SkillOpt — Controlled Skill Optimization for Hermes Agent

Optimize any Hermes skill document using a rigorous, methodology-driven pipeline inspired by Microsoft Research's SkillOpt paper (Yifan Yang et al., 2025). The core insight: evaluate skill changes by measuring task execution, not by reading the skill text.

When to Use This Skill

• A skill exists but its performance is inconsistent — sometimes it works, sometimes it doesn't
• You want to improve a skill but aren't sure which changes will actually help
• You've proposed edits to a skill and want to validate them before deploying
• You maintain multiple skills and want a repeatable process for quality improvement
• You're curious whether a skill change actually improved anything (the surface-plausibility trap)

SkillOpt is designed for skills with measurable task outcomes. For creative skills (image generation, writing) where "correctness" is subjective, the methodology still works but the validation criteria need thoughtful definition.

Documentation Boundary for SkillOpt Itself

When optimizing ordinary target skills, keep this SKILL.md focused on always-on agent operating guidance: when to run SkillOpt, phase routing, validation gates, artifact discipline, failure classification, and merge/revert rules.

When maintaining or optimizing the SkillOpt repository itself, keep these surfaces separate: