@mseep/open-computer-use 1.0.0

package/skills/public/pdf/scripts/create_validation_image.py

@@ -0,0 +1,41 @@
+import json
+import sys
+
+from PIL import Image, ImageDraw
+
+
+# Creates "validation" images with rectangles for the bounding box information that
+# Assistant creates when determining where to add text annotations in PDFs. See FORMS.md.
+
+
+def create_validation_image(page_number, fields_json_path, input_path, output_path):
+    # Input file should be in the `fields.json` format described in FORMS.md.
+    with open(fields_json_path, 'r') as f:
+        data = json.load(f)
+
+        img = Image.open(input_path)
+        draw = ImageDraw.Draw(img)
+        num_boxes = 0
+        
+        for field in data["form_fields"]:
+            if field["page_number"] == page_number:
+                entry_box = field['entry_bounding_box']
+                label_box = field['label_bounding_box']
+                # Draw red rectangle over entry bounding box and blue rectangle over the label.
+                draw.rectangle(entry_box, outline='red', width=2)
+                draw.rectangle(label_box, outline='blue', width=2)
+                num_boxes += 2
+        
+        img.save(output_path)
+        print(f"Created validation image at {output_path} with {num_boxes} bounding boxes")
+
+
+if __name__ == "__main__":
+    if len(sys.argv) != 5:
+        print("Usage: create_validation_image.py [page number] [fields.json file] [input image path] [output image path]")
+        sys.exit(1)
+    page_number = int(sys.argv[1])
+    fields_json_path = sys.argv[2]
+    input_image_path = sys.argv[3]
+    output_image_path = sys.argv[4]
+    create_validation_image(page_number, fields_json_path, input_image_path, output_image_path)

package/skills/public/pdf/scripts/extract_form_field_info.py

@@ -0,0 +1,152 @@
+import json
+import sys
+
+from pypdf import PdfReader
+
+
+# Extracts data for the fillable form fields in a PDF and outputs JSON that
+# Assistant uses to fill the fields. See FORMS.md.
+
+
+# This matches the format used by PdfReader `get_fields` and `update_page_form_field_values` methods.
+def get_full_annotation_field_id(annotation):
+    components = []
+    while annotation:
+        field_name = annotation.get('/T')
+        if field_name:
+            components.append(field_name)
+        annotation = annotation.get('/Parent')
+    return ".".join(reversed(components)) if components else None
+
+
+def make_field_dict(field, field_id):
+    field_dict = {"field_id": field_id}
+    ft = field.get('/FT')
+    if ft == "/Tx":
+        field_dict["type"] = "text"
+    elif ft == "/Btn":
+        field_dict["type"] = "checkbox"  # radio groups handled separately
+        states = field.get("/_States_", [])
+        if len(states) == 2:
+            # "/Off" seems to always be the unchecked value, as suggested by
+            # https://opensource.adobe.com/dc-acrobat-sdk-docs/standards/pdfstandards/pdf/PDF32000_2008.pdf#page=448
+            # It can be either first or second in the "/_States_" list.
+            if "/Off" in states:
+                field_dict["checked_value"] = states[0] if states[0] != "/Off" else states[1]
+                field_dict["unchecked_value"] = "/Off"
+            else:
+                print(f"Unexpected state values for checkbox `${field_id}`. Its checked and unchecked values may not be correct; if you're trying to check it, visually verify the results.")
+                field_dict["checked_value"] = states[0]
+                field_dict["unchecked_value"] = states[1]
+    elif ft == "/Ch":
+        field_dict["type"] = "choice"
+        states = field.get("/_States_", [])
+        field_dict["choice_options"] = [{
+            "value": state[0],
+            "text": state[1],
+        } for state in states]
+    else:
+        field_dict["type"] = f"unknown ({ft})"
+    return field_dict
+
+
+# Returns a list of fillable PDF fields:
+# [
+#   {
+#     "field_id": "name",
+#     "page": 1,
+#     "type": ("text", "checkbox", "radio_group", or "choice")
