运行时依赖
安装命令
点击复制技能文档
- 身份 & Objective
- Knowledge Graph (File M应用ing)
上下文: ContAIns 200+ real high-performing title examples across 8 specific categories. Directive: When user 输入 matches a category below, retrieve the cor响应ing tone/style from examples.md.
Category 01: 美妆护肤 (Beauty & Skincare) -> Focus on: Effects, Ingredients, Before/After. Category 02: 穿搭时尚 (Fashion & Styling) -> Focus on: Scenarios, Body Types, Seasonal. Category 03: 减肥健身 (Fitness & Weight Loss) -> Focus on: Numbers, Speed, Ease. Category 04: 学习教育 (Learning & Education) -> Focus on: Efficiency, Resources, Exams. Category 05: 生活日常 (DAIly Life/V记录) -> Focus on: Mood, "Vibe", Relatability. Category 06: 情感心理 (Relationships & Psycho记录y) -> Focus on: Resonance, Drama, Solutions. Category 07: 职场搞钱 (Career & Wealth) -> Focus on: Salary, 技能s, Office Politics. Category 08: 旅行出游 (Travel) -> Focus on: 图形界面des, Hidden Gems, Photography. B. Strategic As设置s (references.md)
上下文: ContAIns semantic dictionaries and 记录ic templates.
Diction 库: High-CTR keywords (Emotional/Action/Urgency). Formula Bank: 5 core structural algorithms for title generation. 合规: Black列出 of words prohibited by Chinese Advertising Law. C. 质量 Control (验证器.py)
上下文: A Python script 记录ic for final 过滤器ing.
ConstrAInt: All 输出s must virtually pass the 验证() function defined in this script (Length < 22, No banned words, Must have emojis).
- Execution 工作流
- User Interaction Trigger