Web Interface Guidelines Reviewer
vercel-labs/openreview
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my…
A skill your agent uses when the question is whether users can perceive the content — see it, hear it, or feel it — regardless of impairment.
$ npx skills add hashgraph-online/awesome-codex-plugins --skill accessibility-perceivable -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins accessibility-perceivable --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/HDeibler/universal-design-principles/plugins/process-and-robustness-principles/skills/accessibility-perceivable .claude/skills/accessibility-perceivable && rm -rf skills-srcUse ~/.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/
Install the "accessibility-perceivable" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/process-and-robustness-principles/skills/accessibility-perceivable into .claude/skills/accessibility-perceivable/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "accessibility-perceivable", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/process-and-robustness-principles/skills/accessibility-perceivableType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add hashgraph-online/awesome-codex-plugins --skill accessibility-perceivable -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins accessibility-perceivable --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/HDeibler/universal-design-principles/plugins/process-and-robustness-principles/skills/accessibility-perceivable .agents/skills/accessibility-perceivable && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "accessibility-perceivable" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/process-and-robustness-principles/skills/accessibility-perceivable into .agents/skills/accessibility-perceivable/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "accessibility-perceivable", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add hashgraph-online/awesome-codex-plugins --skill accessibility-perceivable -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins accessibility-perceivable --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/HDeibler/universal-design-principles/plugins/process-and-robustness-principles/skills/accessibility-perceivable .cursor/skills/accessibility-perceivable && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "accessibility-perceivable" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/process-and-robustness-principles/skills/accessibility-perceivable into .cursor/skills/accessibility-perceivable/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "accessibility-perceivable", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/hashgraph-online/awesome-codex-plugins.git --path plugins/HDeibler/universal-design-principles/plugins/process-and-robustness-principles/skills/accessibility-perceivable--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add hashgraph-online/awesome-codex-plugins --skill accessibility-perceivable -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins accessibility-perceivable --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/HDeibler/universal-design-principles/plugins/process-and-robustness-principles/skills/accessibility-perceivable .gemini/skills/accessibility-perceivable && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "accessibility-perceivable" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/process-and-robustness-principles/skills/accessibility-perceivable into .gemini/skills/accessibility-perceivable/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "accessibility-perceivable", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install hashgraph-online/awesome-codex-plugins accessibility-perceivableInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add hashgraph-online/awesome-codex-plugins --skill accessibility-perceivable -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/HDeibler/universal-design-principles/plugins/process-and-robustness-principles/skills/accessibility-perceivable .github/skills/accessibility-perceivable && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "accessibility-perceivable" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/process-and-robustness-principles/skills/accessibility-perceivable into .github/skills/accessibility-perceivable/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "accessibility-perceivable", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add hashgraph-online/awesome-codex-plugins --skill accessibility-perceivable -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins accessibility-perceivable --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/HDeibler/universal-design-principles/plugins/process-and-robustness-principles/skills/accessibility-perceivable .opencode/skills/accessibility-perceivable && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "accessibility-perceivable" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/process-and-robustness-principles/skills/accessibility-perceivable into .opencode/skills/accessibility-perceivable/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "accessibility-perceivable", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
accessibility-perceivableA skill your agent uses when the question is whether users can perceive the content — see it, hear it, or feel it — regardless of impairment.
Accessibility Perceivable is an agent skill from hashgraph-online/awesome-codex-plugins. Use this skill when the question is whether users can perceive the content — see it, hear it, or feel it — regardless of impairment. Trigger when designing color systems, picking text sizes, building image-heavy surfaces, working with video/audio, designing for low-vision users, or running an accessibility audit. Covers WCAG Principle 1 (Perceivable). Sub-aspect of accessibility; read that first if you haven't already.
Its SKILL.md is about 2.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/perceivable-deep-dive.md`).
It sits in Frontend & Design, covering Accessibility. The repository describes itself as: A curated list of awesome OpenAI Codex / ChatGPT plugins, skills, and resources. The 1 Codex Marketplace. See live plugins at: https://hol.org/plugins/best-codex-plugins. The licence is Apache-2.0.
4 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 78497e5. It shows what the files ask for, not the result of running them.
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.
No scripts in the folder and no shell commands in SKILL.md (its code samples are html and css).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Accessibility Perceivable loads about 2.9k tokens when it runs, and up to ~4.2k if it reads all its reference files. Until then it costs about 113 tokens; SKILL.md has 978 words of instructions outside code blocks.
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.
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.
The full file from hashgraph-online/awesome-codex-plugins at commit 78497e5, republished under its Apache-2.0 licence (© hashgraph-online). 978 words, ~2,860 tokens.
.claude/skills/accessibility-perceivable/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.WCAG Principle 1: information and user-interface components must be presentable to users in ways they can perceive.
The four sub-criteria, simplified:
This skill covers each in practical detail.
