rl environments skills

9 tagged rl environments, measured the same way as everything else here.

Browse within: evals 9terminal-bench 9

create-adapter

01

harbor-framework/harbor

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.

4.8k 2d ago A 34 tokens original Apache-2.0

rewardkit

02

harbor-framework/harbor

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.

4.8k 2d ago A 46 tokens original Apache-2.0

harbor-framework/harbor

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.

4.8k 2d ago A 49 tokens original Apache-2.0