skills.rest
ozkayas
ozkayasCOMMUNITY
Explore all skills by this author →
𝕏@suat_twGitHub

jlpt-n5-listening-variation-creator

Generate JLPT N5 listening question variations from YouTube clip data.

Updated Feb 22, 2026
Search Tags:#language learning#content generation#ai assistant#jlpt#n5#listening comprehension
One-click install
npx skills add https://github.com/ozkayas/jlpt-bites-ecosystem --skill jlpt-n5-listening-variation-creator
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: jlpt-n5-listening-variation-creator
Source: https://github.com/ozkayas/jlpt-bites-ecosystem/tree/main/.agents/skills/jlpt-n5-listening-variation-creator
Command: npx skills add https://github.com/ozkayas/jlpt-bites-ecosystem --skill jlpt-n5-listening-variation-creator

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai, python-dotenv, pillow, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the creation of new JLPT N5 listening practice questions by transforming existing YouTube clip data, making it easier to generate diverse and engaging study materials.

Core Features & Use Cases

  • Automated Variation Generation: Swaps entities in real listening questions, rewrites dialogue, and generates accompanying images.
  • Content Engineering: Preserves the original question logic and difficulty while creating novel variations.
  • Use Case: Given a YouTube clip of a JLPT N5 listening question, this Skill can produce a new, similar question with different objects or scenarios, ready for student practice.

Quick Start

Use the jlpt-n5-listening-variation-creator skill to process a clip from the tobeprocessed directory.

Frequently Asked Questions about jlpt-n5-listening-variation-creator

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

FAQPage Schema
How do I generate JLPT N5 listening comprehension variations from YouTube clips?▼

To generate JLPT N5 listening comprehension variations, this Skill reads existing YouTube clip data from a data.json file, swaps entities within the dialogue, and outputs a new derived-data.json file alongside generated images for practice.

How does entity swapping work when creating new JLPT N5 listening practice questions?▼

Entity swapping preserves the original question logic and difficulty of real listening questions while rewriting dialogue and generating new accompanying images. This automated content engineering produces novel scenarios ready for student practice.

Do I need to prepare a specific data format before creating JLPT N5 listening variations?▼

Yes, you must prepare a data.json file containing the original YouTube clip data. The Skill processes this input to produce TTS scripts, generate image prompts, and output the transformed variations.

Can I use Imagen 3 to create images for automated language learning content generation?▼

Yes, this Skill uses Imagen 3 to generate accompanying images for automated language learning content generation. It creates image prompts based on the rewritten dialogue and outputs an image.png file.

What steps are involved in finalizing AI-generated listening comprehension questions?▼

The process includes critical steps for concurrency control during generation, self-validation of the output, and a mandatory user approval step before finalizing the derived listening comprehension questions.

Related Skills

Explore More Education & Research Skills→
CDO-07-NewCDO-07-New

content-engine

Transform source material into platform-native content for multiple channels.

Official
Intermediate
ozkayasozkayas

jlpt-n5-listening-variation-tester

Validate JLPT N5 listening variation derived-data.json files through six validation passes.

Community
Advanced
michaelboedingmichaelboeding
24

voice-generation

Convert text into speech using Gemini, ElevenLabs, or OpenAI TTS backends.

Community
Intermediate
ozkayasozkayas

JLPT N5 Listening "Select Image" Question Creator

Generates JLPT N5 listening questions with dialogues, image prompts, and audio scripts.

Community
Advanced