Agent skill

Kb Office Remediation

by Community-Access in Community-Access/accessibility-agents

Reference data, not a reviewer. An agent skill from Community-Access/accessibility-agents.

MITAuto-check passedDocuments & Office

Install Kb Office Remediation

skills CLI
$ npx skills add Community-Access/accessibility-agents --skill kb-office-remediation -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Community-Access/accessibility-agents kb-office-remediation --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Community-Access/accessibility-agents.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/kb-office-remediation .claude/skills/kb-office-remediation && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
kb-office-remediation
GitHub stars
423
Token cost
~2k tokens
SKILL.md length
214 words
Files
2
Skills in repo
108
Repo updated
First seen
Licence
MIT

At a glance

Reference data, not a reviewer. An agent skill from Community-Access/accessibility-agents.

  • Works in 5 steps: Always back up the original file before… → Never overwrite — use -fixed suffix or… → Validate after fix — recommend Microsoft… → …
  • Tasks that involve PowerPoint presentations
  • SKILL.md covers Office Remediation Patterns…, python-docx Patterns (Word…, openpyxl Patterns (Excel .xlsx) and python-pptx Patterns…, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Kb Office Remediation is an agent skill from Community-Access/accessibility-agents. Reference data, not a reviewer. Remediate Office documents (Word/Excel/PowerPoint) for accessibility. Generates Python scripts via python-docx, openpyxl, python-pptx API references.

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Documents & Office, covering PowerPoint presentations, Excel spreadsheets and Accessibility. It works with Microsoft Excel, Microsoft PowerPoint, openpyxl and python-docx. The repository describes itself as: Accessibility review agents for Claude Code, GitHub Copilot, and Claude Desktop. Eleven specialists that enforce WCAG 2.2 AA compliance so AI coding tools stop generating… The licence is MIT.

When your agent uses it

  • Tasks that involve PowerPoint presentations
  • Tasks that involve Excel spreadsheets
  • Tasks that involve Accessibility

Example prompts

  • “/kb-office-remediation”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Always back up the original file before any modification
  2. Never overwrite — use -fixed suffix or separate output path
  3. Validate after fix — recommend Microsoft Accessibility Checker or re-audit
  4. COM cleanup — always ReleaseComObject and Quit() after COM automation
  5. Encoding — OOXML uses UTF-8; preserve BOM if present in core.xml

What it can do on your machine

Read from SKILL.md and the folder at commit decf6ba. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are python, powershell and bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Kb Office Remediation loads about 2k tokens when it runs. Until then it costs about 51 tokens; SKILL.md has 214 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~51
When it runs · the whole SKILL.md, loaded when a task matches
~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Community-Access/accessibility-agents at commit decf6ba, republished under its MIT licence (© Community-Access). 214 words, ~1,957 tokens.

Download SKILL.mdSave it as .claude/skills/kb-office-remediation/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
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
metadata.domain
cross-cutting
metadata.output
none
metadata.effort
low
metadata.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
python
from docx import Document
doc = Document("input.docx")
doc.core_properties.title = "Descriptive Title"
doc.save("output.docx")
Set Document Language
python
from docx import Document
from docx.oxml.ns import qn
from lxml import etree

doc = Document("input.docx")
styles_element = doc.styles.element
rPrDefault = styles_element.find(qn("w:docDefaults/w:rPrDefault/w:rPr"))
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
python
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")
Add Alt Text to Images
python
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:
body = doc.element.body
for docPr in body.iter(qn("wp:docPr")):
    if not docPr.get("descr"):
        docPr.set("descr", "TODO: Add alt text")
doc.save("output.docx")
Fix Heading Levels
python
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
python
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)
python
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
python
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
python
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
python
from pptx import Presentation

prs = Presentation("input.pptx")
prs.core_properties.title = "Descriptive Title"
prs.save("output.pptx")
Check for Missing Slide Titles
python
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")
Set Alt Text on Images
python
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:
            if not getattr(shape, "_element").get("descr", ""):
                # Access via XML for older python-pptx versions
                shape._element.set("descr", "TODO: Add alt text")
prs.save("output.pptx")
Check Reading Order
python
from pptx import Presentation
from lxml import etree

