@lovehlmmm/primekit 1.0.0

package/skills/document-skills/ak-xlsx/SKILL.md

@@ -0,0 +1,296 @@
+---
+name: pk:xlsx
+description: Create, edit, analyze spreadsheets (.xlsx, .csv, .tsv). Use for Excel formulas, data analysis, visualization, formatting, pivot tables, charts, formula recalculation.
+user-invocable: true
+when_to_use: "Invoke for spreadsheet analysis, formulas, charts, or edits."
+category: multimedia
+keywords: [xlsx, excel, spreadsheet, data]
+license: Proprietary. LICENSE.txt has complete terms
+metadata:
+  author: primekit
+  version: "1.0.0"
+---
+
+# Requirements for Outputs
+
+## All Excel files
+
+### Zero Formula Errors
+- Every Excel model MUST be delivered with ZERO formula errors (#REF!, #DIV/0!, #VALUE!, #N/A, #NAME?)
+
+### Preserve Existing Templates (when updating templates)
+- Study and EXACTLY match existing format, style, and conventions when modifying files
+- Never impose standardized formatting on files with established patterns
+- Existing template conventions ALWAYS override these guidelines
+
+## Financial models
+
+### Color Coding Standards
+Unless otherwise stated by the user or existing template
+
+#### Industry-Standard Color Conventions
+- **Blue text (RGB: 0,0,255)**: Hardcoded inputs, and numbers users will change for scenarios
+- **Black text (RGB: 0,0,0)**: ALL formulas and calculations
+- **Green text (RGB: 0,128,0)**: Links pulling from other worksheets within same workbook
+- **Red text (RGB: 255,0,0)**: External links to other files
+- **Yellow background (RGB: 255,255,0)**: Key assumptions needing attention or cells that need to be updated
+
+### Number Formatting Standards
+
+#### Required Format Rules
+- **Years**: Format as text strings (e.g., "2024" not "2,024")
+- **Currency**: Use $#,##0 format; ALWAYS specify units in headers ("Revenue ($mm)")
+- **Zeros**: Use number formatting to make all zeros "-", including percentages (e.g., "$#,##0;($#,##0);-")
+- **Percentages**: Default to 0.0% format (one decimal)
+- **Multiples**: Format as 0.0x for valuation multiples (EV/EBITDA, P/E)
+- **Negative numbers**: Use parentheses (123) not minus -123
+
+### Formula Construction Rules
+
+#### Assumptions Placement
+- Place ALL assumptions (growth rates, margins, multiples, etc.) in separate assumption cells
+- Use cell references instead of hardcoded values in formulas
+- Example: Use =B5*(1+$B$6) instead of =B5*1.05
+
+#### Formula Error Prevention
+- Verify all cell references are correct
+- Check for off-by-one errors in ranges
+- Ensure consistent formulas across all projection periods
+- Test with edge cases (zero values, negative numbers)
+- Verify no unintended circular references
+
+#### Documentation Requirements for Hardcodes
+- Comment or in cells beside (if end of table). Format: "Source: [System/Document], [Date], [Specific Reference], [URL if applicable]"
+- Examples:
+  - "Source: Company 10-K, FY2024, Page 45, Revenue Note, [SEC EDGAR URL]"
+  - "Source: Company 10-Q, Q2 2025, Exhibit 99.1, [SEC EDGAR URL]"
+  - "Source: Bloomberg Terminal, 8/15/2025, AAPL US Equity"
+  - "Source: FactSet, 8/20/2025, Consensus Estimates Screen"
+
+# XLSX creation, editing, and analysis
+
+## Overview
+
+A user may ask you to create, edit, or analyze the contents of an .xlsx file. You have different tools and workflows available for different tasks.