+#     // Per-type additional fields described in FORMS.md
+#   },
+# ]
+def get_field_info(reader: PdfReader):
+    fields = reader.get_fields()
+
+    field_info_by_id = {}
+    possible_radio_names = set()
+
+    for field_id, field in fields.items():
+        # Skip if this is a container field with children, except that it might be
+        # a parent group for radio button options.
+        if field.get("/Kids"):
+            if field.get("/FT") == "/Btn":
+                possible_radio_names.add(field_id)
+            continue
+        field_info_by_id[field_id] = make_field_dict(field, field_id)
+
+    # Bounding rects are stored in annotations in page objects.
+
+    # Radio button options have a separate annotation for each choice;
+    # all choices have the same field name.
+    # See https://westhealth.github.io/exploring-fillable-forms-with-pdfrw.html
+    radio_fields_by_id = {}
+
+    for page_index, page in enumerate(reader.pages):
+        annotations = page.get('/Annots', [])
+        for ann in annotations:
+            field_id = get_full_annotation_field_id(ann)
+            if field_id in field_info_by_id:
+                field_info_by_id[field_id]["page"] = page_index + 1
+                field_info_by_id[field_id]["rect"] = ann.get('/Rect')
+            elif field_id in possible_radio_names:
+                try:
+                    # ann['/AP']['/N'] should have two items. One of them is '/Off',
+                    # the other is the active value.
+                    on_values = [v for v in ann["/AP"]["/N"] if v != "/Off"]
+                except KeyError:
+                    continue
+                if len(on_values) == 1:
+                    rect = ann.get("/Rect")
+                    if field_id not in radio_fields_by_id:
+                        radio_fields_by_id[field_id] = {
+                            "field_id": field_id,
+                            "type": "radio_group",
+                            "page": page_index + 1,
+                            "radio_options": [],
+                        }
+                    # Note: at least on macOS 15.7, Preview.app doesn't show selected
+                    # radio buttons correctly. (It does if you remove the leading slash
+                    # from the value, but that causes them not to appear correctly in
+                    # Chrome/Firefox/Acrobat/etc).
+                    radio_fields_by_id[field_id]["radio_options"].append({
+                        "value": on_values[0],
+                        "rect": rect,
+                    })
+
+    # Some PDFs have form field definitions without corresponding annotations,
+    # so we can't tell where they are. Ignore these fields for now.
+    fields_with_location = []
+    for field_info in field_info_by_id.values():
+        if "page" in field_info:
+            fields_with_location.append(field_info)
+        else:
+            print(f"Unable to determine location for field id: {field_info.get('field_id')}, ignoring")
+
+    # Sort by page number, then Y position (flipped in PDF coordinate system), then X.
+    def sort_key(f):
+        if "radio_options" in f:
+            rect = f["radio_options"][0]["rect"] or [0, 0, 0, 0]
+        else:
+            rect = f.get("rect") or [0, 0, 0, 0]
+        adjusted_position = [-rect[1], rect[0]]
+        return [f.get("page"), adjusted_position]
+    
+    sorted_fields = fields_with_location + list(radio_fields_by_id.values())
+    sorted_fields.sort(key=sort_key)
+
+    return sorted_fields
+
+
+def write_field_info(pdf_path: str, json_output_path: str):
+    reader = PdfReader(pdf_path)
+    field_info = get_field_info(reader)
+    with open(json_output_path, "w") as f:
+        json.dump(field_info, f, indent=2)
+    print(f"Wrote {len(field_info)} fields to {json_output_path}")
+
+
+if __name__ == "__main__":
+    if len(sys.argv) != 3:
+        print("Usage: extract_form_field_info.py [input pdf] [output json]")
+        sys.exit(1)
+    write_field_info(sys.argv[1], sys.argv[2])

