/kb-office-remediation

name: kb-office-remediation
description: Reference data, not a reviewer. Remediate Office documents (Word/Excel/PowerPoint) for accessibility. Generates Python scripts via python-docx, openpyxl, python-pptx API references.
license: MIT
disable-model-invocation: true
user-invocable: false
metadata:
  tier: reference
  domain: cross-cutting
  output: none
  effort: low
  title: Office Remediation

Office Remediation Patterns Skill

API reference and code patterns for programmatically fixing accessibility issues in Microsoft Office documents.

---

python-docx Patterns (Word .docx)

Set Document Title

from docx import Document
doc = Document("input.docx")
doc.core_properties.title = "Descriptive Title"
doc.save("output.docx")

Set Document Language

from docx import Document
from docx.oxml.ns import qn
from lxml import etree

doc = Document("input.docx")
styles_element = doc.styles.element
# qn() takes one tag, not a path; use xpath for the path
found = styles_element.xpath("w:docDefaults/w:rPrDefault/w:rPr")
rPrDefault = found[0] if found else None
if rPrDefault is not None:
    lang = rPrDefault.find(qn("w:lang"))
    if lang is None:
        lang = etree.SubElement(rPrDefault, qn("w:lang"))
    lang.set(qn("w:val"), "en-US")
doc.save("output.docx")

Set Table Header Row

from docx import Document
from docx.oxml.ns import qn
from lxml import etree

doc = Document("input.docx")
for table in doc.tables:
    first_row = table.rows[0]._tr
    trPr = first_row.get_or_add_trPr()
    existing = trPr.find(qn("w:tblHeader"))
    if existing is None:
        header_elem = etree.SubElement(trPr, qn("w:tblHeader"))
        header_elem.set(qn("w:val"), "true")
doc.save("output.docx")

Find Images Missing Alt Text

from docx import Document
from docx.oxml.ns import qn

doc = Document("input.docx")
for rel in doc.part.rels.values():
    if "image" in rel.reltype:
        # Images are referenced via <wp:docPr> in the document XML
        # Alt text is the 'descr' attribute on the docPr element
        pass

# Direct XML approach for inline images: report missing alt text.
# Write real descriptions only (docPr.set("descr", text)); never insert a
# placeholder such as "TODO", which hides the problem from checkers.
body = doc.element.body
for docPr in body.iter(qn("wp:docPr")):
    if not docPr.get("descr"):
        print(f"Image '{docPr.get('name')}' (id {docPr.get('id')}) has no alt text")

Fix Heading Levels

from docx import Document

HEADING_MAP = {
    "Heading 3": "Heading 2",  # Example: fix skipped level
}

doc = Document("input.docx")
for para in doc.paragraphs:
    if para.style.name in HEADING_MAP:
        para.style = doc.styles[HEADING_MAP[para.style.name]]
doc.save("output.docx")

---

openpyxl Patterns (Excel .xlsx)

Set Workbook Title and Author

from openpyxl import load_workbook

wb = load_workbook("input.xlsx")
wb.properties.title = "Descriptive Title"
wb.properties.creator = "Author Name"
wb.save("output.xlsx")

Set Print Title Rows (Header Repeat)

from openpyxl import load_workbook

wb = load_workbook("input.xlsx")
for ws in wb.worksheets:
    if ws.max_row > 1:
        ws.print_title_rows = "1:1"  # Repeat row 1 on every printed page
wb.save("output.xlsx")

Detect Generic Sheet Names

GENERIC = {"Sheet", "Sheet1", "Sheet2", "Sheet3", "Tabelle1", "Feuil1"}

from openpyxl import load_workbook
wb = load_workbook("input.xlsx")
for ws in wb.worksheets:
    if ws.title in GENERIC:
        print(f"Generic sheet name: '{ws.title}' - rename to describe content")

Detect Merged Cells

from openpyxl import load_workbook

wb = load_workbook("input.xlsx")
for ws in wb.worksheets:
    if ws.merged_cells.ranges:
        for merged in ws.merged_cells.ranges:
            print(f"Sheet '{ws.title}': merged range {merged}")

---

python-pptx Patterns (PowerPoint .pptx)

Set Presentation Title

from pptx import Presentation

prs = Presentation("input.pptx")
prs.core_properties.title = "Descriptive Title"
prs.save("output.pptx")

Check for Missing Slide Titles

from pptx import Presentation

prs = Presentation("input.pptx")
for i, slide in enumerate(prs.slides, 1):
    title_shape = slide.shapes.title
    if title_shape is None:
        print(f"Slide {i}: No title placeholder")
    elif not title_shape.text.strip():
        print(f"Slide {i}: Empty title")

Find Pictures Missing Alt Text

from pptx import Presentation
from pptx.enum.shapes import MSO_SHAPE_TYPE

prs = Presentation("input.pptx")
for i, slide in enumerate(prs.slides, 1):
    for shape in slide.shapes:
        if shape.shape_type == MSO_SHAPE_TYPE.PICTURE:
            # descr lives on p:nvPicPr/p:cNvPr, not on the p:pic element
            cNvPr = shape._element.nvPicPr.cNvPr
            if not cNvPr.get("descr"):
                print(f"Slide {i}: picture '{shape.name}' has no alt text")
                # When a real description is known: cNvPr.set("descr", text)

Check Reading Order

from pptx import Presentation

prs = Presentation("input.pptx")
for i, slide in enumerate(prs.slides, 1):
    # left/top can be None for placeholders that inherit position
    shapes = [(s.left or 0, s.top or 0, s.name) for s in slide.shapes]
    # Visual order (top-to-bottom, left-to-right) vs. XML order
    visual = sorted(shapes, key=lambda s: (s[1], s[0]))
    xml_order = [s.name for s in slide.shapes]
    visual_order = [s[2] for s in visual]
    if xml_order != visual_order:
        print(f"Slide {i}: Reading order may differ from visual layout")

---

PowerShell COM Automation (Windows + Office)

Word - Set Title

$word = New-Object -ComObject Word.Application
$word.Visible = $false
$doc = $word.Documents.Open("C:\path\document.docx")
$doc.BuiltinDocumentProperties("Title").Value =