Create Task

Walks you through building a Harbor task from scratch, which means creating the instruction prompt, setting up the Docker environment, writing a verifier (usually the hardest part), and scripting a reference solution. The guidance is opinionated about verifier choice: it nudges you toward Reward Kit for multi-criteria grading, pytest for straightforward assertions, or plain shell for single-command checks. Useful if you're designing agent benchmarks or evals and need help structuring the pieces, especially around network policies, timeout configs, and the difference between shared versus separate verifier environments. The step-by-step format keeps you from dumping half-baked scaffolding and forgetting to test the Dockerfile interactively.

Install to Claude Code

npx -y skills add harbor-framework/harbor --skill create-task --agent claude-code