Razshy/Wiggle / mnt-skills/public/docx
docx
VerifiedUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file (to download, email or print), use this skill. However, if they ask for a document, page, report, memo, or notes WITHOUT naming a file format and the session offers a dedicated document or page skill or connector, use that instead. Do NOT use for PDFs, spreadsheets, Google Docs, or coding unrelated to document generation.
scripts/office/validators/redlining.py
View on GitHub"""
Validator for tracked changes in Word documents.
Detects untracked edits in word/document.xml: text that differs from the
original without a <w:ins>/<w:del> wrapper recording it. The tracked changes
that are new relative to the original are undone, and the result is compared
against the original; whatever text still differs was edited without being
tracked.
Only the document body is compared. Headers, footers, footnotes and endnotes
are separate parts and are not checked.
"""
import subprocess
import tempfile
import zipfile
from pathlib import Path
import defusedxml.ElementTree as ET
from defusedxml.common import DefusedXmlException
from helpers import rendered_text, safe_extract
class RedliningValidator:
def __init__(self, unpacked_dir, original_docx, verbose=False):
self.unpacked_dir = Path(unpacked_dir)
self.original_docx = Path(original_docx)
self.verbose = verbose
self.namespaces = {
"w": "http://schemas.openxmlformats.org/wordprocessingml/2006/main"
}
def repair(self) -> int:
return 0
def validate(self):
modified_file = self.unpacked_dir / "word" / "document.xml"
if not modified_file.exists():
print(f"FAILED - Modified document.xml not found at {modified_file}")
return False
with tempfile.TemporaryDirectory() as temp_dir:
temp_path = Path(temp_dir)
try:
with zipfile.ZipFile(self.original_docx, "r") as zip_ref:
safe_extract(zip_ref, temp_path)
except Exception as e:
print(f"FAILED - Error unpacking original docx: {e}")
return False
original_file = temp_path / "word" / "document.xml"
if not original_file.exists():
print(
f"FAILED - Original document.xml not found in {self.original_docx}"
)
return False
try:
modified_tree = ET.parse(modified_file)
modified_root = modified_tree.getroot()
original_tree = ET.parse(original_file)
original_root = original_tree.getroot()
except (ET.ParseError, DefusedXmlException) as e:
print(f"FAILED - Error parsing XML files: {e}")
return False
new_changes = self._new_tracked_changes(original_root, modified_root)
self._remove_tracked_changes(modified_root, new_changes)
modified_text = self._extract_text_content(modified_root)
original_text = self._extract_text_content(original_root)
if modified_text != original_text:
error_message = self._generate_detailed_diff(
original_text, modified_text
)
print(error_message)
return False
if self.verbose:
print(
f"PASSED - All {len(new_changes)} change(s) against the original "
"are properly tracked"
)
return True
def _tracked_change_elements(self, root):
w = self.namespaces["w"]
tags = (f"{{{w}}}ins", f"{{{w}}}del", f"{{{w}}}moveFrom", f"{{{w}}}moveTo")
return [elem for elem in root.iter() if elem.tag in tags]
def _rendered_text(self, elem):
preserve = elem.get("{http://www.w3.org/XML/1998/namespace}space") == "preserve"
return rendered_text(elem.text or "", preserve)
def _text_elements(self, elem):
w = self.namespaces["w"]
return [
node
for node in elem.iter()
if node.tag in (f"{{{w}}}t", f"{{{w}}}delText")
]
def _tracked_change_key(self, elem):
w = self.namespaces["w"]
text = "".join(self._rendered_text(node) for node in self._text_elements(elem))
return (elem.tag, elem.get(f"{{{w}}}author"), elem.get(f"{{{w}}}date"), text)
def _new_tracked_changes(self, original_root, modified_root):
original = self._tracked_change_elements(original_root)
modified = self._tracked_change_elements(modified_root)
pool = {}
for elem in original:
pool.setdefault(self._tracked_change_key(elem), []).append(elem)
matched, leftover = set(), []
for elem in modified:
bucket = pool.get(self._tracked_change_key(elem))
if bucket:
matched.add(bucket.pop())
else:
leftover.append(elem)
def group(elem):
return self._tracked_change_key(elem)[:3]
def text_of(elems):
return "".join(self._tracked_change_key(e)[3] for e in elems)
unmatched_original = {}
for elem in original:
if elem not in matched:
unmatched_original.setdefault(group(elem), []).append(elem)
by_group = {}
for elem in leftover:
by_group.setdefault(group(elem), []).append(elem)
new = set()
for key, elems in by_group.items():
rebuilt = text_of(elems)
if rebuilt and rebuilt == text_of(unmatched_original.get(key, [])):
continue
new.update(elems)
return new
def _generate_detailed_diff(self, original_text, modified_text):
error_parts = [
"FAILED - Document text doesn't match after removing the tracked changes",
"",
"Likely causes:",
" 1. Modified text inside another author's <w:ins> or <w:del> tags",
" 2. Made edits without proper tracked changes",
" 3. Didn't nest <w:del> inside <w:ins> when deleting another's insertion",
" 4. Rewrote another author's <w:ins>/<w:del> and changed its text on",
