Tag
An article discussing methods for evaluating skills to build better agent tools, likely focusing on practical approaches for AI agent development.
Skill RSI is a free tool that recursively evaluates and improves AI skills via procedural evaluations and a research agent, supporting standalone or Codex plugin usage.
A developer built SkillBenchmark, a tool to objectively measure whether Claude Code skills like Caveman actually improve LLM output quality, revealing that Caveman shows no statistically significant quality improvement despite increased token cost.
OpenSkillEval is an automatic evaluation framework for auditing open-source skills used by LLM agents across multiple downstream tasks. Using over 600 dynamically generated tasks and 30 skills, the authors find that skill availability does not guarantee effective usage and that benefits depend heavily on the model and framework.