edi-sample-convert

Convert VTT, audio/video, PDFs, and DOCX into JSONL skeletons.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/Telepotch/hirano-edi-on-claude-code --skill edi-sample-convert
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: edi-sample-convert
Source: https://github.com/Telepotch/hirano-edi-on-claude-code/tree/main/.claude/skills/edi-sample-convert
Command: npx skills add https://github.com/Telepotch/hirano-edi-on-claude-code --skill edi-sample-convert

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires subtitle, openai, zod, and includes scripts (resource) components.

What problem does it solve?

This Skill enables teams to ingest and convert diverse source materials (VTT transcripts, audio/video, PDFs, DOCX, etc.) into consistent JSONL skeletons with empty semantic fields, laying the groundwork for downstream AI enrichment and structured book material workflows.

Core Features & Use Cases

  • Ingests source materials from any location into the project’s 01-source/ directory (single files or batch folders).
  • Converts source media and documents (VTT, audio, video, PDF, DOCX, etc.) into structured skeletons (JSONL) with semantic fields left empty for later enrichment.
  • Supports an end-to-end workflow that enables downstream skills (edi-anastyle, edi-concept-mtg, edi-bookplan, edi-export) to enrich and finalize content for books, reports, or research materials.
  • Ideal for teams building books or long-form content who want automated material-to-structure conversion and a scalable ingestion pipeline.

Quick Start

Place your source files anywhere in the project, then run the edi-sample-convert workflow to ingest and convert them into JSONL skeletons ready for semantic enrichment.

Frequently Asked Questions about edi-sample-convert

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

FAQPage Schema
How do I convert VTT transcripts and PDFs into structured JSONL for AI enrichment?

To convert VTT transcripts and PDFs into structured JSONL, you can use an automated ingestion pipeline that transforms diverse source materials into JSONL skeletons with empty semantic fields for downstream AI enrichment.

What's the best way to batch ingest audio and video files for book material workflows?

The best way to batch ingest audio and video files for book workflows is using an AI-assisted conversion tool that automatically places source materials into a designated directory and outputs structured JSONL skeletons.

Do I need an OpenAI API key to convert media into JSONL skeletons?

Yes, you need an OpenAI API key because the media conversion and AI-assisted skeleton generation path requires OpenAI API access to process diverse source materials into structured JSONL.

Can I use this conversion workflow for DOCX documents and still support downstream enrichment?

Yes, you can convert DOCX documents into JSONL skeletons with empty semantic fields, which directly supports end-to-end book workflows and downstream AI-driven enrichment skills.

What does an AI-assisted JSONL skeleton actually contain after media conversion?

An AI-assisted JSONL skeleton contains structured data parsed from converted media with semantic fields intentionally left empty for later AI enrichment and book material finalization.