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/envs/officeqa/skills/initial.md

@@ -0,0 +1,15 @@
+# OfficeQA Skill
+
+## Retrieval Discipline
+- Start by narrowing to the most likely candidate file before reading long passages.
+- Prefer targeted search terms that name the exact entity, period, measure, or table concept from the question.
+- After a promising match, read only a small surrounding span and verify it matches the requested year, basis, and unit.
+
+## Evidence Discipline
+- Extract the exact value from the retrieved text before doing any arithmetic.
+- Keep track of each operand's period, unit, and semantic role so nearby proxy values are not mixed in.
+- If the question asks for a transformed or derived quantity, compute only after confirming every operand.
+
+## Final Answer Discipline
+- Return the final answer only after one last consistency check against the retrieved evidence.
+- Copy the final answer from a checked value, not from an unverified intermediate guess.