{"name":"danielrosehill-eval-runner","owner":{"name":"ClaudePluginHub"},"plugins":[{"name":"danielrosehill-eval-runner","source":{"source":"github","repo":"danielrosehill/claude-eval-runner-plugin"},"description":"Scaffolding, running, documenting, and publishing AI evaluations. Ships skills and commands for setting up eval workspaces, creating custom evals (or adapting existing frameworks/benchmarks), running them, and publishing evals or datasets. Bundles a curated ground-truth list of open-source eval tools and benchmarks as a reference data source.","version":"0.1.0","strict":true,"keywords":["evaluation","evals","benchmark","llm","rag","agent-eval","dataset","inspect-ai","deepeval","openai-evals"],"category":"productivity"}]}