wowdespacito/anthropics_skills
1
0
Fork 0
mirror of https://github.com/anthropics/skills.git synced 2026-08-02 13:05:28 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update docx, xlsx, pdf, pptx skills with latest improvements (#330)

Browse Source 
docx: Add commenting and track-changes support. Reorganize OOXML
tooling into a shared office/ module.

pptx: Streamline SKILL.md, add slide-editing and pptxgenjs guides,
bundle html2pptx as a tgz. Reorganize OOXML tooling into a shared
office/ module.

xlsx: Move recalc script into scripts/ and expand it. Add shared
office/ module for OOXML pack/unpack/validate.

pdf: Improve form-filling workflow with new form-structure extraction
script and updated field-info extraction.
This commit is contained in:
Keith Lazuka
2026-02-03 21:09:36 -05:00
committed by GitHub
parent 69c0b1a067
commit 4e6907a33c
202 changed files with 28554 additions and 9472 deletions
Download Patch File Download Diff File Expand all files Collapse all files
skills/pdf/scripts/check_bounding_boxes.py
-5
View File
@@ -3,8 +3,6 @@ import json
import sys
# Script to check that the `fields.json` file that Claude creates when analyzing PDFs
# does not have overlapping bounding boxes. See forms.md.
@dataclass
@@ -14,7 +12,6 @@ class RectAndField:
field: dict
# Returns a list of messages that are printed to stdout for Claude to read.
def get_bounding_box_messages(fields_json_stream) -> list[str]:
messages = []
fields = json.load(fields_json_stream)
@@ -32,7 +29,6 @@ def get_bounding_box_messages(fields_json_stream) -> list[str]:
has_error = False
for i, ri in enumerate(rects_and_fields):
# This is O(N^2); we can optimize if it becomes a problem.
for j in range(i + 1, len(rects_and_fields)):
rj = rects_and_fields[j]
if ri.field["page_number"] == rj.field["page_number"] and rects_intersect(ri.rect, rj.rect):
@@ -63,7 +59,6 @@ if __name__ == "__main__":
if len(sys.argv) != 2:
print("Usage: check_bounding_boxes.py [fields.json]")
sys.exit(1)
# Input file should be in the `fields.json` format described in forms.md.
with open(sys.argv[1]) as f:
messages = get_bounding_box_messages(f)
for msg in messages:
skills/pdf/scripts/check_bounding_boxes_test.py
-226
View File
@@ -1,226 +0,0 @@
import unittest
import json
import io
from check_bounding_boxes import get_bounding_box_messages
# Currently this is not run automatically in CI; it's just for documentation and manual checking.
class TestGetBoundingBoxMessages(unittest.TestCase):
def create_json_stream(self, data):
"""Helper to create a JSON stream from data"""
return io.StringIO(json.dumps(data))
def test_no_intersections(self):
"""Test case with no bounding box intersections"""
data = {
"form_fields": [
{
"description": "Name",
"page_number": 1,
"label_bounding_box": [10, 10, 50, 30],
"entry_bounding_box": [60, 10, 150, 30]
},
{
"description": "Email",
"page_number": 1,
"label_bounding_box": [10, 40, 50, 60],
"entry_bounding_box": [60, 40, 150, 60]
}
]
}
stream = self.create_json_stream(data)
messages = get_bounding_box_messages(stream)
self.assertTrue(any("SUCCESS" in msg for msg in messages))
self.assertFalse(any("FAILURE" in msg for msg in messages))
def test_label_entry_intersection_same_field(self):
"""Test intersection between label and entry of the same field"""
data = {
"form_fields": [
{
"description": "Name",
"page_number": 1,
"label_bounding_box": [10, 10, 60, 30],
"entry_bounding_box": [50, 10, 150, 30] # Overlaps with label
}
]
}
stream = self.create_json_stream(data)
messages = get_bounding_box_messages(stream)
self.assertTrue(any("FAILURE" in msg and "intersection" in msg for msg in messages))
self.assertFalse(any("SUCCESS" in msg for msg in messages))
def test_intersection_between_different_fields(self):
"""Test intersection between bounding boxes of different fields"""
data = {
"form_fields": [
{
"description": "Name",
"page_number": 1,
"label_bounding_box": [10, 10, 50, 30],
"entry_bounding_box": [60, 10, 150, 30]
},
{
"description": "Email",
"page_number": 1,
"label_bounding_box": [40, 20, 80, 40], # Overlaps with Name's boxes
"entry_bounding_box": [160, 10, 250, 30]
}
]
}
stream = self.create_json_stream(data)
messages = get_bounding_box_messages(stream)
