SkillOpt introduces a method for improving AI agent performance by treating skills as external state, allowing a frozen agent to be evaluated on scored batches while a separate optimizer model proposes structured edits. The system only accepts a new skill candidate when validation performance shows measurable improvement, eliminating the need for model fine-tuning or manual prompt maintenance. This approach enables continuous, automated skill evolution without altering the underlying agent model.
Instead of fine-tuning a model or hand-maintaining prompts, SkillOpt runs the frozen agent on scored batches, asks a separate optimizer model to propose structured edits, and accepts a candidate only when validation performance improves.
EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.