feat: Implement Agentic Architecture for robust session workflows

Phase 1 - Session Bootstrap:
- Add .claude/ATOMIZER_CONTEXT.md as single entry point for new sessions
- Add study state detection and task routing

Phase 2 - Code Deduplication:
- Add optimization_engine/base_runner.py (ConfigDrivenRunner)
- Add optimization_engine/generic_surrogate.py (ConfigDrivenSurrogate)
- Add optimization_engine/study_state.py for study detection
- Add optimization_engine/templates/ with registry and templates
- Studies now require ~50 lines instead of ~300

Phase 3 - Skill Consolidation:
- Add YAML frontmatter metadata to all skills (versioning, dependencies)
- Consolidate create-study.md into core/study-creation-core.md
- Update 00_BOOTSTRAP.md, 01_CHEATSHEET.md, 02_CONTEXT_LOADER.md

Phase 4 - Self-Expanding Knowledge:
- Add optimization_engine/auto_doc.py for auto-generating documentation
- Generate docs/generated/EXTRACTORS.md (27 extractors documented)
- Generate docs/generated/TEMPLATES.md (6 templates)
- Generate docs/generated/EXTRACTOR_CHEATSHEET.md

Phase 5 - Subagent Implementation:
- Add .claude/commands/study-builder.md (create studies)
- Add .claude/commands/nx-expert.md (NX Open API)
- Add .claude/commands/protocol-auditor.md (config validation)
- Add .claude/commands/results-analyzer.md (results analysis)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

optimization_engine/templates/run_optimization_template.py

@@ -0,0 +1,41 @@
+#!/usr/bin/env python
+"""
+{STUDY_NAME} - Optimization Script (Simplified)
+================================================================
+
+This script uses the ConfigDrivenRunner for config-driven optimization.
+The ~300 lines of boilerplate code is now handled automatically.
+
+Workflow:
+---------
+1. python run_optimization.py --discover    # Model introspection
+2. python run_optimization.py --validate    # Single trial validation
+3. python run_optimization.py --test        # Quick 3-trial test
+4. python run_optimization.py --run         # Full optimization
+
+Generated by Atomizer StudyWizard
+"""
+
+from pathlib import Path
+import sys
+
+# Add project root to path
+project_root = Path(__file__).resolve().parents[2]
+sys.path.insert(0, str(project_root))
+
+from optimization_engine.base_runner import ConfigDrivenRunner
+
+
+def main():
+    """Run optimization using config-driven runner."""
+    # Create runner - all config read from optimization_config.json
+    runner = ConfigDrivenRunner(__file__)
+
+    # Element type: 'auto' detects from DAT file
+    # Override if needed: runner.element_type = 'cquad4' (shell) or 'ctetra' (solid)
+
+    return runner.run()
+
+
+if __name__ == "__main__":
+    exit(main())