Content Design logo

Content Design

Community
mgifford
content-design

Load this skill whenever writing, editing, or reviewing any web content, copy, headings, labels, error messages, or instructions. Under no circumstances write inaccessible content — every piece of text must be clear, structured, and usable by people with cognitive, visual, and language differences. Absolutely always apply plain language, logical heading hierarchy, and meaningful link text.

Overview

Publishermgifford
Repositoryaccessibility-skills
Skill namecontent-design
Stars
57
Forks
5
Bundled files
1
LicenseAGPL-3.0
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.

  • 1 bundled files

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

  • Open source

    Published by mgifford on GitHub. Read the source before you install it.

Installation

Install the Content Design 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/mgifford/accessibility-skills/tree/main/skills/content-design
  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/mgifford/accessibility-skills.git /tmp/accessibility-skills
mkdir -p .claude/skills
cp -r /tmp/accessibility-skills/skills/content-design .claude/skills/content-design
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Content Design 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 Content Design 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 Content Design 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.

Content Design Accessibility Skill

Canonical source: examples/CONTENT_DESIGN_ACCESSIBILITY_BEST_PRACTICES.md in mgifford/ACCESSIBILITY.md This skill is derived from that file. When in doubt, the example is authoritative.

Apply these rules when writing, editing, or reviewing any web content.


Core Mandate

Content design and accessibility are inseparable. A technically accessible page that is confusing or poorly structured still creates barriers. Design content for the widest possible audience: write clearly, structure logically, and present information in the order users need it.


Severity Scale (this skill)

LevelMeaning
CriticalContent is completely inaccessible or incomprehensible to a disability group
SeriousSignificant barrier; unreasonable to expect workaround
ModerateCreates friction; workaround exists and is not too burdensome
MinorBest-practice gap; marginal impact

Critical: Images Must Have Appropriate Text Alternatives

A meaningful image with no alt attribute or alt="" is Critical — blind users receive no information. A decorative image with descriptive alt is Moderate — it adds noise but does not block information.

  • Every informative image needs meaningful alt text that conveys its purpose, not just its appearance
  • Decorative images: alt="" (empty string — the attribute must still be present)
  • Do not rely on images alone to convey information; support visual content with accompanying text
  • Charts and graphs must be accompanied by a text summary or accessible data table (see skills/charts-graphs/SKILL.md)
  • For diagram-specific guidance, see skills/svg/SKILL.md

Serious: All Link Text Must Make Sense Out of Context

"Click here", "Read more", and "Learn more" are Serious — screen reader users navigate by links and hear them without surrounding context.

html
<!-- Serious issue -->
<a href="/report">Read more</a>

<!-- Good -->
<a href="/report">2024 Accessibility Annual Report</a>

For document links, include file type and size:

html
<a href="/report.pdf">2024 Annual Report (PDF, 2.3 MB)</a>

Warn users when links open in new tabs:

html
<a href="/report" target="_blank">
  Annual Report
  <span class="visually-hidden">(opens in new tab)</span>
</a>

Use consistent terminology: if a concept is called "accessibility statement" in one place, do not call it "a11y disclosure" somewhere else.


Serious: Heading Hierarchy Must Be Logical

Skipping heading levels is Moderate; having no <h1> or using headings purely for visual styling is Serious — screen reader users rely on headings for page navigation.

  • One <h1> per page describing the page's main purpose
  • Logical hierarchy: h1 → h2 → h3 (do not skip levels)
  • Headings must be descriptive and unique — not "Introduction" or "Overview" alone
  • Write headings as statements or clear topic labels, not questions (unless FAQ format is appropriate)
  • Navigation labels, button text, and form labels must be descriptive and unambiguous out of context

Moderate: Plain Language

Overly complex language is Moderate — it creates real barriers for users with cognitive disabilities and low literacy, but the content is technically still present.

  • Common words, short sentences, active voice
  • Target Grade 8 reading level or lower for general audiences
  • Avoid jargon, acronyms on first use, and insider terminology unless the audience requires it
  • Define technical terms inline; spell out abbreviations on first use
  • Front-load key information — most important point first
  • Use the second person ("you") to speak directly to the reader
  • Avoid double negatives and conditional stacking — write "Complete all required fields to proceed" instead of "You can only proceed if you have not failed to complete the required fields"
  • Prefer short, concrete words over long, abstract ones ("use" instead of "utilize")
  • Run a readability checker before publishing; target Flesch-Kincaid Grade 8 or lower for general audiences

Moderate: Tables

  • Use only for genuinely tabular data — never for layout (Critical if layout table has no role="presentation")
  • <caption> or heading explaining what the table contains
  • Header cells marked with <th scope="col"> or <th scope="row">
  • Keep tables simple; avoid merging cells unless necessary
  • Provide a text summary for complex tables

Missing scope on a simple table is Moderate; missing it on a complex table with multiple header rows is Serious. (For code-level table requirements, also load skills/tables/SKILL.md.)


Moderate: Page and Content Structure

  • Use lists for three or more parallel items (not embedded in dense prose)
  • Short paragraphs: 3–5 sentences maximum; one idea per paragraph
  • Inverted pyramid: most critical content at top
  • Use white space generously

Moderate: Forms — Writing Requirements

  • Write form instructions before the form, not inside it
  • Label fields with what the user needs to enter, not how the system stores it
  • Provide format examples for unusual inputs: Date: DD/MM/YYYY
  • Error messages must describe the problem and the fix — avoid system error codes

(For code-level form requirements, also load skills/forms/SKILL.md.)


Moderate: Cognitive Accessibility

  • Supplement complex content with summaries, key takeaways, or "what you need to know" sections
  • Break long processes into numbered steps
  • Use examples and analogies to explain abstract concepts
  • Avoid time-pressured content presentation where possible
  • Provide enough context so users can understand content without relying on memory of prior sections

Minor: Writing Style Details

  • Active voice preferred: "The form saves your data" not "Your data is saved"
  • Present tense where possible
  • Gender-neutral and inclusive language throughout
  • Consistent terminology: one term per concept across the site; maintain a content style guide and a defined voice/tone applied consistently
  • Unique, descriptive page <title> elements
  • Review content periodically to remove outdated, misleading, or contradictory information

Minor: Content for Diverse Audiences

  • Assume a broad audience that includes people with cognitive, learning, and language differences
  • Provide content in more than one format where feasible (e.g., video summary alongside written guidance)
  • Consider whether translations or Easy Read versions are appropriate
  • Avoid idioms, metaphors, or culturally specific references that may not translate

Testing and Review

  • Read content aloud to check for clarity and natural flow
  • Have someone unfamiliar with the topic review it before publishing
  • Test page navigation with keyboard only and confirm headings convey structure
  • Use a screen reader to verify the content makes sense in linear reading order
  • Check that all links are descriptive and functional
  • Run a readability score on key pages and track it over time

Definition of Done Checklist

  • Reading level checked (Grade 8 or lower for general audiences)
  • One <h1>, logical heading hierarchy, no skipped levels
  • All link text descriptive out of context
  • Document links include file type and size
  • New-tab links warn the user
  • All images have appropriate alt (meaningful description or empty for decorative)
  • Tables use <caption> and <th scope="…">
  • Consistent terminology across the page/site
  • Unique, descriptive page title
  • Reviewed by someone outside the team

Key WCAG Criteria

  • 1.1.1 Non-text Content (A) — Critical if meaningful images lack alt
  • 1.3.1 Info and Relationships (A)
  • 2.4.4 Link Purpose in Context (AA) — Serious if links are ambiguous
  • 2.4.6 Headings and Labels (AA)
  • 2.4.2 Page Titled (A)
  • 3.1.5 Reading Level (AAA — target for general audiences)

References

Standards horizon: WCAG 3.0 is in development. Content design requirements are not expected to change substantially. Monitor: https://www.w3.org/TR/wcag-3.0/

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 Content Design AI skill do?

Load this skill whenever writing, editing, or reviewing any web content, copy, headings, labels, error messages, or instructions. Under no circumstances write inaccessible content — every piece of text must be clear, structured, and usable by people with cognitive, visual, and language differences. Absolutely always apply plain language, logical heading hierarchy, and meaningful link text.

Why use Content Design on TypingMind?

Because you install it once and use it with any model. Content Design 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 Content Design in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mgifford/accessibility-skills/tree/main/skills/content-design. 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 Content Design?

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 Content Design?

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

Is the Content Design AI skill free?

Yes. It is published on GitHub by mgifford under the AGPL-3.0 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 👇