interview-ingest

Transcribe audio interviews and convert PDFs into analyzable markdown.

14|1|Updated Dec 8, 2025
One-click install
npx skills add https://github.com/linxule/interpretive-orchestration --skill interview-ingest
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: interview-ingest
Source: https://github.com/linxule/interpretive-orchestration/tree/main/skills/interview-ingest
Command: npx skills add https://github.com/linxule/interpretive-orchestration --skill interview-ingest

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires MinerU, and includes scripts (resource) components.

What problem does it solve?

This Skill streamlines the tedious process of converting raw qualitative data, such as audio interview recordings and PDF documents, into clean, analyzable markdown files. It intelligently selects the best conversion tool based on availability and document complexity.

Core Features & Use Cases

  • Audio Transcription: Transcribe interview recordings into markdown using Markdownify.
  • PDF Conversion: Convert PDFs to markdown, leveraging MinerU for complex documents (tables, figures) or Markdownify for simpler ones.
  • Batch Processing: Process multiple audio files or documents efficiently, organizing outputs and tracking data sources.
  • Use Case: You have 10 audio interviews and 5 academic papers in PDF format. Use this skill to automatically transcribe all interviews and convert all PDFs into markdown, ready for coding.

Quick Start

To transcribe an audio file, use Markdownify audio-to-markdown on /path/to/interview.mp3. The output will be interview.md with the transcript.

Frequently Asked Questions about interview-ingest

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

FAQPage Schema
How do I convert audio interviews to markdown transcripts?

Audio transcription converts interview recordings into markdown using Markdownify. Upload your MP3 or audio file to generate a transcript file with all spoken content formatted as analyzable markdown, ready for qualitative coding.

Can I convert PDFs to markdown with complex tables and figures?

PDF conversion to markdown uses MinerU for advanced documents containing tables, figures, and complex layouts, or Markdownify for simpler PDFs. The Skill automatically selects the best tool to preserve structure and produce clean markdown output.

What's the best way to batch process multiple interviews and documents?

Batch processing handles multiple audio files and PDFs efficiently in one operation, organizing outputs and tracking data sources. Process 10 interviews and 5 academic papers simultaneously into a structured markdown dataset ready for qualitative analysis.

Do I need MinerU installed to use this Skill?

MinerU is optional but recommended for complex PDFs with tables and figures. If unavailable, the Skill falls back to Markdownify to ensure you can still convert documents into markdown without additional installation requirements.

How does this prepare data for qualitative research workflows?

The Skill outputs interview transcripts and a structured data-inventory in stage1-foundation format, organizing raw qualitative data into analyzable markdown. This prepares your documents for Stage 1 or Stage 2 qualitative coding and analysis workflows.

What file formats can be converted to markdown?

Supported formats include audio files (MP3 and other interview recordings) and PDFs (academic papers, research documents, and complex layouts). All convert to clean, analyzable markdown organized for qualitative data preparation.