claude reads long answers and splits them into focused Q&As that cover distinct topics.
Automatic keywords: Uses jieba TF-IDF to generate searchable keywords for each entry.
Multi-format support: Works with Excel, Word, PDF, and TXT sources to produce a standardized RAG-ready output.
Quality checks: Deduplication and consistency validation to ensure reliable knowledge bases.

Quick Start

Run: python process-faq/scripts/convert_to_markdown.py <input_file> # converts to Markdown for Claude
Have Claude analyze and expand the content
Run: python process-faq/scripts/generate_rag_faq.py <expanded_file.xlsx> <final_rag.xlsx> # produce final RAG KB