+
+## Important Requirements
+
+**LibreOffice Required for Formula Recalculation**: You can assume LibreOffice is installed for recalculating formula values using the `recalc.py` script. The script automatically configures LibreOffice on first run
+
+## Reading and analyzing data
+
+### Data analysis with pandas
+For data analysis, visualization, and basic operations, use **pandas** which provides powerful data manipulation capabilities:
+
+```python
+import pandas as pd
+
+# Read Excel
+df = pd.read_excel('file.xlsx')  # Default: first sheet
+all_sheets = pd.read_excel('file.xlsx', sheet_name=None)  # All sheets as dict
+
+# Analyze
+df.head()      # Preview data
+df.info()      # Column info
+df.describe()  # Statistics
+
+# Write Excel
+df.to_excel('output.xlsx', index=False)
+```
+
+## Excel File Workflows
+
+## CRITICAL: Use Formulas, Not Hardcoded Values
+
+**Always use Excel formulas instead of calculating values in Python and hardcoding them.** This ensures the spreadsheet remains dynamic and updateable.
+
+### ❌ WRONG - Hardcoding Calculated Values
+```python
+# Bad: Calculating in Python and hardcoding result
+total = df['Sales'].sum()
+sheet['B10'] = total  # Hardcodes 5000
+
+# Bad: Computing growth rate in Python
+growth = (df.iloc[-1]['Revenue'] - df.iloc[0]['Revenue']) / df.iloc[0]['Revenue']
+sheet['C5'] = growth  # Hardcodes 0.15
+
+# Bad: Python calculation for average
+avg = sum(values) / len(values)
+sheet['D20'] = avg  # Hardcodes 42.5
+```
+
+### ✅ CORRECT - Using Excel Formulas
+```python
+# Good: Let Excel calculate the sum
+sheet['B10'] = '=SUM(B2:B9)'
+
+# Good: Growth rate as Excel formula
+sheet['C5'] = '=(C4-C2)/C2'
+
+# Good: Average using Excel function
+sheet['D20'] = '=AVERAGE(D2:D19)'
+```
+
+This applies to ALL calculations - totals, percentages, ratios, differences, etc. The spreadsheet should be able to recalculate when source data changes.
+
+## Common Workflow
+1. **Choose tool**: pandas for data, openpyxl for formulas/formatting
+2. **Create/Load**: Create new workbook or load existing file
+3. **Modify**: Add/edit data, formulas, and formatting
+4. **Save**: Write to file
+5. **Recalculate formulas (MANDATORY IF USING FORMULAS)**: Use the recalc.py script
+   ```bash
+   python recalc.py output.xlsx
+   ```
+6. **Verify and fix any errors**: 
+   - The script returns JSON with error details
+   - If `status` is `errors_found`, check `error_summary` for specific error types and locations
+   - Fix the identified errors and recalculate again
+   - Common errors to fix:
+     - `#REF!`: Invalid cell references
+     - `#DIV/0!`: Division by zero
+     - `#VALUE!`: Wrong data type in formula
+     - `#NAME?`: Unrecognized formula name
+
+### Creating new Excel files
+
+```python
+# Using openpyxl for formulas and formatting
+from openpyxl import Workbook
+from openpyxl.styles import Font, PatternFill, Alignment
+
+wb = Workbook()
+sheet = wb.active
+
+# Add data
+sheet['A1'] = 'Hello'
+sheet['B1'] = 'World'
+sheet.append(['Row', 'of', 'data'])
+
+# Add formula
+sheet['B2'] = '=SUM(A1:A10)'
+
+# Formatting
+sheet['A1'].font = Font(bold=True, color='FF0000')
+sheet['A1'].fill = PatternFill('solid', start_color='FFFF00')
+sheet['A1'].alignment = Alignment(horizontal='center')
+
+# Column width
+sheet.column_dimensions['A'].width = 20
+
+wb.save('output.xlsx')
+```
+
+### Editing existing Excel files
+
+```python
+# Using openpyxl to preserve formulas and formatting
+from openpyxl import load_workbook
+
+# Load existing file
+wb = load_workbook('existing.xlsx')
+sheet = wb.active  # or wb['SheetName'] for specific sheet
+
+# Working with multiple sheets
+for sheet_name in wb.sheetnames:
+    sheet = wb[sheet_name]
+    print(f"Sheet: {sheet_name}")
+
+# Modify cells
+sheet['A1'] = 'New Value'
+sheet.insert_rows(2)  # Insert row at position 2
+sheet.delete_cols(3)  # Delete column 3
+
+# Add new sheet
+new_sheet = wb.create_sheet('NewSheet')
+new_sheet['A1'] = 'Data'
+
+wb.save('modified.xlsx')
+```
+
+## Recalculating formulas
+
+Excel files created or modified by openpyxl contain formulas as strings but not calculated values. Use the provided `recalc.py` script to recalculate formulas:
+
+```bash
+python recalc.py <excel_file> [timeout_seconds]
+```
+
+Example:
+```bash
+python recalc.py output.xlsx 30
+```
+
+The script:
+- Automatically sets up LibreOffice macro on first run
+- Recalculates all formulas in all sheets
+- Scans ALL cells for Excel errors (#REF!, #DIV/0!, etc.)