prs = Presentation("input.pptx")
for i, slide in enumerate(prs.slides, 1):
    shapes = [(s.left, s.top, 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
powershell
$word = New-Object -ComObject Word.Application
$word.Visible = $false
$doc = $word.Documents.Open("C:\path\document.docx")
$doc.BuiltinDocumentProperties("Title").Value = "Accessible Title"
$doc.Save()
$doc.Close()
$word.Quit()
[System.Runtime.InteropServices.Marshal]::ReleaseComObject($word) | Out-Null
Excel — Set Title and Sheet Names
powershell
$excel = New-Object -ComObject Excel.Application
$excel.Visible = $false
$wb = $excel.Workbooks.Open("C:\path\spreadsheet.xlsx")
$wb.BuiltinDocumentProperties("Title").Value = "Accessible Title"
# Rename sheets (example)
# $wb.Sheets.Item(1).Name = "Revenue Data"
$wb.Save()
$wb.Close()
$excel.Quit()
[System.Runtime.InteropServices.Marshal]::ReleaseComObject($excel) | Out-Null
PowerPoint — Set Title
powershell
$ppt = New-Object -ComObject PowerPoint.Application
$prs = $ppt.Presentations.Open("C:\path\presentation.pptx")
$prs.BuiltinDocumentProperties("Title").Value = "Accessible Title"
$prs.Save()
$prs.Close()
$ppt.Quit()
[System.Runtime.InteropServices.Marshal]::ReleaseComObject($ppt) | Out-Null

OOXML Direct Manipulation (ZIP + XML)

For environments without Python or Office, documents can be manipulated directly as ZIP archives:

Extract and Edit core.xml (Title/Language)
bash
# Extract
mkdir -p extracted
unzip -o document.docx -d extracted

# Edit title in docProps/core.xml
sed -i 's|<dc:title/>|<dc:title>Accessible Title</dc:title>|' extracted/docProps/core.xml

# Repackage
cd extracted && zip -r ../document-fixed.docx . && cd ..
Key OOXML Paths

Each property, with its file and XML element.

PropertyFileXML Element
TitledocProps/core.xml<dc:title>
AuthordocProps/core.xml<dc:creator>
Languageword/settings.xml<w:themeFontLang>
Heading stylesword/document.xml<w:pStyle w:val="Heading1">
Alt textword/document.xml<wp:docPr descr="...">
Table headersword/document.xml<w:tblHeader/>

Safety Rules

  1. Always back up the original file before any modification
  2. Never overwrite — use -fixed suffix or separate output path
  3. Validate after fix — recommend Microsoft Accessibility Checker or re-audit
  4. COM cleanup — always ReleaseComObject and Quit() after COM automation
  5. Encoding — OOXML uses UTF-8; preserve BOM if present in core.xml

© Community-Access, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/kb-office-remediation of Community-Access/accessibility-agents.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit decf6ba

Compare with similar skills

Kb Office Remediation next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Kb Office Remediation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Kb Office Remediation this skillCommunity-Access/accessibility-agents423—~2kAutomated safety check: PassMIT
Brand DOCXferdinandobons/brand-docs272—~3.8kAutomated safety check: PassMIT
Brand PPTXferdinandobons/brand-docs272—~3.5kAutomated safety check: PassMIT
Brand XLSXferdinandobons/brand-docs272—~3.3kAutomated safety check: PassMIT
Office ArtifactsPrismer-AI/PrismerCloud1.6k—~2.6kAutomated safety check: PassMIT
Office File Processxstongxue/best-skills3k—~1.8kAutomated safety check: PassProprietary

Similar skills

  • Brand DOCX

    ferdinandobons/brand-docs

    Brand-aware Word engine. An agent skill from ferdinandobons/brand-docs.

    272 GitHub stars~3.8k tokensUpdated 3 mo ago
    Documents & OfficeAuto-check passed
  • Brand PPTX

    ferdinandobons/brand-docs

    Brand-aware PowerPoint engine. An agent skill from ferdinandobons/brand-docs.

    272 GitHub stars~3.5k tokensUpdated 3 mo ago
    Documents & OfficeAuto-check passed
  • Brand XLSX

    ferdinandobons/brand-docs

    Brand-aware Excel engine. An agent skill from ferdinandobons/brand-docs.

    272 GitHub stars~3.3k tokensUpdated 3 mo ago
    Documents & OfficeAuto-check passed
  • Office Artifacts

    Prismer-AI/PrismerCloud

    Generate real DOCX, PPTX, XLSX, PDF, CSV files using python-docx / python-pptx / openpyxl / reportlab by writing them into the dispatch artifacts dir, then explicitly deliver each one with cloud…

    1.6k GitHub stars~2.6k tokensUpdated today
    Documents & OfficeAuto-check passed
  • Office File Process

    xstongxue/best-skills

    处理 Office 文档的一站式 skill:Word(.doc/.docx/.dotx)、Excel(.xls/.xlsx/.xlsm/.csv)、PowerPoint(.ppt/.pptx/.potx) 的创建、读取、编辑、提取、转换、校验。触发:『读取 word 文档』『提取 excel 内容』『看 ppt 讲了什么』、.doc 老格式打不开、生成/编辑 Word…

    3k GitHub stars~1.8k tokensUpdated 28 days ago
    Documents & OfficeAuto-check passed
  • Markdown Exporter

    bowenliang123/markdown-exporter

    Convert Markdown text to DOCX, PPTX, XLSX, PDF, PNG, SVG, HTML, IPYNB, MD, CSV, JSON, JSONL, XML files, and extract code blocks in Markdown to Python, Bash,JS and etc files.

