diverse-content-gen

This skill teaches agents how to use Verbalized Sampling (VS) - a research-backed prompting technique that dramatically increases output diversity (1.6-2.1× improvement) without sacrificing quality.

The Problem: Standard aligned LLMs suffer from "mode collapse" - they generate overly similar, safe, predictable outputs because of typicality bias in training data.

The Solution: Instead of asking for single instances ("write a blog post"), VS prompts the model to verbalize a probability distribution over multiple responses ("generate 5 blog post ideas with their probabilities").

使用言语采样 (VS) 技术生成高度多样化的创意内容的代理工作流程。当用户请求多种变化、集思广益、创造性想法时，或者当标准提示产生重复输出时使用。在保持质量的同时将多样性提高 1.6-2.1 倍。适用于：博客文章、社交媒体标题、故事、活动创意、产品描述、口号和开放式创意任务。 来源：rfxlamia/claude-skillkit。