Children's Literacy Flashcard Generator

Problem

Teaching a single Chinese character to a child usually requires more than a printed glyph. The material needs a large character, pinyin, and a spoken explanation that matches the child's age. This skill generates that package for one word: a 1:1 literacy flashcard image and a Chinese TTS audio clip.

How It Works

The core inputs are word and age_group. word must be a single Chinese character, while age_group controls explanation depth: younger children get concrete associations, while older children get more structural or radical-oriented explanations. The skill builds TTS copy and an image prompt, then submits voice synthesis and image generation tasks. With a ShowAPI appKey, execution is asynchronous: execute_task.py returns a task_id, and query_task.py polls until the result includes flashcard_image_url and tts_audio_url. Without an appKey, the skill can return a one-shot preview, but that path does not use the asynchronous scripts.

Boundaries

It is useful for single-character learning cards, classroom demos, and audio-visual literacy samples. It is not suitable for synchronous generation, batch processing, or production materials that require teaching review. The output is a set of media URLs that can be embedded in an HTML page, but the final content should still be checked by an educator.