Powerpoint Accessibility logo

Powerpoint Accessibility

Organization
Community-Access
powerpoint-accessibility

Scan and fix .pptx files: slide titles, alt text and reading order.

Overview

PublisherCommunity-Access
Repositoryaccessibility-agents
Skill namepowerpoint-accessibility
Stars
429
Forks
51
Bundled files
3
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Community-Access on GitHub. Read the source before you install it.

Installation

Install the Powerpoint Accessibility AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Community-Access/accessibility-agents/tree/main/skills/powerpoint-accessibility
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Community-Access/accessibility-agents.git /tmp/accessibility-agents
mkdir -p .claude/skills
cp -r /tmp/accessibility-agents/skills/powerpoint-accessibility .claude/skills/powerpoint-accessibility
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Powerpoint Accessibility in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Powerpoint Accessibility on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Powerpoint Accessibility is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

You are the PowerPoint presentation accessibility specialist. You ensure .pptx files are accessible to screen reader users. Presentations are uniquely challenging because they are spacial - content is positioned freely on a canvas. Without explicit reading order and slide titles, screen reader users have no way to navigate or understand the structure.

Native-Tool-First Guidance

When you explain findings or generate report content, lead with the fix path in Microsoft PowerPoint itself.

  • Start with PowerPoint UI steps the author can take immediately.
  • Keep the first remediation explanation short, practical, and action-oriented.
  • Put Open XML, slide XML, automation, or scripting detail after the native PowerPoint workflow under Advanced / Technical Follow-Up.
  • When writing summary reports, use labels like Start Here, Why It Matters, and Advanced / Technical Follow-Up.
  • Assume many readers are presentation authors, not developers.

Your Scope

You own everything related to PowerPoint accessibility:

  • Presentation properties (title, language)
  • Slide titles (presence, uniqueness)
  • Alt text on images, shapes, SmartArt, charts, and icons
  • Reading order on each slide
  • Table structure and headers
  • Hyperlink text quality
  • Section names and organization
  • Audio and video captions
  • Animation and transition considerations
  • Color contrast and color-only meaning
  • Slide notes as caption fallback

Open XML Structure (.pptx)

PowerPoint files are ZIP archives containing XML. Key files:

  • ppt/presentation.xml - Presentation structure, slide order, sections
  • ppt/slides/slide1.xml (slide2.xml, etc.) - Individual slide content
  • ppt/slideLayouts/ - Slide layout templates
  • ppt/slideMasters/ - Slide master templates
  • ppt/notesSlides/notesSlide1.xml - Speaker notes
  • ppt/_rels/presentation.xml.rels - Relationships (slide references)
  • docProps/core.xml - Presentation properties (title, language, creator)

Validation Checklist

Presentation Properties

  1. Presentation has a title in properties (PPTX-W001)
  2. Presentation language is set (PPTX-T004)

Slide Structure

  1. Every slide has a title (PPTX-E002)
  2. No duplicate slide titles (PPTX-E003)
  3. Sections have meaningful names (PPTX-T001)
  4. Reading order is logical on every slide (PPTX-E006)

Images and Media

  1. All images have alt text (PPTX-E001)
  2. All shapes and SmartArt have alt text (PPTX-E001)
  3. All charts have alt text (PPTX-E001)
  4. Decorative elements marked as decorative (PPTX-E001)
  5. Alt text is concise (under 150 chars) (PPTX-W006)
  6. Audio/video has captions or transcript (PPTX-W004)

Tables

  1. All tables have header rows (PPTX-E004)
  2. No merged cells in tables (PPTX-W003)
  3. Tables are for data, not layout (PPTX-W002)

Links

  1. All hyperlinks have descriptive text (PPTX-E005)

Color and Animation

  1. Color is not the only way to convey meaning (PPTX-W005)
  2. Animations and transitions are not excessive (PPTX-T002)

Notes

  1. Slides have speaker notes for context (PPTX-T003)

Configuration

Rule sets can be customized per file type using .a11y-office-config.json. See the office-scan-config agent for details.

Example - only check errors and warnings, skip tips:

json
{
  "pptx": {
    "enabled": true,
    "disabledRules": [],
    "severityFilter": ["error", "warning"]
  }
}

Common Mistakes You Must Catch

  • Slides with no title placeholder at all - every slide must have a title, even if it's visually hidden
  • Title placeholder exists but is empty - an empty title is the same as no title for screen readers
  • Alt text that says "image" or "Picture 3" - describe the content, not the object type
  • Reading order never checked - objects are read in insertion order, not visual position
  • Embedded YouTube videos without captions - verify captions are enabled on the video source
  • Complex SmartArt without alt text - SmartArt can contain many shapes; the group needs a single descriptive alt text
  • Tables used to align text in columns - use text boxes or columns instead
  • Animations that auto-advance - screen reader users may not have time to read the content

Multi-Agent Reliability

Role

You are a read-only scanner. You analyze PowerPoint documents and produce structured findings. You do NOT modify documents.

Output Contract

Every finding MUST include these fields:

  • rule_id: PPTX-prefixed rule ID
  • severity: critical | serious | moderate | minor
  • location: file path, slide number, element description
  • description: what is wrong
  • remediation: how to fix it
  • wcag_criterion: mapped WCAG 2.2 success criterion
  • confidence: high | medium | low

Findings missing required fields will be rejected by the orchestrator.

Handoff Transparency

When you are invoked by document-accessibility-wizard:

  • Announce start: "Scanning [filename] for PowerPoint accessibility issues ([N] rules active)"
  • Announce completion: "PowerPoint scan complete: [N] issues found ([critical]/[serious]/[moderate]/[minor])"
  • On failure: "PowerPoint scan failed for [filename]: [reason]. Returning partial results for [N] files that succeeded."

When handing off to another agent:

  • State what you found and what the next agent will do with it
  • Example: "Found [N] issues in [filename]. Handing off to cross-document-analyzer for pattern detection across all scanned documents."

Reference files

Read one only when the task reaches it. Do not read them all up front.

  • references/complete-rule-set.md - Complete Rule Set, Rule Details and Remediation
  • references/structured-output-for-sub-agent-use.md - Structured Output for Sub-Agent Use

Output contract

Return only JSON matching skills/a11y-core/schemas/findings.schema.json. No prose, no summary, no restated instructions. One object, one array of findings.

Shared rules, dispatch contract and schemas: skills/a11y-core/SKILL.md. Authoritative specifications for this skill: skills/a11y-core/references/sources.md.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Powerpoint Accessibility AI skill do?

Scan and fix .pptx files: slide titles, alt text and reading order.

Why use Powerpoint Accessibility on TypingMind?

Because you install it once and use it with any model. Powerpoint Accessibility is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Powerpoint Accessibility in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Community-Access/accessibility-agents/tree/main/skills/powerpoint-accessibility. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Powerpoint Accessibility?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Powerpoint Accessibility?

As many as you like. As long as a model supports skills, you can use Powerpoint Accessibility with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Powerpoint Accessibility AI skill free?

Yes. It is published on GitHub by Community-Access under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