Darwin-skill is a meta-skill (SKILL.md) and supporting tooling for autonomously optimizing agent skills (SKILL.md files). It implements a ratchet-based hill-climbing loop that evaluates skills across 9 dimensions (structure, effectiveness, meta-skill), spawns independent LLM judges for paired comparison, and only retains improvements validated by human-in-the-loop checkpoints. The repo includes a Node.js screenshot script for generating result cards, HTML templates, documentation, and references integrating Microsoft Research's SkillLens and SkillOpt papers. Despite being primarily a markdown document, it exhibits high craftsmanship: rigorous empirical grounding, explicit anti-pattern blacklist, versioned design philosophy, and detailed operational procedures. The actual executable code is minimal (one utility script), but the skill definition itself is a sophisticated artifact that demonstrates deep understanding of LLM evaluation pitfalls and optimization strategies.