Darwin Skill
Meta skill that optimizes your other skills: it takes an existing skill, runs it on cases, evaluates the result, proposes an improved version, tests it, then keeps the improvement or rolls back if it regresses. An evaluate → improve → test → keep-or-revert loop, inspired by Karpathy's autoresearch (an agent that self-improves in a loop). Integrates SkillOpt (Microsoft), published on PyPI v0.1.0 since June 3, 2026 (`pip install skillopt`). The pitch: Darwin optimizes your skills while you sleep.
Strengths
- Evolutionary loop with rollback: only versions proven better are kept
- Integrates SkillOpt (Microsoft), available on PyPI (`pip install skillopt`): a tooled optimization base
- Automates a tedious tuning job nobody does by hand on their skills
Limitations
- Without a representative evaluation set, it optimizes for the wrong metric: the test harness is your responsibility
- Recent and niche: little production feedback, be cautious before automating it on critical skills
Best for
- Skill builders who already have an internal library and want to harden it without manual tuning
- AI platform teams industrializing the maintenance of a shared skill catalog
- Tech leads curious about the self-improving agent pattern wanting a concrete case to experiment with