Xiao Sheng Shopping Assistant Digital Human Video Prompt Generation System for JI Meng
Task Goal
- This Skill is used for: Generating JI Meng video prompts for Xiao Sheng shopping assistant digital human promotional videos.
- Capabilities include:
- Four-agent collaboration: Prompt Generator, Quality Controller, Knowledge Base Operator, Cross-Tool Adapter.
- Prompt formula driven: Subject + Movement + Scene + (Shot Language + Lighting + Atmosphere).
- Bilingual (Chinese/English) versions: Compatible with international AI tools.
- Consistency assurance: Character consistency, visual coherence, emotional continuity.
- Knowledge base intelligent reuse: Direct retrieval for similar needs, iterative optimization for new ones.
- Cross-tool adaptation: Integration with Suno music generation and AI painting generation.
- Trigger Condition: User needs to generate prompts for Xiao Sheng shopping assistant digital human promotional videos.
Prerequisites
- No special dependencies required.
- Prepare promotional video information:
- Scene type (product recommendation, price comparison, promotion event, etc.).
- Emotion tone (enthusiastic, professional, friendly, urgent, etc.).
- Video duration (default 5s).
- Number of storyboard scenes (default 5 scenes).
Operating Steps
Standard Workflow (Four-Agent Collaboration)
Step 1: Demand Intake and Knowledge Base Check (Agent 3: Knowledge Base Operator)
Responsibilities: Prioritize checking the knowledge base; directly retrieve for similar needs; initiate collaboration for new needs.
- Requirement Identification: Identify scene type, emotion tone, number of storyboard scenes.
- Knowledge Base Check: Query if prompt templates for similar scenes exist.
- Direct Reuse: If matched, directly retrieve and return prompts.
- New Demand Handling: If not matched, hand over to the Prompt Generator to initiate creation.
Output Format:
{
"demand_type": "product recommendation / price comparison / promotion event",
"emotion_tone": "enthusiastic / professional / friendly / urgent",
"scene_count": 5,
"knowledge_base_match": "true / false",
"existing_prompts": "If matched, return existing prompts; if not matched, return null"
}
Step 2: Prompt Generation (Agent 1: Prompt Generator)
Responsibilities: Output JI Meng prompts according to the formula, strictly adhering to consistency.
Prompt Formula:
Subject (subject description) + Movement + Scene (scene description) + (Shot Language + Lighting + Atmosphere)
Core Requirements:
- Subject Consistency: All scenes use the fixed core character description.
- Emotion Adaptation: Lighting and atmosphere match the emotion of the corresponding scene.
- Bilingual Version: Generate Chinese and English corresponding versions.
- Detailed Specificity: Coherent movements, adapted for 5s short video.
- Extended Detailing: Avoid context discontinuity issues from independent AI generation.
Output Format (per scene):
{
"scene_number": 1,
"scene_name": "Scene Name",
"duration": "5s",
"chinese_prompt": {
"subject": "Subject description",
"movement": "Movement description",
"scene": "Scene description",
"shot_language": "Shot language",
"light": "Lighting",
"atmosphere": "Atmosphere",
"full_prompt": "Complete Chinese prompt"
},
"english_prompt": {
"subject": "Subject description",
"movement": "Movement description",
"scene": "Scene description",
"shot_language": "Shot language",
"light": "Lighting",
"atmosphere": "Atmosphere",
"full_prompt": "Complete English prompt"
},
"emotion_tone": "Adapted emotion",
"consistency_check": {
"character_description": "Consistent with core character fixed description",
"visual_elements": "Visual elements are coherent",
"emotion_progression": "Emotion progression is natural"
}
}
Step 3: Quality Check (Agent 2: Quality Controller)
Responsibilities: Check the suitability of scene framing, lighting, and emotion.
Checklist:
- Subject Consistency: Unified description of the same character's appearance (age, hairstyle, clothing, temperament).
- Scene Framing Reasonableness: Shot language fits the scene requirements.
- Lighting Matching: Lighting adapts to the emotion tone.
- Emotional Continuity: Natural emotion progression from scene 1 to scene 5.
- Visual Coherence: Visual cues run through all 5 scenes (color palette, scene elements).
- AI Image/Video Requirements: Specific details, coherent movements, adapted for 5s short video.
- Chinese/English Correspondence: Semantic consistency between Chinese and English versions.
Handling Non-Pass:
- If inconsistencies are found, provide feedback to the Prompt Generator for adjustment.
- Maximum of 2 rounds of feedback to avoid over-iteration.
Output Format:
{
"quality_check": "pass / fail",
"check_results": {
"character_consistency": "pass",
"shot_language": "pass",
"light_matching": "pass",
"emotion_progression": "pass",
"visual_coherence": "pass",
"ai_requirement": "pass",
"translation_quality": "pass"
},
"issues": [],
"adjustment_needed": "false"
}
Step 4: Knowledge Base Archiving (Agent 3: Knowledge Base Operator)
Responsibilities: Archive fixed character descriptions and prompt templates to support reuse.
Archiving Content:
- Core character fixed description (Xiao Sheng shopping assistant).
- Five-scene emotion prompt template.
- Chinese/English corresponding versions.
- Scene classification index.
Output Format:
{
"archive_id": "Unique identifier",
"scene_type": "product recommendation / price comparison / promotion event",
"emotion_tone": "Emotion tone",
"character_profile": {
"gender": "Female",
"age": "Approximately 25 years old",
"appearance": "Appearance description",
"outfit": "Outfit description",
"temperament": "Temperament description"
},
"prompt_templates": {
"scene_1": "Template for scene 1",
"scene_2": "Template for scene 2",
"scene_3": "Template for scene 3",
"scene_4": "Template for scene 4",
"scene_5": "Template for scene 5"
},
"bilingual_version": "Chinese/English corresponding version",
"tags": ["Tag 1", "Tag 2"]
}
Step 5: Cross-Tool Adaptation (Agent 4: Cross-Tool Adapter)
Responsibilities: Integrate with Suno music generation and AI painting, ensuring prompts share the same source.
Suno Music Prompts (per scene):
{
"scene_number": 1,
"music_style": "Music style",
"music_prompt": "Music prompt",
"emotion_match": "Emotion match",
"instrumentation": "Instrumentation",
"tempo": "Tempo",
"duration": "Duration"
}
AI Painting Prompts (pre-action frames):
{
"scene_number": 1,
"painting_prompt": "Painting prompt",
"pre_action_description": "Pre-action frame description",
"visual_elements": "Visual elements",
"composition": "Composition",
"color_palette": "Color palette"
}
Output Format:
{
"cross_tool_prompts": {
"suno_music": {
"scene_1": {...},
"scene_2": {...},
"scene_3": {...},
"scene_4": {...},
"scene_5": {...}
},
"ai_painting": {
"scene_1": {...},
"scene_2": {...},
"scene_3": {...},
"scene_4": {...},
"scene_5": {...}
}
}
}
Complete Output Example
{
"metadata": {
"scene_type": "Product recommendation",
"emotion_tone": "Enthusiastic and professional",
"total_duration": "25s (5 scenes × 5s)",
"character": "Xiao Sheng shopping assistant"
},
"scenes": [
{
"scene_number": 1,
"scene_name": "Opening Attention Grabber",
"duration": "5s",
"chinese_prompt": {
"full_prompt": "Subject: 25-year-old female digital human, oval face, almond eyes with smile, light brown shoulder-length curly hair, fair skin, light pink lips, wearing light gray tailored suit skirt, white shirt, beige pumps, simple silver necklace, professional and friendly temperament, elegant hand gestures. Movement: Slowly raise hand pointing to the right, upright posture. Scene: Modern business setting, product display shelf in background, simple documents in foreground. Shot: Medium fixed shot, bokeh background, front light. Light: Warm soft light, bright and clear. Atmosphere: Enthusiastic and professional, attention-grabbing."
},
"english_prompt": {
"full_prompt": "Subject: 25-year-old female digital human, oval face, almond eyes with smile, light brown shoulder-length curly hair, fair skin, light pink lips, wearing light gray tailored suit skirt, white shirt, beige pumps, simple silver necklace, professional and friendly temperament, elegant hand gestures. Movement: Slowly raise hand pointing to the right, upright posture. Scene: Modern business setting, product display shelf in background, simple documents in foreground. Shot: Medium fixed shot, bokeh background, front light. Light: Warm soft light, bright and clear. Atmosphere: Enthusiastic and professional, attention-grabbing."
},
"emotion_tone": "Enthusiastic and professional",
"suno_music_prompt": "Upbeat modern music, lively tempo, piano + electronic, instrumental, creating an enthusiastic and professional atmosphere",
"ai_painting_prompt": "Medium shot, front lighting, warm soft light in a modern business setting, product display shelf in background blurred, simple documents in foreground; 25-year-old female digital human (oval face, smiling almond eyes, light brown shoulder-length curly hair, light gray suit skirt + white shirt + beige pumps, silver necklace) upright posture, hand gestures ready to point right, expression enthusiastic and professional, overall image bright and clear."
