Vibe Coding DiscoverSkill2Env
View on GitHubDemocratizing Collective Intelligence
Skill2Env converts Agent Skills into Docker-based, host-validated terminal-agent tasks in Harbor format, ready for reinforcement learning or dataset publication. It uses Codex agents to plan and create tasks.
Use Cases
Generate RL-ready terminal tasks from Agent SkillsBuild and validate agent task datasetsPublish generated tasks to Harbor Hub
Built With
- Language
- Python
- Frameworks
- Harbor · Codex CLI
Tags
agent evaluation · RL tasks · task generation · terminal agents · Agent Skills · benchmarking · Docker