You can make your AI assistant give better answers. This tool uses real data from your AI's past interactions to find the best way to ask it questions. It looks at how the AI responded and uses that feedback to improve your prompts automatically.
Anyone who works with AI prompts will find this useful. You can tune system messages, user instructions, or whole conversation templates. The tool runs an optimization loop based on actual performance signals like human ratings or automated evaluations.
You just need the ax CLI and a configured Arize profile. The skill extracts prompts from trace data, gathers signal, and applies changes to get better results. No need to guess what works.
Global
mkdir -p ~/.claude/skills/arize-prompt-optimizationProject
mkdir -p .claude/skills/arize-prompt-optimizationSource Repository
Cavemanjuliusbrussee/caveman
Talk like a smart caveman to save tokens without losing technical accuracy
Cavemanmattpocock/skills
Caveman mode for AI cuts token count 75% without losing technical accuracy
Enhance Promptgoogle-labs-code/stitch-skills
Turn vague UI ideas into clear, polished prompts with design system consistency
Humanizer Zhop7418/humanizer-zh
Remove AI writing patterns to make your text sound natural and human
Gws Modelarmorgoogleworkspace/cli
Filter harmful user content automatically with Google Model Armor for safety
Prompt Engineering Patternswshobson/agents
Master advanced prompt engineering patterns to get reliable and powerful AI outputs every time
Context Engineeringaddyosmani/agent-skills
Optimize your agent's context to improve output quality and focus
Writetw93/waza
Rewrite your prose to sound human and natural every time