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/__main__.py

@@ -0,0 +1,28 @@
+"""
+CLI for the Atomizer Template Registry.
+"""
+
+from . import list_templates, list_categories, format_template_summary, get_template
+
+
+def main():
+    print("=== Atomizer Template Registry ===\n")
+
+    for category_id, category in list_categories().items():
+        # Use ASCII-safe icons for Windows compatibility
+        icon = "[" + category_id[:3].upper() + "]"
+        print(f"{icon} {category['name']}")
+        print(f"   {category['description']}\n")
+
+    print("\n=== Available Templates ===\n")
+
+    for t in list_templates():
+        status = "[TURBO]" if t["turbo_suitable"] else "[FEA]"
+        print(f"{status} {t['name']} ({t['id']})")
+        print(f"   {t['description']}")
+        print(f"   Objectives: {t['n_objectives']} | Example: {t['example_study'] or 'N/A'}")
+        print()
+
+
+if __name__ == "__main__":
+    main()