PluginEval
Scores a Claude Code skill on ten dimensions across static checks, an LLM judge and Monte Carlo runs.
Install
Ships scriptsClaude Code: /plugin marketplace add wshobson/agents → /plugin install plugin-eval@claude-code-workflows
Yazılan bir skill ya da eklentinin kalitesi ölçülürken, iki skill karşılaştırılırken ya da bir pazar yeri için puan eşiği belirlenirken
- Author
- Seth Hobson
- License
- MIT
Three layers stack, each more expensive than the last: a static pass that parses SKILL.md and finishes in under two seconds, an LLM judge that scores triggering, orchestration, output and scope in about thirty seconds, and a Monte Carlo layer that runs the skill fifty to a hundred times to estimate reliability. The static checks are opinionated in a way worth knowing before writing skills — progressive disclosure is measured against a 200 to 600 line sweet spot, and every detected anti-pattern multiplies the layer score down by another five percent, flooring at half. Results feed an Elo ranking against a corpus, so a skill is placed relative to its peers instead of against an absolute bar. It ships as a real Python package with a test suite, not just prompt files.
Similar skills
MLflow Skills
SkillCloses the loop for agent work: instrument, trace, evaluate, change, then verify the change helped.
DeepEval Skills
SkillEvaluation, tracing and OpenTelemetry export for LLM apps, split into three non-overlapping skills.
Claude Security
SkillDeep vulnerability scan of your own code, with every finding challenged before it is reported.
Comments(0)
Sign in to comment