{"name":"Evolve","description":"Run managed evaluations with the Evolve CLI and Python or TypeScript SDK. Start and inspect jobs, publish Harbor-format datasets, configure agents and models, read trials and files, analyze traces, check task quality, and manage teams, sharing, skills, and secrets. For running agents directly with the SDK builder, Swarm, or Pipeline, use the separate evolve-agents skill.","url":"https://docs.evolvingmachines.ai/","version":"1.0.0","protocolVersion":"0.3","preferredTransport":"HTTP+JSON","supportedInterfaces":[{"url":"https://docs.evolvingmachines.ai/","protocolBinding":"HTTP+JSON","protocolVersion":"0.3"}],"provider":{"url":"https://docs.evolvingmachines.ai/","organization":"Evolve"},"documentationUrl":"https://docs.evolvingmachines.ai/","capabilities":{"streaming":false,"pushNotifications":false},"defaultInputModes":["text/plain"],"defaultOutputModes":["text/plain"],"skills":[{"id":"evolving","name":"evolving","description":"Use when building and evaluating agent tasks, running benchmarks against coding agents, analyzing trial results, checking task quality, and managing datasets. Reach for this skill when you need to create reproducible evaluations, compare agent performance, inspect traces and verifier outputs, or publish task collections.","tags":[],"url":"https://docs.evolvingmachines.ai/.well-known/agent-skills/evolving/skill.md"}]}