Word Explorer Kids · öffentlicher Open Skill

Word Explorer Kids

# Kids English Word Video Generator ### One Word · One Frame · One Voice > Help children learn English by seeing, hearing, and feeling the meaning. **Kids English Word Video Generator** is an AI Agent Skill designed for parents and teachers who want simple, visual, and memorable English learning videos. It transforms one English word into a complete learning experience: **Word → Visual Meaning → Learning Image → Motion Video → Pronunciation** No vocabulary lists. No textbook explanations. No subtitles. Just one clear word, one meaningful scene, and one natural pronunciation moment. --- # Core Features | Feature | Description | |---|---| | **One Word Learning System** | Each video focuses on one English word to create a clear memory point | | **Visual Meaning Understanding** | Children understand the word through the scene instead of reading explanations | | **Motion-Based Memory** | Gentle animation connects the word with real actions and situations | | **Built-In Pronunciation** | The word is spoken naturally three times inside the generated video | | **Child-Friendly Design** | Creates warm, simple, and safe learning environments | | **Vocabulary Expansion** | Build a complete English learning library one word at a time | --- # Production Pipeline | Stage | Output | |---|---| | **1. Word Analysis** | Identifies the word meaning and category (noun, verb, adjective, preposition, etc.) | | **2. Scene Design** | Creates a visual situation that explains the meaning without text | | **3. Learning Reference Image** | Generates a 9:16 educational image with word and matching visual scene | | **4. Video Generation** | Creates a short animated learning clip with movement and pronunciation | | **5. Final Delivery** | Outputs a ready-to-use vocabulary learning video | --- # Learning Design System | Element | Description | |---|---| | Learning Method | Visual association + motion + sound | | Target Audience | Young children and pre-reading learners | | Teaching Style | Learn through seeing and hearing | | Video Structure | One word → One scene → One action | | Memory Goal | Create a quick "aha moment" for each vocabulary item | --- # Example Learning Scenes | Word Type | Example | Visual Design | |---|---|---| | Noun | Apple | A cute character picks up a red apple in a sunny orchard | | Verb | Jump | A child character jumps happily on a playground | | Adjective | Happy | A character smiles brightly in a warm sunny environment | | Animal | Cat | A cute cat plays in a cozy room | | Emotion | Sad | A character shows a gentle sad expression | --- # Production Technology | Parameter | Specification | |---|---| | Generation Engine | t2i.hd → Reference Image → i2v Video | | Video Style | Child-friendly educational animation | | Duration | 5 seconds | | Orientation | Portrait 9:16 | | Reference Image | 1080P | | Video Output | 720P | | Audio | Built-in video model pronunciation | | Pronunciation Format | Word repeated three times | | Content Rule | One English word per video | --- # Creation Modes | Mode | User Input | AI Output | |---|---|---| | **Full Auto Run** | One English word | Creates complete learning image and video | | **Reference Rebuild** | "Regenerate the learning image" | Recreates only the visual stage | | **Video Rebuild** | "Wrong pronunciation / unclear animation" | Regenerates only the video stage | --- # Example Commands | User Request | AI Action | |---|---| | "Make a video teaching my kid the word apple." | Creates an apple vocabulary lesson video | | "Teach the word jump." | Creates an action-based learning scene | | "Make happy easier for children to understand." | Creates an emotion visualization | | "Regenerate the video because pronunciation is wrong." | Recreates only the video stage | --- # Perfect For | Use Case | Description | |---|---| | **Early English Learning** | Teach vocabulary to children before reading ability develops | | **Home Education** | Create personalized learning videos for children | | **Teacher Materials** | Generate classroom-friendly vocabulary content | | **Vocabulary Series** | Build themed word collections such as animals, actions, feelings, and objects | | **Short Educational Content** | Create engaging learning clips for children's platforms | --- # Best Results Require | Requirement | Reason | |---|---| | Single English word | Keeps the learning focus clear | | Simple concept | Helps children understand visually | | Clear meaning | Improves scene-to-word connection | Not recommended for: - Full sentences or conversations - Multi-word lessons - Complex stories - Additional narration systems - Background music-based learning videos --- # Invoke ```text /kids_english_word_video_generator ``` or simply: > "Make a video that teaches my kid the word 'apple'."

@skyyyyyy

Kids

164 13 58

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/3656250/2026-08-20/khq2p5dw.jpg

# Kids English Word Video Generator

## When to use
- The user inputs a single English word (e.g., apple / cat / jump / happy) and wants a short English learning video that helps children understand that word.
- Also use when only redoing one stage: only the learning reference image, or only the word video.

## Core principles
- One video teaches exactly one word.
- The image builds visual memory, the video adds dynamic understanding, and the sound reinforces correct pronunciation.
- Children who do not know English should still understand the word from the visuals alone — do not use textual explanations.
- Pronunciation is spoken by the video generation model's built-in audio (TTS, long narration, and background music are forbidden unless the user explicitly requests them).

## Steps

### Step 1: Receive the word
1. Handle only a **single English word**. First trim surrounding whitespace and lowercase it as the canonical form, e.g., `Apple` → `apple`.
2. If the user inputs a phrase, sentence, or multiple words, politely explain that this skill handles one word at a time and ask the user to pick one core word (or just continue with the most core word among them).
3. Auto-detect the part of speech: noun (apple, cat), verb (jump, run), adjective (happy, big), simple preposition (in, on), or other.

### Step 2: Understand the word meaning
1. Understand the word's meaning and design a visual scene that "children can understand without reading text":
   - Noun: show the object itself and its natural state (e.g., apple → a red apple, optionally with a small hand picking it up).
   - Verb: show a clear action (e.g., jump → a cartoon child happily jumping, both feet off the ground).
   - Adjective: show the state (e.g., happy → the character smiling cheerfully, bright expression).
   - Simple preposition: show a positional relationship (e.g., on → a kitten sitting on top of a box).
2. Background design (mandatory): always design a simple background scene that matches the word's meaning — noun: the natural environment where the object belongs (e.g., apple → orchard or picnic table, flower → sunny garden); verb: an outdoor scene suited to the action (e.g., jump → grassy playground); adjective: a scene that conveys the feeling (e.g., happy → bright sunny meadow); preposition: a simple scene that clearly shows the positional relationship (e.g., on → a cozy room with a box on a low table). Never use a plain white, solid-color, or empty background.
3. Visual design essentials: prominent subject, simple scene, clear action, no explanatory text inside the frame.

### Step 3: Generate the children's learning reference image
Use `generate_image` with the following fixed parameters:
- `model='t2i.hd'` (clearer text rendering; fall back to `t2i` if unavailable)
- `orientation='portrait'` (9:16 vertical)
- `resolution='1080P'`
- `name='{word}-learning-reference'` (e.g., `apple-learning-reference`)
- `entity_type='word_reference_images'`
- `add_to_canvas=true`

Prompt structure (write in English for easier image-model understanding):
1. Top word display: The word "apple" in large, colorful, child-friendly rounded font at the top of the image (colorful, large, child-friendly font, clear and readable).
2. Main visual explanation: a cute cartoon child/small animal happily holding/showing a red apple in the center of the frame (write according to the Step 2 visual design).
3. Background scene: a simple background scene that matches the word's meaning (write according to the Step 2 background design; never a plain white or empty background).
4. Style: 3D Pixar-style animated render, cute expressive character with soft rounded features, vibrant colors, soft cinematic lighting, warm friendly atmosphere, one clear subject.
5. Restriction: only this one word appears in the image; do not add any other English text, captions, or complex story elements.

### Step 4: Generate the video from the reference image
Use `generate_video` with the following fixed param