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").
Agent workflow for generating highly diverse creative content using Verbalized Sampling (VS) technique. Use when user requests multiple variations, brainstorming, creative ideas, or when standard prompting produces repetitive outputs. Increases diversity by 1.6-2.1× while maintaining quality. Works for: blog posts, social media captions, stories, campaign ideas, product descriptions, taglines, and open-ended creative tasks. Source: rfxlamia/claude-skillkit.