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

configs/livemathematicianbench/default.yaml

@@ -0,0 +1,22 @@
+_base_: ../_base_/default.yaml
+
+train:
+  train_size: 0
+  batch_size: 40
+  accumulation: 1
+
+env:
+  name: livemathematicianbench
+  skill_init: skillopt/envs/livemathematicianbench/skills/initial.md
+  split_mode: split_dir
+  split_ratio: "2:1:7"
+  split_dir: data/ablation_splits/livemathematicianbench/2-1-7_seed42
+  data_path: ""
+  split_output_dir: ""
+  max_turns: 1
+  exec_timeout: 300
+  workers: 64
+  limit: 0
+  shuffle_choices: true
+  use_theorem: false
+  use_sketch: false