+- Returns JSON with detailed error locations and counts
+- Works on both Linux and macOS
+
+## Formula Verification Checklist
+
+Quick checks to ensure formulas work correctly:
+
+### Essential Verification
+- [ ] **Test 2-3 sample references**: Verify they pull correct values before building full model
+- [ ] **Column mapping**: Confirm Excel columns match (e.g., column 64 = BL, not BK)
+- [ ] **Row offset**: Remember Excel rows are 1-indexed (DataFrame row 5 = Excel row 6)
+
+### Common Pitfalls
+- [ ] **NaN handling**: Check for null values with `pd.notna()`
+- [ ] **Far-right columns**: FY data often in columns 50+ 
+- [ ] **Multiple matches**: Search all occurrences, not just first
+- [ ] **Division by zero**: Check denominators before using `/` in formulas (#DIV/0!)
+- [ ] **Wrong references**: Verify all cell references point to intended cells (#REF!)
+- [ ] **Cross-sheet references**: Use correct format (Sheet1!A1) for linking sheets
+
+### Formula Testing Strategy
+- [ ] **Start small**: Test formulas on 2-3 cells before applying broadly
+- [ ] **Verify dependencies**: Check all cells referenced in formulas exist
+- [ ] **Test edge cases**: Include zero, negative, and very large values
+
+### Interpreting recalc.py Output
+The script returns JSON with error details:
+```json
+{
+  "status": "success",           // or "errors_found"
+  "total_errors": 0,              // Total error count
+  "total_formulas": 42,           // Number of formulas in file
+  "error_summary": {              // Only present if errors found
+    "#REF!": {
+      "count": 2,
+      "locations": ["Sheet1!B5", "Sheet1!C10"]
+    }
+  }
+}
+```
+
+## Best Practices
+
+### Library Selection
+- **pandas**: Best for data analysis, bulk operations, and simple data export
+- **openpyxl**: Best for complex formatting, formulas, and Excel-specific features
+
+### Working with openpyxl
+- Cell indices are 1-based (row=1, column=1 refers to cell A1)
+- Use `data_only=True` to read calculated values: `load_workbook('file.xlsx', data_only=True)`
+- **Warning**: If opened with `data_only=True` and saved, formulas are replaced with values and permanently lost
+- For large files: Use `read_only=True` for reading or `write_only=True` for writing
+- Formulas are preserved but not evaluated - use recalc.py to update values
+
+### Working with pandas
+- Specify data types to avoid inference issues: `pd.read_excel('file.xlsx', dtype={'id': str})`
+- For large files, read specific columns: `pd.read_excel('file.xlsx', usecols=['A', 'C', 'E'])`
+- Handle dates properly: `pd.read_excel('file.xlsx', parse_dates=['date_column'])`
+
+## Code Style Guidelines
+**IMPORTANT**: When generating Python code for Excel operations:
+- Write minimal, concise Python code without unnecessary comments
+- Avoid verbose variable names and redundant operations
+- Avoid unnecessary print statements
+
+**For Excel files themselves**:
+- Add comments to cells with complex formulas or important assumptions
+- Document data sources for hardcoded values
+- Include notes for key calculations and model sections

package/skills/document-skills/ak-xlsx/recalc.py

@@ -0,0 +1,191 @@
+#!/usr/bin/env python3
+"""
+Excel Formula Recalculation Script
+Recalculates all formulas in an Excel file using LibreOffice
+"""
+
+import json
+import sys
+import subprocess
+import os
+import platform
+from pathlib import Path
+
+# Windows UTF-8 compatibility (works for both local and global installs)
+CLAUDE_ROOT = Path(__file__).parent.parent.parent.parent
+sys.path.insert(0, str(CLAUDE_ROOT / 'scripts'))
+try:
+    from win_compat import ensure_utf8_stdout
+    ensure_utf8_stdout()
+except ImportError:
+    if sys.platform == 'win32':
+        import io
+        if hasattr(sys.stdout, 'buffer'):
+            sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8')
+
+from openpyxl import load_workbook
+
+
+def setup_libreoffice_macro():
+    """Setup LibreOffice macro for recalculation if not already configured"""
+    if platform.system() == 'Darwin':
+        macro_dir = os.path.expanduser('~/Library/Application Support/LibreOffice/4/user/basic/Standard')
+    else:
+        macro_dir = os.path.expanduser('~/.config/libreoffice/4/user/basic/Standard')
+    
+    macro_file = os.path.join(macro_dir, 'Module1.xba')
+    
+    if os.path.exists(macro_file):
+        with open(macro_file, 'r') as f:
+            if 'RecalculateAndSave' in f.read():
+                return True
+    
+    if not os.path.exists(macro_dir):
+        subprocess.run(['soffice', '--headless', '--terminate_after_init'], 
+                      capture_output=True, timeout=10)
+        os.makedirs(macro_dir, exist_ok=True)
+    
+    macro_content = '''<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE script:module PUBLIC "-//OpenOffice.org//DTD OfficeDocument 1.0//EN" "module.dtd">
+<script:module xmlns:script="http://openoffice.org/2000/script" script:name="Module1" script:language="StarBasic">
+    Sub RecalculateAndSave()
+      ThisComponent.calculateAll()
+      ThisComponent.store()
+      ThisComponent.close(True)
+    End Sub
+</script:module>'''
+    
+    try:
+        with open(macro_file, 'w') as f:
+            f.write(macro_content)
+        return True
+    except Exception:
+        return False
+
+
+def recalc(filename, timeout=30):
+    """
+    Recalculate formulas in Excel file and report any errors
+    
+    Args:
+        filename: Path to Excel file
+        timeout: Maximum time to wait for recalculation (seconds)
+    
+    Returns:
+        dict with error locations and counts
+    """
+    if not Path(filename).exists():
+        return {'error': f'File {filename} does not exist'}
+    
+    abs_path = str(Path(filename).absolute())
+    
+    if not setup_libreoffice_macro():
+        return {'error': 'Failed to setup LibreOffice macro'}
+    
+    cmd = [
+        'soffice', '--headless', '--norestore',
+        'vnd.sun.star.script:Standard.Module1.RecalculateAndSave?language=Basic&location=application',
+        abs_path
+    ]
+    
+    # Handle timeout command differences between Linux and macOS
+    if platform.system() != 'Windows':
+        timeout_cmd = 'timeout' if platform.system() == 'Linux' else None
+        if platform.system() == 'Darwin':
+            # Check if gtimeout is available on macOS
+            try:
+                subprocess.run(['gtimeout', '--version'], capture_output=True, timeout=1, check=False)
+                timeout_cmd = 'gtimeout'
+            except (FileNotFoundError, subprocess.TimeoutExpired):
+                pass
+        
+        if timeout_cmd:
+            cmd = [timeout_cmd, str(timeout)] + cmd
+    
+    result = subprocess.run(cmd, capture_output=True, text=True)
+    
+    if result.returncode != 0 and result.returncode != 124:  # 124 is timeout exit code
+        error_msg = result.stderr or 'Unknown error during recalculation'
+        if 'Module1' in error_msg or 'RecalculateAndSave' not in error_msg:
+            return {'error': 'LibreOffice macro not configured properly'}
+        else:
+            return {'error': error_msg}
+    
+    # Check for Excel errors in the recalculated file - scan ALL cells
+    try:
