@brookmind/ai-toolkit 1.0.5 → 1.1.2

package/skills/pdf/scripts/fill_pdf_form_with_annotations.py

@@ -1,108 +0,0 @@
-import json
-import sys
-
-from pypdf import PdfReader, PdfWriter
-from pypdf.annotations import FreeText
-
-
-# Fills a PDF by adding text annotations defined in `fields.json`. See forms.md.
-
-
-def transform_coordinates(bbox, image_width, image_height, pdf_width, pdf_height):
-    """Transform bounding box from image coordinates to PDF coordinates"""
-    # Image coordinates: origin at top-left, y increases downward
-    # PDF coordinates: origin at bottom-left, y increases upward
-    x_scale = pdf_width / image_width
-    y_scale = pdf_height / image_height
-    
-    left = bbox[0] * x_scale
-    right = bbox[2] * x_scale
-    
-    # Flip Y coordinates for PDF
-    top = pdf_height - (bbox[1] * y_scale)
-    bottom = pdf_height - (bbox[3] * y_scale)
-    
-    return left, bottom, right, top
-
-
-def fill_pdf_form(input_pdf_path, fields_json_path, output_pdf_path):
-    """Fill the PDF form with data from fields.json"""
-    
-    # `fields.json` format described in forms.md.
-    with open(fields_json_path, "r") as f:
-        fields_data = json.load(f)
-    
-    # Open the PDF
-    reader = PdfReader(input_pdf_path)
-    writer = PdfWriter()
-    
-    # Copy all pages to writer
-    writer.append(reader)
-    
-    # Get PDF dimensions for each page
-    pdf_dimensions = {}
-    for i, page in enumerate(reader.pages):
-        mediabox = page.mediabox
-        pdf_dimensions[i + 1] = [mediabox.width, mediabox.height]
-    
-    # Process each form field
-    annotations = []
-    for field in fields_data["form_fields"]:
-        page_num = field["page_number"]
-        
-        # Get page dimensions and transform coordinates.
-        page_info = next(p for p in fields_data["pages"] if p["page_number"] == page_num)
-        image_width = page_info["image_width"]
-        image_height = page_info["image_height"]
-        pdf_width, pdf_height = pdf_dimensions[page_num]
-        
-        transformed_entry_box = transform_coordinates(
-            field["entry_bounding_box"],
-            image_width, image_height,
-            pdf_width, pdf_height
-        )
-        
-        # Skip empty fields
-        if "entry_text" not in field or "text" not in field["entry_text"]:
-            continue
-        entry_text = field["entry_text"]
-        text = entry_text["text"]
-        if not text:
-            continue
-        
-        font_name = entry_text.get("font", "Arial")
-        font_size = str(entry_text.get("font_size", 14)) + "pt"
-        font_color = entry_text.get("font_color", "000000")
-
-        # Font size/color seems to not work reliably across viewers:
-        # https://github.com/py-pdf/pypdf/issues/2084
-        annotation = FreeText(
-            text=text,
-            rect=transformed_entry_box,
-            font=font_name,
-            font_size=font_size,
-            font_color=font_color,
-            border_color=None,
-            background_color=None,
-        )
-        annotations.append(annotation)
-        # page_number is 0-based for pypdf
-        writer.add_annotation(page_number=page_num - 1, annotation=annotation)
-        
-    # Save the filled PDF
-    with open(output_pdf_path, "wb") as output:
-        writer.write(output)
-    
-    print(f"Successfully filled PDF form and saved to {output_pdf_path}")
-    print(f"Added {len(annotations)} text annotations")
-
-
-if __name__ == "__main__":
-    if len(sys.argv) != 4:
-        print("Usage: fill_pdf_form_with_annotations.py [input pdf] [fields.json] [output pdf]")
-        sys.exit(1)
-    input_pdf = sys.argv[1]
-    fields_json = sys.argv[2]
-    output_pdf = sys.argv[3]
-    
-    fill_pdf_form(input_pdf, fields_json, output_pdf)

package/skills/xlsx/LICENSE.txt

@@ -1,30 +0,0 @@
-© 2025 Anthropic, PBC. All rights reserved.
-
-LICENSE: Use of these materials (including all code, prompts, assets, files,
-and other components of this Skill) is governed by your agreement with
-Anthropic regarding use of Anthropic's services. If no separate agreement
-exists, use is governed by Anthropic's Consumer Terms of Service or
-Commercial Terms of Service, as applicable:
-https://www.anthropic.com/legal/consumer-terms
-https://www.anthropic.com/legal/commercial-terms
-Your applicable agreement is referred to as the "Agreement." "Services" are
-as defined in the Agreement.
-
-ADDITIONAL RESTRICTIONS: Notwithstanding anything in the Agreement to the
-contrary, users may not:
-
-- Extract these materials from the Services or retain copies of these
-  materials outside the Services
-- Reproduce or copy these materials, except for temporary copies created
-  automatically during authorized use of the Services
-- Create derivative works based on these materials
-- Distribute, sublicense, or transfer these materials to any third party
-- Make, offer to sell, sell, or import any inventions embodied in these
-  materials
-- Reverse engineer, decompile, or disassemble these materials
-
-The receipt, viewing, or possession of these materials does not convey or
-imply any license or right beyond those expressly granted above.
-
-Anthropic retains all right, title, and interest in these materials,
-including all copyrights, patents, and other intellectual property rights.

package/skills/xlsx/SKILL.md

@@ -1,289 +0,0 @@
----
-name: xlsx
-description: "Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas"
-license: Proprietary. LICENSE.txt has complete terms
----
-
-# 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/xlsx/recalc.py

@@ -1,178 +0,0 @@
-#!/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
-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()