When Better Prompts Hurt

Evaluation-driven prompt iteration using the Define-Test-Diagnose-Fix loop and Minimum Viable Evaluation Suite (MVES). Prevents regressions when changing LLM prompts by building structured test suites before iterating. Use when: 'evaluate my prompts', 'my prompt change broke something', 'build a test suite for my LLM app', 'why did my improved prompt make results worse', 'set up eval for my RAG pipeline', 'create evaluation harness for my agent'.

ndpvt-web Updated 14 repo stars

File contents

ndpvt-web/arxiv-claude-skills commit 651a5e515a

Frequently asked questions

npx get-skill add ndpvt-web/when-better-prompts-hurt