SkillOpt v0.1.0: initial release

- Skill optimization framework with training loop analogy
- 11 benchmarks, 4 model backends (Azure OpenAI, Claude, Codex, Qwen)
- WebUI for browser-based training control
- Pluggable architecture for extending benchmarks and backends

skillopt/datasets/__init__.py

@@ -0,0 +1,7 @@
+"""ReflACT Datasets -- task batch planning and data loading.
+
+Analogous to the datasets and dataloaders in neural network training:
+provides batch sampling, epoch planning, and data management for the
+ReflACT training pipeline.
+"""
+from skillopt.datasets.base import BaseDataLoader, BatchSpec, SplitDataLoader  # noqa: F401