Skill Claude CodeCodex
Scaffold a new Harbor benchmark adapter by running harbor adapter init and then guide implementation using the Adapters Agent Guide as the authoritative spec.
15 tagged terminal-bench, measured the same way as everything else here.
Browse within: evals 9rl-environments 9fable5 6long-horizon-agents 6long-horizon-tasks 6long-horizon-terminal-bench 6
Skill Claude CodeCodex
Scaffold a new Harbor benchmark adapter by running harbor adapter init and then guide implementation using the Adapters Agent Guide as the authoritative spec.
Skill Claude CodeCodex
Write Harbor task verifiers using Reward Kit. Use when creating or editing a task's tests/ directory, adding grading criteria, setting up LLM/agent judges, or designing verifiers that produce a reward score.
Skill Claude CodeCodex
Create or reuse Hugging Face dataset PRs for harborframework/parity-experiments and upload Harbor parity/oracle result folders efficiently with sparse checkout, raw git pushes, and Git LFS.
Skill Claude CodeCodex
Scaffold a new Harbor benchmark adapter by running harbor adapter init and then guide implementation using the Adapters Agent Guide as the authoritative spec.
Skill Claude CodeCodex
Publish a Harbor task or dataset to the registry. Use when the user wants to upload, publish, or share tasks or datasets/benchmarks on the Harbor registry.
Skill Claude CodeCodex
Write Harbor task verifiers using Reward Kit. Use when creating or editing a task's tests/ directory, adding grading criteria, setting up LLM/agent judges, or designing verifiers that produce a reward score.