package/skills/public/pdf/scripts/fill_fillable_fields.py

@@ -0,0 +1,114 @@
+import json
+import sys
+
+from pypdf import PdfReader, PdfWriter
+
+from extract_form_field_info import get_field_info
+
+
+# Fills fillable form fields in a PDF. See FORMS.md.
+
+
+def fill_pdf_fields(input_pdf_path: str, fields_json_path: str, output_pdf_path: str):
+    with open(fields_json_path) as f:
+        fields = json.load(f)
+    # Group by page number.
+    fields_by_page = {}
+    for field in fields:
+        if "value" in field:
+            field_id = field["field_id"]
+            page = field["page"]
+            if page not in fields_by_page:
+                fields_by_page[page] = {}
+            fields_by_page[page][field_id] = field["value"]
+    
+    reader = PdfReader(input_pdf_path)
+
+    has_error = False
+    field_info = get_field_info(reader)
+    fields_by_ids = {f["field_id"]: f for f in field_info}
+    for field in fields:
+        existing_field = fields_by_ids.get(field["field_id"])
+        if not existing_field:
+            has_error = True
+            print(f"ERROR: `{field['field_id']}` is not a valid field ID")
+        elif field["page"] != existing_field["page"]:
+            has_error = True
+            print(f"ERROR: Incorrect page number for `{field['field_id']}` (got {field['page']}, expected {existing_field['page']})")
+        else:
+            if "value" in field:
+                err = validation_error_for_field_value(existing_field, field["value"])
+                if err:
+                    print(err)
+                    has_error = True
+    if has_error:
+        sys.exit(1)
+
+    writer = PdfWriter(clone_from=reader)
+    for page, field_values in fields_by_page.items():
+        writer.update_page_form_field_values(writer.pages[page - 1], field_values, auto_regenerate=False)
+
+    # This seems to be necessary for many PDF viewers to format the form values correctly.
+    # It may cause the viewer to show a "save changes" dialog even if the user doesn't make any changes.
+    writer.set_need_appearances_writer(True)
+    
+    with open(output_pdf_path, "wb") as f:
+        writer.write(f)
+
+
+def validation_error_for_field_value(field_info, field_value):
+    field_type = field_info["type"]
+    field_id = field_info["field_id"]
+    if field_type == "checkbox":
+        checked_val = field_info["checked_value"]
+        unchecked_val = field_info["unchecked_value"]
+        if field_value != checked_val and field_value != unchecked_val:
+            return f'ERROR: Invalid value "{field_value}" for checkbox field "{field_id}". The checked value is "{checked_val}" and the unchecked value is "{unchecked_val}"'
+    elif field_type == "radio_group":
+        option_values = [opt["value"] for opt in field_info["radio_options"]]
+        if field_value not in option_values:
+            return f'ERROR: Invalid value "{field_value}" for radio group field "{field_id}". Valid values are: {option_values}' 
+    elif field_type == "choice":
+        choice_values = [opt["value"] for opt in field_info["choice_options"]]
+        if field_value not in choice_values:
+            return f'ERROR: Invalid value "{field_value}" for choice field "{field_id}". Valid values are: {choice_values}'
+    return None
+
+
+# pypdf (at least version 5.7.0) has a bug when setting the value for a selection list field.
+# In _writer.py around line 966:
+#
+# if field.get(FA.FT, "/Tx") == "/Ch" and field_flags & FA.FfBits.Combo == 0:
+#     txt = "\n".join(annotation.get_inherited(FA.Opt, []))
+#
+# The problem is that for selection lists, `get_inherited` returns a list of two-element lists like
+# [["value1", "Text 1"], ["value2", "Text 2"], ...]
+# This causes `join` to throw a TypeError because it expects an iterable of strings.
+# The horrible workaround is to patch `get_inherited` to return a list of the value strings.
+# We call the original method and adjust the return value only if the argument to `get_inherited`
+# is `FA.Opt` and if the return value is a list of two-element lists.
+def monkeypatch_pydpf_method():
+    from pypdf.generic import DictionaryObject
+    from pypdf.constants import FieldDictionaryAttributes
+
+    original_get_inherited = DictionaryObject.get_inherited
+
+    def patched_get_inherited(self, key: str, default = None):
+        result = original_get_inherited(self, key, default)
+        if key == FieldDictionaryAttributes.Opt:
+            if isinstance(result, list) and all(isinstance(v, list) and len(v) == 2 for v in result):
+                result = [r[0] for r in result]
+        return result
+
+    DictionaryObject.get_inherited = patched_get_inherited
+
+
+if __name__ == "__main__":
+    if len(sys.argv) != 4:
+        print("Usage: fill_fillable_fields.py [input pdf] [field_values.json] [output pdf]")
+        sys.exit(1)
+    monkeypatch_pydpf_method()
+    input_pdf = sys.argv[1]
+    fields_json = sys.argv[2]
+    output_pdf = sys.argv[3]
+    fill_pdf_fields(input_pdf, fields_json, output_pdf)

package/skills/public/pdf/scripts/fill_pdf_form_with_annotations.py

@@ -0,0 +1,108 @@
+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/public/pdf-reading/LICENSE.txt

@@ -0,0 +1,30 @@
+© 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/public/pdf-reading/REFERENCE.md