    272 GitHub starsUsed in 1 repo~5.3k tokens
    Documents & OfficeAuto-check passed

More from Community-Access/accessibility-agents

All 108 skills in this repo
  • A11y Core

    Community-Access/accessibility-agents

    Shared contract for the Accessibility Agents skills - dispatch, findings schema, report rules.

    423 GitHub stars~1.2k tokensUpdated 18 days ago
    Auto-check passed
  • Kb Web Scanning

    Community-Access/accessibility-agents

    Reference data, not a reviewer. An agent skill from Community-Access/accessibility-agents.

    423 GitHub stars~1.2k tokensUpdated 18 days ago
    Auto-check passed
  • Accessibility Lead

    Community-Access/accessibility-agents

    Web UI accessibility lead. An agent skill from Community-Access/accessibility-agents.

    423 GitHub stars~932 tokensUpdated 18 days ago
    Auto-check passed
  • Alt Text Headings

    Community-Access/accessibility-agents

    Alt text, SVGs, figures, charts, heading order, page titles and landmarks.

    423 GitHub stars~1.5k tokensUpdated 18 days ago
    Auto-check passed
  • Aria Specialist

    Community-Access/accessibility-agents

    ARIA roles, states and properties for custom widgets and dynamic content.

    423 GitHub stars~1.6k tokensUpdated 18 days ago
    Auto-check passed
  • Cognitive Accessibility

    Community-Access/accessibility-agents

    Plain language, WCAG 2.2 cognitive criteria, COGA guidance and auth UX.

    423 GitHub stars~1.4k tokensUpdated 18 days ago
    Auto-check passed

Questions about Kb Office Remediation

What does Kb Office Remediation do?

Reference data, not a reviewer. An agent skill from Community-Access/accessibility-agents. Kb Office Remediation is an agent skill from Community-Access/accessibility-agents. Reference data, not a reviewer.

When should I use Kb Office Remediation?

Kb Office Remediation fits situations like: tasks that involve PowerPoint presentations; tasks that involve Excel spreadsheets; tasks that involve Accessibility.

How do I install Kb Office Remediation in Claude Code?

Run `npx skills add Community-Access/accessibility-agents --skill kb-office-remediation -a claude-code`. Or copy the skill folder (skills/kb-office-remediation in Community-Access/accessibility-agents) into .claude/skills/kb-office-remediation in your project. Claude Code loads it when a task matches its description.

How do I install Kb Office Remediation in Codex?

Run `npx skills add Community-Access/accessibility-agents --skill kb-office-remediation -a codex`. Or copy the skill folder (skills/kb-office-remediation in Community-Access/accessibility-agents) into .agents/skills/kb-office-remediation in your project. Codex loads it when a task matches its description.

Can I use Kb Office Remediation in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Community-Access/accessibility-agents --skill kb-office-remediation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/kb-office-remediation, .gemini/skills/kb-office-remediation, .github/skills/kb-office-remediation and .opencode/skills/kb-office-remediation in your project.

What does Kb Office Remediation need to run?

SKILL.md names no scripts, command-line tools or credentials: Kb Office Remediation is instructions for the agent only. Our summary lists: Python 3.

Does Kb Office Remediation access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Kb Office Remediation safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Kb Office Remediation use?

Kb Office Remediation is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Kb Office Remediation use?

About 2k tokens (SKILL.md is roughly 7.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Kb Office Remediation?

Skills that share tags, products or a category with Kb Office Remediation: Brand DOCX (ferdinandobons/brand-docs, 272 stars), Brand PPTX (ferdinandobons/brand-docs, 272 stars), Brand XLSX (ferdinandobons/brand-docs, 272 stars) and Office Artifacts (Prismer-AI/PrismerCloud, 1.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Kb Office Remediation?

Community-Access (a GitHub organization) maintains it in Community-Access/accessibility-agents, which has 423 GitHub stars. The repository holds 108 skills in this directory. The repository was last updated on September 23, 2026.

Source: Community-Access/accessibility-agents on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.