self.assertTrue(any("FAILURE" in msg and "intersection" in msg for msg in messages))
self.assertFalse(any("SUCCESS" in msg for msg in messages))
def test_different_pages_no_intersection(self):
"""Test that boxes on different pages don't count as intersecting"""
data = {
"form_fields": [
{
"description": "Name",
"page_number": 1,
"label_bounding_box": [10, 10, 50, 30],
"entry_bounding_box": [60, 10, 150, 30]
},
{
"description": "Email",
"page_number": 2,
"label_bounding_box": [10, 10, 50, 30], # Same coordinates but different page
"entry_bounding_box": [60, 10, 150, 30]
}
]
}
stream = self.create_json_stream(data)
messages = get_bounding_box_messages(stream)
self.assertTrue(any("SUCCESS" in msg for msg in messages))
self.assertFalse(any("FAILURE" in msg for msg in messages))
def test_entry_height_too_small(self):
"""Test that entry box height is checked against font size"""
data = {
"form_fields": [
{
"description": "Name",
"page_number": 1,
"label_bounding_box": [10, 10, 50, 30],
"entry_bounding_box": [60, 10, 150, 20], # Height is 10
"entry_text": {
"font_size": 14 # Font size larger than height
}
}
]
}
stream = self.create_json_stream(data)
messages = get_bounding_box_messages(stream)
self.assertTrue(any("FAILURE" in msg and "height" in msg for msg in messages))
self.assertFalse(any("SUCCESS" in msg for msg in messages))
def test_entry_height_adequate(self):
"""Test that adequate entry box height passes"""
data = {
"form_fields": [
{
"description": "Name",
"page_number": 1,
"label_bounding_box": [10, 10, 50, 30],
"entry_bounding_box": [60, 10, 150, 30], # Height is 20
"entry_text": {
"font_size": 14 # Font size smaller than height
}
}
]
}
stream = self.create_json_stream(data)
messages = get_bounding_box_messages(stream)
self.assertTrue(any("SUCCESS" in msg for msg in messages))
self.assertFalse(any("FAILURE" in msg for msg in messages))
def test_default_font_size(self):
"""Test that default font size is used when not specified"""
data = {
"form_fields": [
{
"description": "Name",
"page_number": 1,
"label_bounding_box": [10, 10, 50, 30],
"entry_bounding_box": [60, 10, 150, 20], # Height is 10
"entry_text": {} # No font_size specified, should use default 14
}
]
}
stream = self.create_json_stream(data)
messages = get_bounding_box_messages(stream)
self.assertTrue(any("FAILURE" in msg and "height" in msg for msg in messages))
self.assertFalse(any("SUCCESS" in msg for msg in messages))
def test_no_entry_text(self):
"""Test that missing entry_text doesn't cause height check"""
data = {
"form_fields": [
{
"description": "Name",
"page_number": 1,
"label_bounding_box": [10, 10, 50, 30],
"entry_bounding_box": [60, 10, 150, 20] # Small height but no entry_text
}
]
}
stream = self.create_json_stream(data)
messages = get_bounding_box_messages(stream)
self.assertTrue(any("SUCCESS" in msg for msg in messages))
self.assertFalse(any("FAILURE" in msg for msg in messages))
def test_multiple_errors_limit(self):
"""Test that error messages are limited to prevent excessive output"""
fields = []
# Create many overlapping fields
for i in range(25):
fields.append({
"description": f"Field{i}",
"page_number": 1,
"label_bounding_box": [10, 10, 50, 30], # All overlap
"entry_bounding_box": [20, 15, 60, 35] # All overlap
})
data = {"form_fields": fields}
stream = self.create_json_stream(data)
messages = get_bounding_box_messages(stream)
# Should abort after ~20 messages
self.assertTrue(any("Aborting" in msg for msg in messages))
# Should have some FAILURE messages but not hundreds
failure_count = sum(1 for msg in messages if "FAILURE" in msg)
self.assertGreater(failure_count, 0)
self.assertLess(len(messages), 30) # Should be limited
def test_edge_touching_boxes(self):
"""Test that boxes touching at edges don't count as intersecting"""
data = {
"form_fields": [
{
"description": "Name",
"page_number": 1,
"label_bounding_box": [10, 10, 50, 30],
"entry_bounding_box": [50, 10, 150, 30] # Touches at x=50
}
]
}
stream = self.create_json_stream(data)
messages = get_bounding_box_messages(stream)
self.assertTrue(any("SUCCESS" in msg for msg in messages))
self.assertFalse(any("FAILURE" in msg for msg in messages))
if __name__ == '__main__':
unittest.main()
