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").

使用言語採樣 (VS) 技術產生高度多樣化的創意內容的代理工作流程。當使用者要求多種變更、集思廣益、創造性想法時，或當標準提示產生重複輸出時使用。在保持品質的同時將多樣性提高 1.6-2.1 倍。適用於：部落格文章、社群媒體標題、故事、活動創意、產品描述、口號和開放式創意任務。 來源：rfxlamia/claude-skillkit。