+        wb = load_workbook(filename, data_only=True)
+        
+        excel_errors = ['#VALUE!', '#DIV/0!', '#REF!', '#NAME?', '#NULL!', '#NUM!', '#N/A']
+        error_details = {err: [] for err in excel_errors}
+        total_errors = 0
+        
+        for sheet_name in wb.sheetnames:
+            ws = wb[sheet_name]
+            # Check ALL rows and columns - no limits
+            for row in ws.iter_rows():
+                for cell in row:
+                    if cell.value is not None and isinstance(cell.value, str):
+                        for err in excel_errors:
+                            if err in cell.value:
+                                location = f"{sheet_name}!{cell.coordinate}"
+                                error_details[err].append(location)
+                                total_errors += 1
+                                break
+        
+        wb.close()
+        
+        # Build result summary
+        result = {
+            'status': 'success' if total_errors == 0 else 'errors_found',
+            'total_errors': total_errors,
+            'error_summary': {}
+        }
+        
+        # Add non-empty error categories
+        for err_type, locations in error_details.items():
+            if locations:
+                result['error_summary'][err_type] = {
+                    'count': len(locations),
+                    'locations': locations[:20]  # Show up to 20 locations
+                }
+        
+        # Add formula count for context - also check ALL cells
+        wb_formulas = load_workbook(filename, data_only=False)
+        formula_count = 0
+        for sheet_name in wb_formulas.sheetnames:
+            ws = wb_formulas[sheet_name]
+            for row in ws.iter_rows():
+                for cell in row:
+                    if cell.value and isinstance(cell.value, str) and cell.value.startswith('='):
+                        formula_count += 1
+        wb_formulas.close()
+        
+        result['total_formulas'] = formula_count
+        
+        return result
+        
+    except Exception as e:
+        return {'error': str(e)}
+
+
+def main():
+    if len(sys.argv) < 2:
+        print("Usage: python recalc.py <excel_file> [timeout_seconds]")
+        print("\nRecalculates all formulas in an Excel file using LibreOffice")
+        print("\nReturns JSON with error details:")
+        print("  - status: 'success' or 'errors_found'")
+        print("  - total_errors: Total number of Excel errors found")
+        print("  - total_formulas: Number of formulas in the file")
+        print("  - error_summary: Breakdown by error type with locations")
+        print("    - #VALUE!, #DIV/0!, #REF!, #NAME?, #NULL!, #NUM!, #N/A")
+        sys.exit(1)
+    
+    filename = sys.argv[1]
+    timeout = int(sys.argv[2]) if len(sys.argv) > 2 else 30
+    
+    result = recalc(filename, timeout)
+    print(json.dumps(result, indent=2))
+
+
+if __name__ == '__main__':
+    main()

package/skills/excalidraw/SKILL.md

@@ -0,0 +1,210 @@
+---
+name: pk:excalidraw
+description: >-
+  Create Excalidraw diagrams — architecture, data flow, workflows, system design.
+  Use when user wants to visualize, diagram, draw architecture, show data flow,
+  create flowcharts, map components, or export .excalidraw files to PNG/SVG.
+  Supports two modes: live MCP canvas (real-time) or file-based JSON + Playwright
+  rendering. Also supports zero-config codebase auto-diagramming — just say
+  "diagram this repo" or "visualize the architecture".
+user-invocable: true
+when_to_use: "Invoke for editable canvas diagrams or codebase visual maps."