skills/pdf/scripts/check_fillable_fields.py
-1
View File
@@ -2,7 +2,6 @@ import sys
from pypdf import PdfReader
# Script for Claude to run to determine whether a PDF has fillable form fields. See forms.md.
reader = PdfReader(sys.argv[1])
skills/pdf/scripts/convert_pdf_to_images.py
-2
View File
@@ -4,14 +4,12 @@ import sys
from pdf2image import convert_from_path
# Converts each page of a PDF to a PNG image.
def convert(pdf_path, output_dir, max_dim=1000):
images = convert_from_path(pdf_path, dpi=200)
for i, image in enumerate(images):
# Scale image if needed to keep width/height under `max_dim`
width, height = image.size
if width > max_dim or height > max_dim:
scale_factor = min(max_dim / width, max_dim / height)
skills/pdf/scripts/create_validation_image.py
-4
View File
@@ -4,12 +4,9 @@ import sys
from PIL import Image, ImageDraw
# Creates "validation" images with rectangles for the bounding box information that
# Claude 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)
@@ -21,7 +18,6 @@ def create_validation_image(page_number, fields_json_path, input_path, output_pa
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
skills/pdf/scripts/extract_form_field_info.py
+1 -31
View File
@@ -4,11 +4,8 @@ import sys
from pypdf import PdfReader
# Extracts data for the fillable form fields in a PDF and outputs JSON that
# Claude 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:
@@ -25,12 +22,9 @@ def make_field_dict(field, field_id):
if ft == "/Tx":
field_dict["type"] = "text"
elif ft == "/Btn":
field_dict["type"] = "checkbox" # radio groups handled separately
field_dict["type"] = "checkbox"
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"
@@ -50,15 +44,6 @@ def make_field_dict(field, field_id):
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()
@@ -66,19 +51,13 @@ def get_field_info(reader: PdfReader):
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):
@@ -90,8 +69,6 @@ def get_field_info(reader: PdfReader):
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
@@ -104,17 +81,11 @@ def get_field_info(reader: PdfReader):
"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:
@@ -122,7 +93,6 @@ def get_field_info(reader: PdfReader):
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]
skills/pdf/scripts/extract_form_structure.py
+115
View File
@@ -0,0 +1,115 @@
"""
Extract form structure from a non-fillable PDF.
This script analyzes the PDF to find:
- Text labels with their exact coordinates
- Horizontal lines (row boundaries)
- Checkboxes (small rectangles)
Output: A JSON file with the form structure that can be used to generate
accurate field coordinates for filling.
