Explain a core web accessibility concept through what breaks for an assistive technology user, or review pasted HTML and flag specific accessibility gaps by line.
You are an accessibility instructor who refuses to teach any rule as an abstract best practice, because "add alt text" and "use semantic HTML" only actually mean something once a student has pictured the specific real person on the other end, someone using a screen reader that reads the page aloud, or someone navigating entirely by keyboard with no mouse, and can name exactly what breaks for that person when the rule gets skipped. Work in [MODE:select:explain a core concept,review my own HTML for accessibility gaps] mode. If I chose explain a core concept, my concept is [CONCEPT:select:semantic HTML and landmark elements,alt text for images,aria labels and roles,keyboard navigation and focus order]. Explain [CONCEPT] by first describing the specific assistive technology or interaction pattern it matters for, a screen reader announcing page structure and content, or a person tabbing through the page using only a keyboard, then state exactly what that person experiences when [CONCEPT] is missing or done wrong, a page with no headings or landmarks forcing a screen reader user to listen to everything in order with no way to jump to the main content, or a custom dropdown built entirely with `<div>` elements that a keyboard user simply cannot open at all. Then show a short before-and-after HTML example, the version missing [CONCEPT] and the version implementing it correctly, with a plain-language comment on what specifically changed and why that change is what fixes the experience just described. If I chose review my own HTML for accessibility gaps, my code is: [CODE] If I left [CODE] blank, ask me to paste actual HTML before doing anything else instead of inventing an example to review in its place. Go through [CODE] and identify each accessibility gap present, missing or unhelpful alt text, non-semantic elements standing in for interactive controls, missing form labels, unclear or missing landmarks, and for each one found, name the specific line, describe concretely what a screen reader or keyboard-only user would actually experience because of it, and show the corrected version of that specific piece of code. My depth is [DEPTH:select:just this one concept or review,also explain the general principle it's an example of]. If I chose the second option, name which of the four broad accessibility principles, content being perceivable, the interface being operable, everything being understandable, or the page holding up correctly across different assistive technology, the specific issue falls under, so the one concrete example connects to the wider framework instead of standing alone. Close by asking whether I want a second concept or a second pass over the same code checking for a different category of gap, since accessibility issues rarely travel alone and a page fixed for one specific problem often still has another waiting.
Use this prompt anywhere
10,000+ expert prompts for ChatGPT, Claude, Gemini, and wherever you use AI.
Get Early AccessAdd alt text and use semantic HTML stay abstract rules until someone pictures the actual person on the other end, a screen reader user hearing the page read aloud in order, or a keyboard-only user tabbing through with no mouse, and can name exactly what breaks for that person when the rule gets skipped.
In explain mode, this tool takes your chosen [CONCEPT], semantic HTML and landmarks, alt text, aria labels and roles, or keyboard navigation and focus order, and describes the specific person and interaction it matters for, states exactly what that person experiences when it's missing, a page with no landmarks forcing a screen reader user to listen through everything in order, then shows a before-and-after HTML example with the fix explained line by line.
In review mode, paste your own [CODE] and get each real accessibility gap found, named by line, with what a screen reader or keyboard-only user would actually experience because of it, and the corrected version shown. Set [DEPTH] to also connect the specific issue to one of the four broad accessibility principles. Run it in the Dock Editor to build a set of concepts reviewed, pair with the html form input practice generator for accessible form fields specifically, or the html css code explainer for the surrounding markup.
Start a new conversation in ChatGPT, Claude, or Gemini, or open the Dock Editor instead. Set [MODE] to explain a core concept from scratch, or review my own HTML for accessibility gaps in code you already wrote.
In explain mode, set [CONCEPT] to one of four core topics. In review mode, paste your actual [CODE] instead of an invented example.
Get the specific assistive technology or interaction pattern named, and exactly what that person experiences when the concept is missing or wrong.
Get a short broken example and its corrected version side by side, with a plain-language note on what changed and why that fixes the experience.
Set [DEPTH] to learn which of the four broad accessibility principles, perceivable, operable, understandable, or holding up across assistive technology, the issue falls under.
Learn what a missing accessibility detail actually costs a real user before shipping, instead of treating accessibility as an optional polish step for later.
Get each core concept explained through a concrete broken-then-fixed example, building intuition before a course covers WCAG formally.
Paste real HTML from a project already built and get the specific accessibility gaps named by line instead of running an automated tool with no explanation.
Check a custom dropdown, tab list, or modal for keyboard navigation and aria gaps before assuming a div-based control works for every user.
Discover more prompts that could help with your workflow.
Build a small working program that calls a real public API, with the request, response, and API key setup explained step by step.
Explain a core functional programming idea, such as pure functions or immutability, with a broken code example and its fixed version shown side by side.
Explain a built-in math function, square root, power, absolute value, or rounding, covering math and syntax, then generate practice calls to predict before revealing results.
10,000+ expert-curated prompts for ChatGPT, Claude, Gemini, and wherever you use AI. Our extension helps any prompt deliver better results.