prompt-evaluation
Skill / software-development
prompt-evaluation
Build and maintain prompt/agent evaluation harnesses: promptfoo suites, deterministic local providers, regression cases, rubric assertions, and CI-ready verification for Life OS, Hermes, McCoy, or other prompt-heavy systems.
How to use
This public page intentionally shows the skill name, category, and high-level description only. Full runtime instructions stay in Hermes where they can include operational guardrails.