Usage: python extract_form_structure.py <input.pdf> <output.json>
"""
import json
import sys
import pdfplumber
def extract_form_structure(pdf_path):
structure = {
"pages": [],
"labels": [],
"lines": [],
"checkboxes": [],
"row_boundaries": []
}
with pdfplumber.open(pdf_path) as pdf:
for page_num, page in enumerate(pdf.pages, 1):
structure["pages"].append({
"page_number": page_num,
"width": float(page.width),
"height": float(page.height)
})
words = page.extract_words()
for word in words:
structure["labels"].append({
"page": page_num,
"text": word["text"],
"x0": round(float(word["x0"]), 1),
"top": round(float(word["top"]), 1),
"x1": round(float(word["x1"]), 1),
"bottom": round(float(word["bottom"]), 1)
})
for line in page.lines:
if abs(float(line["x1"]) - float(line["x0"])) > page.width * 0.5:
structure["lines"].append({
"page": page_num,
"y": round(float(line["top"]), 1),
"x0": round(float(line["x0"]), 1),
"x1": round(float(line["x1"]), 1)
})
for rect in page.rects:
width = float(rect["x1"]) - float(rect["x0"])
height = float(rect["bottom"]) - float(rect["top"])
if 5 <= width <= 15 and 5 <= height <= 15 and abs(width - height) < 2:
structure["checkboxes"].append({
"page": page_num,
"x0": round(float(rect["x0"]), 1),
"top": round(float(rect["top"]), 1),
"x1": round(float(rect["x1"]), 1),
"bottom": round(float(rect["bottom"]), 1),
"center_x": round((float(rect["x0"]) + float(rect["x1"])) / 2, 1),
"center_y": round((float(rect["top"]) + float(rect["bottom"])) / 2, 1)
})
lines_by_page = {}
for line in structure["lines"]:
page = line["page"]
if page not in lines_by_page:
lines_by_page[page] = []
lines_by_page[page].append(line["y"])
for page, y_coords in lines_by_page.items():
y_coords = sorted(set(y_coords))
for i in range(len(y_coords) - 1):
structure["row_boundaries"].append({
"page": page,
"row_top": y_coords[i],
"row_bottom": y_coords[i + 1],
"row_height": round(y_coords[i + 1] - y_coords[i], 1)
})
return structure
def main():
if len(sys.argv) != 3:
print("Usage: extract_form_structure.py <input.pdf> <output.json>")
sys.exit(1)
pdf_path = sys.argv[1]
output_path = sys.argv[2]
print(f"Extracting structure from {pdf_path}...")
structure = extract_form_structure(pdf_path)
with open(output_path, "w") as f:
json.dump(structure, f, indent=2)
print(f"Found:")
print(f" - {len(structure['pages'])} pages")
print(f" - {len(structure['labels'])} text labels")
print(f" - {len(structure['lines'])} horizontal lines")
print(f" - {len(structure['checkboxes'])} checkboxes")
print(f" - {len(structure['row_boundaries'])} row boundaries")
print(f"Saved to {output_path}")
if __name__ == "__main__":
main()
skills/pdf/scripts/fill_fillable_fields.py
-16
View File
@@ -6,13 +6,11 @@ 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:
@@ -48,8 +46,6 @@ def fill_pdf_fields(input_pdf_path: str, fields_json_path: str, output_pdf_path:
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:
@@ -75,18 +71,6 @@ def validation_error_for_field_value(field_info, field_value):
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
skills/pdf/scripts/fill_pdf_form_with_annotations.py
+30 -31
View File
@@ -5,64 +5,67 @@ 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
def transform_from_image_coords(bbox, image_width, image_height, pdf_width, pdf_height):
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 transform_from_pdf_coords(bbox, pdf_height):
left = bbox[0]
right = bbox[2]
pypdf_top = pdf_height - bbox[1]
pypdf_bottom = pdf_height - bbox[3]
return left, pypdf_bottom, right, pypdf_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]
if "pdf_width" in page_info:
transformed_entry_box = transform_from_pdf_coords(
field["entry_bounding_box"],
float(pdf_height)
)
else:
image_width = page_info["image_width"]
image_height = page_info["image_height"]
transformed_entry_box = transform_from_image_coords(
field["entry_bounding_box"],
image_width, image_height,
float(pdf_width), float(pdf_height)
)
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"]
@@ -74,8 +77,6 @@ def fill_pdf_form(input_pdf_path, fields_json_path, output_pdf_path):
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,
@@ -86,10 +87,8 @@ def fill_pdf_form(input_pdf_path, fields_json_path, output_pdf_path):
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)
@@ -105,4 +104,4 @@ if __name__ == "__main__":
fields_json = sys.argv[2]
output_pdf = sys.argv[3]
fill_pdf_form(input_pdf, fields_json, output_pdf)
fill_pdf_form(input_pdf, fields_json, output_pdf)