+category: dev-tools
+keywords: [diagrams, architecture, flowcharts, whiteboard, SVG]
+metadata:
+  author: primekit
+  version: "1.2.0"
+---
+
+# Excalidraw Diagram Skill
+
+Generate diagrams that **argue visually** — shapes mirror meaning, not just labeled boxes.
+
+## Mode Detection (Do This First)
+
+This skill supports two rendering backends. Detect which is available:
+
+**Mode A — MCP Canvas (preferred):** Test with `mcp__excalidraw__read_diagram_guide()`.
+If it works, use MCP tools for live canvas editing. See `references/mcp-workflow.md`.
+
+**Mode B — File-based (fallback):** Generate `.excalidraw` JSON files, render to PNG
+via Playwright. No server needed. See `references/file-workflow.md`.
+
+If neither is set up, guide the user through setup (see respective workflow files).
+
+---
+
+## Core Philosophy
+
+**Diagrams should ARGUE, not DISPLAY.**
+
+- **Isomorphism Test**: Remove all text — does the structure alone communicate the concept?
+- **Education Test**: Could someone learn something concrete, or does it just label boxes?
+- **Container Test**: Could any boxed element work as free-floating text? If yes, remove the box.
+
+Default to free-floating text. Add containers only when shapes carry meaning.
+Aim for <30% of text elements inside containers.
+
+---
+
+## Design Process (Before Generating Anything)
+
+### Step 0: Assess Depth
+
+| Simple/Conceptual | Comprehensive/Technical |
+|---|---|
+| Abstract shapes, labels, relationships | Concrete examples, code snippets, real data |
+| Mental models, philosophies | Systems, architectures, tutorials |
+| ~30 seconds to explain | ~2-3 minutes of teaching |
+
+**For technical diagrams**: Research actual specs, event names, APIs before drawing.
+Include evidence artifacts. See `references/design-methodology.md`.
+
+### Step 1: Map Concepts to Visual Patterns
+
+| Concept behavior | Pattern |
+|---|---|
+| Spawns multiple outputs | **Fan-out** (radial arrows) |
+| Combines inputs into one | **Convergence** (funnel) |
+| Has hierarchy/nesting | **Tree** (lines + text, no boxes) |
+| Sequence of steps | **Timeline** (line + dots + labels) |
+| Loops/improves continuously | **Spiral/Cycle** |
+| Abstract state/context | **Cloud** (overlapping ellipses) |
+| Transforms input→output | **Assembly line** (before→process→after) |
+| Compares two things | **Side-by-side** |
+| Separates into phases | **Gap/Break** |
+
+Each major concept should use a **different** visual pattern — no uniform card grids.
+
+### Step 2: Plan Layout
+
+Guide the eye: typically left→right or top→bottom. Important elements get more whitespace.
+
+### Step 3: Generate & Validate
+
+Follow the workflow for your active mode (MCP or file-based).
+
+---
+
+## Auto-Diagram (Zero-Config Codebase Analysis)
+
+When user says "diagram this repo", "visualize the architecture", or "auto diagram":
+
+Follow the full pipeline in `references/auto-diagram-guide.md`:
+1. **Detect** project type and framework
+2. **Discover** components (max 15 tool calls)
+3. **Map** connections (max 10 tool calls)
+4. **Verify** with user before drawing
+5. **Select** layout pattern
+6. **Generate** diagram using active mode
+
+**Limits**: Max 12 components, 20 arrows per diagram. Group if more found.
+
+---
+
+## Color Quick Reference
+
+Pull colors from `references/color-palette.md` (single source of truth).
+
+| Role | Background | Stroke |
+|---|---|---|
+| Frontend/UI | `#a5d8ff` | `#1971c2` |
+| Backend/API | `#d0bfff` | `#7048e8` |
+| Database | `#b2f2bb` | `#2f9e44` |
+| Storage | `#ffec99` | `#f08c00` |
+| AI/ML | `#e599f7` | `#9c36b5` |
+| External API | `#ffc9c9` | `#e03131` |
+| Queue/Event | `#fff3bf` | `#fab005` |
+| Cache | `#ffe8cc` | `#fd7e14` |
+| Decision | `#ffd8a8` | `#e8590c` |
+| Zone/Group | `#e9ecef` | `#868e96` |
+
+**Rule**: Same-role shapes get same colors. Max 3-4 fill colors per diagram.