" the way. A tracked change from the original is recognised by its",
" author, date and text; anything that doesn't reproduce one exactly",
" reads as new, and the text it carried is reported missing.",
"",
"For pre-redlined documents, use correct patterns:",
" - To reject another's INSERTION: Nest <w:del> inside their <w:ins>",
" - To reject PART of one: nest <w:del> around only the runs you reject.",
" Their <w:ins> may be split around it, so long as the pieces keep",
" their author and date and still spell out the same text.",
" - To restore another's DELETION: Add new <w:ins> AFTER their <w:del>",
"",
]
git_diff = self._get_git_word_diff(original_text, modified_text)
if git_diff:
error_parts.extend(["Differences:", "============", git_diff])
else:
error_parts.append("Unable to generate word diff (git not available)")
return "\n".join(error_parts)
def _get_git_word_diff(self, original_text, modified_text):
try:
with tempfile.TemporaryDirectory() as temp_dir:
temp_path = Path(temp_dir)
original_file = temp_path / "original.txt"
modified_file = temp_path / "modified.txt"
original_file.write_text(original_text, encoding="utf-8")
modified_file.write_text(modified_text, encoding="utf-8")
result = subprocess.run(
[
"git",
"diff",
"--word-diff=plain",
"--word-diff-regex=.",
"-U0",
"--no-index",
str(original_file),
str(modified_file),
],
capture_output=True,
encoding="utf-8",
errors="replace",
)
if result.stdout.strip():
lines = result.stdout.split("\n")
content_lines = []
in_content = False
for line in lines:
if line.startswith("@@"):
in_content = True
continue
if in_content and line.strip():
content_lines.append(line)
if content_lines:
return "\n".join(content_lines)
result = subprocess.run(
[
"git",
"diff",
"--word-diff=plain",
"-U0",
"--no-index",
str(original_file),
str(modified_file),
],
capture_output=True,
encoding="utf-8",
errors="replace",
)
if result.stdout.strip():
lines = result.stdout.split("\n")
content_lines = []
in_content = False
for line in lines:
if line.startswith("@@"):
in_content = True
continue
if in_content and line.strip():
content_lines.append(line)
return "\n".join(content_lines)
except (subprocess.CalledProcessError, FileNotFoundError, Exception):
pass
return None
def _remove_tracked_changes(self, root, targets):
w = self.namespaces["w"]
ins_tag = f"{{{w}}}ins"
del_tag = f"{{{w}}}del"
move_from_tag = f"{{{w}}}moveFrom"
move_to_tag = f"{{{w}}}moveTo"
self._merge_split_paragraphs(root, targets)
for parent in root.iter():
to_remove = []
for child in parent:
if child.tag in (ins_tag, move_to_tag) and child in targets:
to_remove.append(child)
for elem in to_remove:
parent.remove(elem)
deltext_tag = f"{{{w}}}delText"
t_tag = f"{{{w}}}t"
for parent in root.iter():
to_process = []
for child in parent:
if child.tag in (del_tag, move_from_tag) and child in targets:
to_process.append((child, list(parent).index(child)))
for del_elem, del_index in reversed(to_process):
for elem in del_elem.iter():
if elem.tag == deltext_tag:
elem.tag = t_tag
for child in reversed(list(del_elem)):
parent.insert(del_index, child)
parent.remove(del_elem)
range_tags = (
f"{{{w}}}moveFromRangeStart",
f"{{{w}}}moveFromRangeEnd",
f"{{{w}}}moveToRangeStart",
f"{{{w}}}moveToRangeEnd",
)
for parent in root.iter():
to_remove = [
c
for c in parent
if c.tag in range_tags and len(c) == 0 and not (c.text or "").strip()
]
for elem in to_remove:
parent.remove(elem)
def _merge_split_paragraphs(self, root, targets):
w = self.namespaces["w"]
p_tag = f"{{{w}}}p"
ppr_tag = f"{{{w}}}pPr"
marker_path = f"{ppr_tag}/{{{w}}}rPr/{{{w}}}ins"
for parent in list(root.iter()):
for para in reversed([child for child in parent if child.tag == p_tag]):
if not any(m in targets for m in para.findall(marker_path)):
continue
siblings = list(parent)
index = siblings.index(para)
following = siblings[index + 1] if index + 1 < len(siblings) else None
if following is None or following.tag != p_tag:
continue
if any(self._text_elements(c) for c in para if c.tag == ppr_tag):
continue
insert_at = 1 if len(following) and following[0].tag == ppr_tag else 0
for child in reversed([c for c in para if c.tag != ppr_tag]):
following.insert(insert_at, child)
parent.remove(para)
def _extract_text_content(self, root):
p_tag = f"{{{self.namespaces['w']}}}p"
t_tag = f"{{{self.namespaces['w']}}}t"
paragraphs = []
for p_elem in root.findall(f".//{p_tag}"):
text_parts = []
for t_elem in p_elem.findall(f".//{t_tag}"):
text_parts.append(self._rendered_text(t_elem))
paragraph_text = "".join(text_parts)
if paragraph_text:
paragraphs.append(paragraph_text)
return "\n".join(paragraphs)
if __name__ == "__main__":
raise RuntimeError("This module should not be run directly.")
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| canvas-designanthropics/skillsCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| docxanthropics/skillsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| pdfanthropics/skillsUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| pptxanthropics/skillsUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |