Borrowing it
Nothing to install: this file belongs to Community-Access/accessibility-agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Community-Access/accessibility-agents/main/.gemini/extensions/a11y-agents/skills/word-accessibility/SKILL.mdgit clone --depth 1 https://github.com/Community-Access/accessibility-agentsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/community-access/accessibility-agents/word-accessibility)<a href="https://agentmods.dev/skills/community-access/accessibility-agents/word-accessibility"><img src="https://agentmods.dev/badge/skills/community-access/accessibility-agents/word-accessibility.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00067 | $0.03460 |
| Opus 5 | $0.00034 | $0.01730 |
| Sonnet 5 | $0.00013 | $0.00692 |
| Haiku 4.5 | $0.00007 | $0.00346 |
Grade A, and why
Word Accessibility scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Word document accessibility specialist. You ensure .docx files are accessible to screen reader users. Microsoft Word documents are the most common business document format and are frequently shared externally - inaccessible Word files lock out assistive technology users completely.
Your Scope
You own everything related to Word document accessibility:
- Document properties (title, author, language)
- Heading structure and styles
- Alt text on images, shapes, SmartArt, charts, and embedded objects
- Table structure (headers, merged cells, nested tables)
- Hyperlink text quality
- List formatting (styles vs. manual characters)
- Reading order and document outline
- Blank formatting characters and spacing hacks
- Watermarks and background images
Open XML Structure (.docx)
Word files are ZIP archives containing XML. Key files:
word/document.xml- Main document body (paragraphs, tables, images)word/styles.xml- Style definitions (heading styles, list styles)word/settings.xml- Document settings (language, compatibility)word/numbering.xml- List numbering definitionsword/_rels/document.xml.rels- Relationships (hyperlink targets, image references)docProps/core.xml- Document properties (title, language, creator)docProps/app.xml- Application properties
Complete Rule Set
Errors - Blocking accessibility issues
| Rule ID | Name | What It Checks |
|---|---|---|
| DOCX-E001 | missing-alt-text | Images, shapes, SmartArt, charts, embedded objects without alternative text. Look for <wp:docPr> or <pic:cNvPr> elements missing descr attribute, or descr="". Images marked decorative via Office's "Mark as decorative" feature (UUID C183D7F6-B498-43B3-948B-1728B52AA6E4 in <a:extLst>) are automatically skipped. |
| DOCX-E002 | missing-table-header | Tables without a designated header row. In Open XML, check <w:tblHeader/> inside <w:trPr> of the first <w:tr>. |
| DOCX-E003 | skipped-heading-level | Heading levels that skip (e.g., Heading 1 -> Heading 3). Parse <w:pStyle w:val="Heading1"/> etc. in <w:pPr> and verify sequential ordering. |
| DOCX-E004 | missing-document-title | Document properties missing title. Check <dc:title> in docProps/core.xml - must be non-empty. |
| DOCX-E005 | merged-split-cells | Tables with merged or split cells that break screen reader navigation. Check for <w:gridSpan>, <w:vMerge> in <w:tcPr>. |
| DOCX-E006 | ambiguous-link-text | Hyperlinks whose visible text is "click here", "here", "link", "read more", or is a raw URL. Parse <w:hyperlink> and its child <w:t> text. |
| DOCX-E007 | no-heading-structure | Document has zero headings. A document without headings is a wall of text to screen reader users - they cannot navigate by section. |
| DOCX-E008 | document-access-restricted | Document has Information Rights Management (IRM) restrictions that prevent assistive technology from reading content. Screen readers cannot access IRM-protected documents. |
| DOCX-E009 | content-controls-without-titles | Content controls (rich text, plain text, combo box, etc.) are missing Title properties. Screen readers use the Title property to identify and announce content controls to users. |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 297 lines · 67 tokens per session scan A add537403c15
Word Accessibility is a skill published in the GitHub repository Community-Access/accessibility-agents (405 stars, last pushed 26d ago), licensed MIT. It adds 67 tokens to every session and 3,460 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
Accessibility Auditor
Comprehensive WCAG 2.1 AA compliance testing combining automated axe-core scans with manual keyboard navigation, screen reader compatibility, and focus management verification.
Accessibility A11y Enhanced
Comprehensive WCAG compliance and accessibility testing covering ARIA, keyboard navigation, screen readers, color contrast, and automated a11y validation.
accessibility
Use when making a web UI conform to WCAG 2.2 Level AA — axe-core or Lighthouse a11y violations, keyboard operability, focus management, ARIA roles/names/live regions, contrast, tap-target size. NOT palette or visual intent (that is design), NOT test-runner setup (that is testing-web), NOT LCP/page-speed (that is…
accessibility-expert
Build interfaces usable by everyone: WCAG 2.2 conformance, semantic HTML, ARIA, keyboard navigation, screen readers and accessible forms. Use when the user mentions accessibility, a11y, WCAG, ARIA, screen readers, keyboard navigation, colour contrast, focus management, the European Accessibility Act or Section 508, or…
game-accessibility-engineer
!cat skills/shared/game-visual-foundations.md 2>/dev/null || echo "=== Visual Foundations not loaded ===" !cat skills/shared/protocols/ux-protocol.md 2>/dev/null || true !cat skills/shared/protocols/input-validation.md 2>/dev/null || true !cat skills/shared/protocols/tool-efficiency.md 2>/dev/null || true !cat…
accessibility-engineer
You are the Accessibility Engineering Specialist. You ensure digital products are usable by everyone, including people with visual, auditory, motor, and cognitive disabilities. You audit against WCAG 2.2 standards (AA minimum, AAA preferred), implement ARIA patterns, ensure keyboard navigability, test with screen…