{"name":"HeyBee","description":"Benchmark, optimize, and train AI systems with real human judgments.","url":"https://docs.heybee.app/","version":"1.0.0","protocolVersion":"0.3","preferredTransport":"HTTP+JSON","supportedInterfaces":[{"url":"https://docs.heybee.app/","protocolBinding":"HTTP+JSON","protocolVersion":"0.3"}],"provider":{"url":"https://docs.heybee.app/","organization":"HeyBee"},"documentationUrl":"https://docs.heybee.app/","capabilities":{"streaming":false,"pushNotifications":false},"defaultInputModes":["text/plain"],"defaultOutputModes":["text/plain"],"skills":[{"id":"heybee","name":"heybee","description":"Use when building evaluation workflows to collect human judgments on AI outputs, benchmark models or prompts, optimize generation parameters, or generate training data for RLHF. Reach for this skill when you need to run A/B tests, compare candidates, score outputs, or export preference data.","tags":[],"url":"https://docs.heybee.app/.well-known/agent-skills/heybee/skill.md"}]}