+
+---
+
+## Shape Reference
+
+| Concept | Shape | Why |
+|---|---|---|
+| Labels, descriptions | **none** (free text) | Typography = hierarchy |
+| Timeline markers | small `ellipse` (10-20px) | Anchor, not container |
+| Start/trigger/input | `ellipse` | Soft, origin-like |
+| Decision/condition | `diamond` | Classic decision |
+| Process/action/step | `rectangle` | Contained action |
+| Abstract state | overlapping `ellipse` | Cloud-like |
+
+---
+
+## Sizing Rules
+
+**Err on the side of too much space.** Tight spacing is the #1 mistake.
+
+| Property | Value |
+|---|---|
+| Box width | 200-240px |
+| Box height | 120-160px |
+| Gap (labeled arrows) | **150-200px** |
+| Gap (unlabeled arrows) | 100-120px |
+| Row spacing | 280-350px |
+| Font (labels) | 16px |
+| Font (titles) | 20-24px |
+| Zone opacity | 25-40 |
+| Zone padding | 50-60px around children |
+
+---
+
+## Modern Aesthetics
+
+- `roughness: 0` for clean/modern (default), `1` for hand-drawn
+- `strokeWidth: 2` standard, `1` subtle, `3` emphasis
+- `opacity: 100` always — use color/size for hierarchy, not transparency
+- `fontFamily: 3` (monospace)
+- Arrow labels: `strokeStyle: "dashed"` for async, `"dotted"` for weak deps
+
+---
+
+## Self-Critique Loop (Both Modes)
+
+After generating, validate before presenting:
+
+1. **Render/screenshot** — view the actual output
+2. **Audit vs. vision** — does structure match the planned design?
+3. **Check defects** — overlaps, clipped text, misrouted arrows, uneven spacing
+4. **Fix** — adjust coordinates, widen containers, reroute arrows
+5. **Re-render** — repeat until clean (typically 2-4 iterations, max 2 for MCP)
+
+**Stop when**: no clipped text, arrows connect correctly, spacing consistent, balanced composition.
+
+---
+
+## Quality Checklist
+
+- [ ] Research done (for technical diagrams)
+- [ ] Evidence artifacts included (code snippets, real data)
+- [ ] Multi-zoom: summary + sections + detail
+- [ ] Each concept uses different visual pattern
+- [ ] Minimal containers (<30% text in boxes)
+- [ ] Lines as structure for trees/timelines
+- [ ] All relationships have arrows
+- [ ] Clear visual flow path
+- [ ] `roughness: 0`, `opacity: 100`, `fontFamily: 3`
+- [ ] Rendered and visually validated
+- [ ] No overlapping/clipped elements
+- [ ] Balanced composition
+
+---
+
+## References (Load As Needed)
+
+| File | Content |
+|---|---|
+| `references/design-methodology.md` | Deep design philosophy, evidence artifacts, multi-zoom, large diagram strategy |
+| `references/mcp-workflow.md` | MCP canvas tools, batch creation, examples, self-critique |
+| `references/file-workflow.md` | JSON generation, section-by-section, render script usage |
+| `references/auto-diagram-guide.md` | Zero-config codebase analysis pipeline |
+| `references/color-palette.md` | All colors: semantic, platform (AWS/Azure/GCP/K8s), text hierarchy |
+| `references/element-templates.md` | Copy-paste JSON templates for file-based mode |
+| `references/json-schema.md` | Excalidraw JSON format reference |
+
+For universal SVG layout rules that apply across any rendered SVG output, load `/pk:tech-graph` and apply its spacing, arrow routing, label placement, and z-index ordering guidance. Useful when reviewing exported Excalidraw SVGs for collisions or unreadable labels.