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

requirements.txt

@@ -0,0 +1,25 @@
+# ── Core ──────────────────────────────────────────
+openai>=1.30.0
+pyyaml>=6.0
+numpy>=1.24.0
+openpyxl>=3.1.0
+azure-identity>=1.15.0
+azure-core>=1.30.0
+httpx>=0.27.0
+
+# ── Optional: ALFWorld benchmark ──────────────────
+# alfworld>=0.4.0
+# gymnasium>=0.29.0
+
+# ── Optional: Claude model backend ────────────────
+# claude-agent-sdk>=0.1.0
+
+# ── Optional: Qwen local model (via vLLM) ────────
+# vllm>=0.4.0
+
+# ── Optional: WebUI dashboard ────────────────────
+# gradio>=4.0.0
+
+# ── Optional: Documentation site ─────────────────
+# mkdocs-material>=9.5.0
+# mkdocstrings[python]>=0.24.0