Prompt Lab

Test, validate, and improve agent instructions (CLAUDE.md, system prompts) using sub-agents as experiment subjects. Measures instruction compliance, context decay, and constraint strength. Use for "test prompt", "validate instructions", "prompt effectiveness", "instruction decay", or when designing robust agent behaviors.

lidessen Updated

File contents

lidessen/moniro commit b4668b9ec0

Frequently asked questions

npx get-skill add lidessen/prompt-lab