Quantifying prompt quality using information theory: entropy and mutual information analysis of 1,800 LLM generations
Scores how well an AI coding agent can understand your prompt -- against your actual repository -- for zero context tokens
Prompt Engineering Tool: Anti-Ambiguity × Web Pre-Search × ELO Ranking — forge production-grade AI prompts for Claude, GPT, and agent systems
📊 Explore how Shannon entropy and mutual information can quantify prompt quality in generative AI systems across various temperature settings.
Claude Code plugin that scores how well you prompt a coding agent, and shows whether your habits are improving. Runs on TypeSafe's Jev model. Zero added latency.
Automatically corrects, translates and enhances user prompts before submission to an LLM Model via OpenCode or Claude Code.
40 AI deviation engines × 14 sigma rungs — push LLM output past the generic median. Cognitive, nature, and physics layers for AI content generation.
Multi-judge static quality scoring for LLM prompt libraries, with inter-judge agreement as a per-prompt confidence signal.
Local-first Agent collaboration quality CLI and Codex plugin for intent diagnosis, evals, safety gates, and confirmation-gated learning.
To associate your repository with the prompt-quality topic, visit your repo's landing page and select "manage topics."