}
]
}
Resource Index
Essential Reference Documents
Four-Agent Role Definitions: See references/agent-roles.md
- Detailed role definitions, capability boundaries, and collaboration workflows for the 4 agents.
- When to read: When needing to understand agent responsibilities and collaboration logic.
Prompt Formula Detailed Explanation: See references/prompt-formula.md
- Detailed explanation, breakdown steps, usage examples for the prompt formula.
- When to read: When needing to generate prompts.
Consistency Assurance Mechanism: See references/consistency-guide.md
- Detailed assurance mechanisms for character consistency, visual coherence, emotional continuity.
- When to read: When needing to ensure prompt consistency.
Character Fixed Description: See references/character-profile.md
- Core fixed description of Xiao Sheng shopping assistant.
- When to read: When generating subject descriptions for prompts.
Scene Templates: See references/scene-templates.md
- Library of five-scene templates for promotional scenarios.
- When to read: When needing to generate prompts quickly.
Cross-Tool Adaptation: See references/cross-tool-adaptation.md
- Guide for adapting to Suno music generation and AI painting.
- When to read: When needing to integrate with other tools.
Output Assets
Example Prompts: See assets/examples/sample-prompts.md
- Complete scene examples (product recommendation, price comparison, promotion event).
- When to read: When needing to refer to specific output formats.
Important Notes
Prompt Generation Principles
- Strictly follow the formula: Subject + Movement + Scene + (Shot Language + Lighting + Atmosphere).
- Chinese/English Correspondence: Ensure semantic consistency, compatible with international AI tools.
- Specific Details: Coherent movements, adapted for 5s short video duration.
- Emotion Matching: Lighting and atmosphere strictly match the emotion tone.
Consistency Assurance
- Character Consistency: All scenes use the same core character description.
- Visual Coherence: Establish visual cues that run through all 5 scenes (color palette, scene elements).
- Emotional Continuity: Natural emotion progression from scene 1 to scene 5.
Knowledge Base Usage
- Prioritize Reuse: Directly retrieve knowledge base assets for similar needs.
- Incremental Archiving: New demands must be archived to the knowledge base after creation.
- Classification Indexing: Build indexes by scene type and emotion tone.
Cross-Tool Adaptation
- Same-Source Design: Suno music prompts and AI painting prompts share the same source as Ji Meng prompts.
- Emotion Unity: Ensure music style and visual texture are consistent with Ji Meng prompt emotions.
- Format Compatibility: Generate formats that meet each tool's requirements.
Usage Examples
Example 1: Product Recommendation Video Prompts
User Request: Generate Ji Meng prompts for a 5-scene product recommendation video.
Execution Method:
- Knowledge Base Operator: Check knowledge base, find matching template.
- Direct Retrieval: Return existing product recommendation prompt template.
- Cross-Tool Adapter: Generate Suno music and AI painting prompts.
Key Parameters:
- Scene type: Product recommendation
- Emotion tone: Enthusiastic and professional
- Number of storyboard scenes: 5
- Video duration: 25 seconds (5 scenes × 5 seconds)
Example 2: Price Comparison Video Prompts
User Request: Generate Ji Meng prompts for a 5-scene price comparison video.
Execution Method:
- Knowledge Base Operator: Check knowledge base, no matching template.
- Prompt Generator: Generate new prompts according to formula.
- Quality Controller: Check prompt quality.
- Knowledge Base Operator: Archive to knowledge base.
- Cross-Tool Adapter: Generate Suno music and AI painting prompts.
Key Parameters:
- Scene type: Price comparison
- Emotion tone: Objective and professional
- Number of storyboard scenes: 5
- Video duration: 25 seconds (5 scenes × 5 seconds)
Example 3: Promotion Event Video Prompts
User Request: Generate Ji Meng prompts for a 5-scene promotion event video.
Execution Method:
- Knowledge Base Operator: Check knowledge base, find similar template.
- Retrieve Similar Template: Fine-tune based on existing template.
- Prompt Generator: Generate customized prompts.
- Quality Controller: Check prompt quality.
- Knowledge Base Operator: Archive new version.
- Cross-Tool Adapter: Generate Suno music and AI painting prompts.
Key Parameters:
- Scene type: Promotion event
- Emotion tone: Urgent and enthusiastic
- Number of storyboard scenes: 5
- Video duration: 25 seconds (5 scenes × 5 seconds)