feat: Add Studio UI, intake system, and extractor improvements

Dashboard:
- Add Studio page with drag-drop model upload and Claude chat
- Add intake system for study creation workflow
- Improve session manager and context builder
- Add intake API routes and frontend components

Optimization Engine:
- Add CLI module for command-line operations
- Add intake module for study preprocessing
- Add validation module with gate checks
- Improve Zernike extractor documentation
- Update spec models with better validation
- Enhance solve_simulation robustness

Documentation:
- Add ATOMIZER_STUDIO.md planning doc
- Add ATOMIZER_UX_SYSTEM.md for UX patterns
- Update extractor library docs
- Add study-readme-generator skill

Tools:
- Add test scripts for extraction validation
- Add Zernike recentering test

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

.claude/skills/01_CHEATSHEET.md

@@ -1,7 +1,7 @@
 ---
 skill_id: SKILL_001
-version: 2.4
-last_updated: 2025-12-31
+version: 2.5
+last_updated: 2026-01-22
 type: reference
 code_dependencies:
   - optimization_engine/extractors/__init__.py
@@ -14,8 +14,8 @@ requires_skills:
 
 # Atomizer Quick Reference Cheatsheet
 
-**Version**: 2.4
-**Updated**: 2025-12-31
+**Version**: 2.5
+**Updated**: 2026-01-22
 **Purpose**: Rapid lookup for common operations. "I want X → Use Y"
 
 ---
@@ -37,6 +37,8 @@ requires_skills:
 | **Use SAT (Self-Aware Turbo)** | **SYS_16** | SAT v3 for high-efficiency neural-accelerated optimization |
 | Generate physics insight | SYS_17 | `python -m optimization_engine.insights generate <study>` |
 | **Manage knowledge/playbook** | **SYS_18** | `from optimization_engine.context import AtomizerPlaybook` |
+| **Automate dev tasks** | **DevLoop** | `python tools/devloop_cli.py start "task"` |
+| **Test dashboard UI** | **DevLoop** | `python tools/devloop_cli.py browser --level full` |
 
 ---
 
@@ -678,6 +680,67 @@ feedback.process_trial_result(
 
 ---
 
+## DevLoop Quick Reference
+
+Closed-loop development system using AI agents + Playwright testing.
+
+### CLI Commands
+
+| Task | Command |
+|------|---------|
+| Full dev cycle | `python tools/devloop_cli.py start "Create new study"` |
+| Plan only | `python tools/devloop_cli.py plan "Fix validation"` |
+| Implement plan | `python tools/devloop_cli.py implement` |
+| Test study files | `python tools/devloop_cli.py test --study support_arm` |
+| Analyze failures | `python tools/devloop_cli.py analyze` |
+| Browser smoke test | `python tools/devloop_cli.py browser` |
+| Browser full tests | `python tools/devloop_cli.py browser --level full` |
+| Check status | `python tools/devloop_cli.py status` |
+| Quick test | `python tools/devloop_cli.py quick` |
+
+### Browser Test Levels
+
+| Level | Description | Tests |
+|-------|-------------|-------|
+| `quick` | Smoke test (page loads) | 1 |
+| `home` | Home page verification | 2 |
+| `full` | All UI + study tests | 5+ |
+| `study` | Canvas/dashboard for specific study | 3 |
+
+### State Files (`.devloop/`)
+
+| File | Purpose |
+|------|---------|
+| `current_plan.json` | Current implementation plan |
+| `test_results.json` | Filesystem/API test results |
+| `browser_test_results.json` | Playwright test results |
+| `analysis.json` | Failure analysis |
+
+### Prerequisites
+
+```bash
+# Start backend
+cd atomizer-dashboard/backend && python -m uvicorn api.main:app --reload --port 8000
+
+# Start frontend
+cd atomizer-dashboard/frontend && npm run dev
+
+# Install Playwright (once)
+cd atomizer-dashboard/frontend && npx playwright install chromium
+```
+
+### Standalone Playwright Tests
+
+```bash
+cd atomizer-dashboard/frontend
+npm run test:e2e          # Run all E2E tests
+npm run test:e2e:ui       # Playwright UI mode
+```
+
+**Full documentation**: `docs/guides/DEVLOOP.md`
+
+---
+
 ## Report Generation Quick Reference (OP_08)
 
 Generate comprehensive study reports from optimization data.