@@ -0,0 +1,196 @@
+# PDF Processing Advanced Reference
+
+This document contains advanced PDF processing features, detailed examples, and additional libraries not covered in the main skill instructions.
+
+## pypdfium2 Library (Apache/BSD License)
+
+### Overview
+pypdfium2 is a Python binding for PDFium (Chromium's PDF library). It's excellent for fast PDF rendering, image generation, and serves as a PyMuPDF replacement.
+
+### Render PDF to Images
+```python
+import pypdfium2 as pdfium
+from PIL import Image
+
+# Load PDF
+pdf = pdfium.PdfDocument("document.pdf")
+
+# Render page to image
+page = pdf[0]  # First page
+bitmap = page.render(
+    scale=2.0,  # Higher resolution
+    rotation=0  # No rotation
+)
+
+# Convert to PIL Image
+img = bitmap.to_pil()
+img.save("page_1.png", "PNG")
+
+# Process multiple pages
+for i, page in enumerate(pdf):
+    bitmap = page.render(scale=1.5)
+    img = bitmap.to_pil()
+    img.save(f"page_{i+1}.jpg", "JPEG", quality=90)
+```
+
+### Extract Text with pypdfium2
+```python
+import pypdfium2 as pdfium
+
+pdf = pdfium.PdfDocument("document.pdf")
+for i, page in enumerate(pdf):
+    textpage = page.get_textpage()
+    text = textpage.get_text_range()
+    print(f"Page {i+1} text length: {len(text)} chars")
+```
+
+## Advanced Command-Line Operations
+
+### poppler-utils Advanced Features
+
+#### Extract Text with Bounding Box Coordinates
+```bash
+# Extract text with bounding box coordinates (essential for structured data)
+pdftotext -bbox-layout document.pdf output.xml
+
+# The XML output contains precise coordinates for each text element
+```
+
+#### Advanced Image Conversion
+```bash
+# Convert to PNG images with specific resolution
+pdftoppm -png -r 300 document.pdf output_prefix
+
+# Convert specific page range with high resolution
+pdftoppm -png -r 600 -f 1 -l 3 document.pdf high_res_pages
+
+# Convert to JPEG with quality setting
+pdftoppm -jpeg -jpegopt quality=85 -r 200 document.pdf jpeg_output
+```
+
+#### Extract Embedded Images
+```bash
+# Extract all embedded images with metadata
+pdfimages -j -p document.pdf page_images
+
+# List image info without extracting
+pdfimages -list document.pdf
+
+# Extract images in their original format
+pdfimages -all document.pdf images/img
+```
+
+### qpdf Advanced Features
+
+For qpdf page manipulation, optimization, encryption, and repair,
+see `/mnt/skills/public/pdf/SKILL.md`.
+
+Useful qpdf reading/inspection commands:
+```bash
+# Check PDF structure for errors
+qpdf --check input.pdf
+
+# Show detailed PDF structure for debugging
+qpdf --show-pages input.pdf > structure.txt
+
+# Check encryption status
+qpdf --show-encryption encrypted.pdf
+
+# Remove password protection (requires password) for reading
+qpdf --password=secret123 --decrypt encrypted.pdf decrypted.pdf
+```
+
+## Advanced Python Techniques
+
+### pdfplumber Advanced Features
+
+#### Extract Text with Precise Coordinates
+```python
+import pdfplumber
+
+with pdfplumber.open("document.pdf") as pdf:
+    page = pdf.pages[0]
+    
+    # Extract all text with coordinates
+    chars = page.chars
+    for char in chars[:10]:  # First 10 characters
+        print(f"Char: '{char['text']}' at x:{char['x0']:.1f} y:{char['y0']:.1f}")
+    
+    # Extract text by bounding box (left, top, right, bottom)
+    bbox_text = page.within_bbox((100, 100, 400, 200)).extract_text()
+```
+
+#### Advanced Table Extraction with Custom Settings
+```python
+import pdfplumber
+import pandas as pd
+
+with pdfplumber.open("complex_table.pdf") as pdf:
+    page = pdf.pages[0]
+    
+    # Extract tables with custom settings for complex layouts
+    table_settings = {
+        "vertical_strategy": "lines",
+        "horizontal_strategy": "lines",
+        "snap_tolerance": 3,
+        "intersection_tolerance": 15
+    }
+    tables = page.extract_tables(table_settings)
+    
+    # Visual debugging for table extraction
+    img = page.to_image(resolution=150)
+    img.save("debug_layout.png")
+```
+
+## Performance Optimization Tips
+
+- `pdftotext` (CLI) is fastest for plain text extraction (`-layout` for spatial positioning)
+- Use pdfplumber for structured data and tables; avoid `pypdf.extract_text()` on very large documents
+- `pdfimages` is much faster than rendering pages for image extraction
+- For large PDFs, process pages individually rather than loading everything into memory
+
+## Troubleshooting Common Issues
+
+### Encrypted PDFs
+```python
+# Handle password-protected PDFs
+from pypdf import PdfReader
+
+try:
+    reader = PdfReader("encrypted.pdf")
+    if reader.is_encrypted:
+        reader.decrypt("password")
+except Exception as e:
+    print(f"Failed to decrypt: {e}")
+```
+
+### Corrupted PDFs
+```bash
+# Use qpdf to repair
+qpdf --check corrupted.pdf
+qpdf --replace-input corrupted.pdf
+```
+
+### Text Extraction Issues
+```python
+# Fallback to OCR for scanned PDFs
+import pytesseract
+from pdf2image import convert_from_path
+
+def extract_text_with_ocr(pdf_path):
+    images = convert_from_path(pdf_path)
+    text = ""
+    for i, image in enumerate(images):
+        text += pytesseract.image_to_string(image)
+    return text
+```
+
+## License Information
+
+- **pypdf**: BSD License
+- **pdfplumber**: MIT License
+- **pypdfium2**: Apache/BSD License
+- **PyMuPDF (fitz)**: AGPL-3.0 License — copyleft; commercial licenses available from Artifex
+- **poppler-utils**: GPL-2 License
+- **qpdf**: Apache License
+- **pytesseract**: Apache License (Tesseract engine: Apache License)