Every image gets alternative text describing what's relevant about it. The right alt text depends on the image's role:
<!-- Informative: describe what the user needs to know -->
<img src="/dashboard-screenshot.png"
alt="Dashboard showing $48,200 monthly revenue, up 12% from last month." />
<!-- Functional (image as link / button): describe the action -->
<a href="/profile">
<img src="/avatar.png" alt="Open your profile" />
</a>
<!-- Decorative: empty alt so screen readers skip -->
<img src="/decorative-pattern.svg" alt="" aria-hidden="true" />
<!-- Complex (chart, infographic): brief alt + linked long description -->
<figure>
<img src="/sales-chart.png"
alt="Quarterly sales chart, see description below."
aria-describedby="chart-desc" />
<figcaption id="chart-desc">
Sales rose from $12k in Q1 to $58k in Q4, with a dip to $31k in Q3 caused
by a supply chain interruption.
</figcaption>
</figure>Common mistakes:
alt="image" or alt="photo of woman" — describes the file type, not the meaning.<figcaption> or linked description.Icon-only buttons need an accessible name. Two patterns:
<!-- Pattern A: aria-label on the button -->
<button aria-label="Close">
<svg aria-hidden="true">...</svg>
</button>
<!-- Pattern B: visually-hidden text -->
<button>
<svg aria-hidden="true">...</svg>
<span class="sr-only">Close</span>
</button>Either is fine; pattern B can be more reliable across screen readers. The sr-only class:
.sr-only {
position: absolute;
width: 1px; height: 1px;
padding: 0; margin: -1px;
overflow: hidden;
clip: rect(0,0,0,0);
white-space: nowrap;
border: 0;
}<svg aria-hidden="true" focusable="false">...</svg>aria-hidden removes from accessibility tree; focusable="false" prevents keyboard focus on the SVG (some browsers focus SVGs by default).
Don't autoplay video or audio with sound. WCAG 1.4.2 requires that audio playing for more than 3 seconds either:
Better: don't autoplay sound at all. It's hostile to users with hearing aids, in public spaces, or sharing audio output.
Use HTML elements for what they're for. Heading order matters; landmarks matter; lists matter.
<!-- Right -->
<main>
<h1>Dashboard</h1>
<section aria-labelledby="kpi-heading">
<h2 id="kpi-heading">This month</h2>
<ul>
<li>Revenue: $48k</li>
<li>Users: 12,481</li>
</ul>
</section>
</main>
<!-- Wrong: divs everywhere, no structure -->
<div>
<div>Dashboard</div>
<div>This month</div>
<div>Revenue: $48k</div>
<div>Users: 12,481</div>
</div>Screen readers navigate by headings (H key in NVDA), landmarks (R key), lists, links. Without semantic structure, navigation falls apart.
Don't skip heading levels. Page structure:
<h1>Page title (one per page)
<h2>Section
<h3>Subsection
<h4>Sub-subsectionGoing from <h1> to <h3> confuses assistive tech. If the visual size you want for an <h2> is too large, restyle the <h2> — don't reach for <h3> to get smaller text.
Source order in HTML should match visual reading order. CSS Grid and Flexbox can rearrange visually, but screen readers follow source order.
<!-- Source order matches visual order: title, then summary, then details -->
<article>
<h2>Article title</h2>
<p class="summary">Brief summary.</p>
<p>Detailed body...</p>
</article>
<!-- Wrong: visually rearranged but source order is now confusing -->
<article style="display: flex; flex-direction: column-reverse;">
<p>Detailed body...</p>
<p>Summary.</p>
<h2>Title</h2>
</article>Use <label for>, aria-labelledby, aria-describedby to expose visual relationships to assistive tech.
<div>
<label for="email">Email</label>
<input id="email" aria-describedby="email-help" />
<p id="email-help">We'll never share this.</p>
</div>The label is associated; the help text is associated. A screen reader announces all three together.
WCAG ratios:
| Content | Level AA | Level AAA |
|---|---|---|
| Body text (< 18pt regular or < 14pt bold) | 4.5:1 | 7:1 |
| Large text (≥ 18pt regular or ≥ 14pt bold) | 3:1 | 4.5:1 |
| UI components and graphical objects | 3:1 | (no AAA) |
| Disabled / inactive elements | (exempt) | (exempt) |
Test every text-on-background combination. Common failures:
#999 on white = 2.85:1, fails AA).#1e90ff on white = 3.4:1, fails AA for body text).Tools: WebAIM Contrast Checker, Stark plugin, Chrome DevTools' contrast inspector.
WCAG 1.4.1: don't use color alone to convey information. Pair with icon, text, pattern, or position.
<!-- Wrong: red border = error, but if red isn't perceivable, no signal -->
<input style="border: 2px solid red" />
<!-- Right: red border + icon + descriptive text -->
<div class="field" data-state="error">
<label for="email">Email</label>
<input id="email" aria-invalid="true" aria-describedby="email-error" />
<p id="email-error">
<AlertIcon aria-hidden="true" /> Please enter a valid email.
</p>
</div>WCAG 1.4.4: text must be resizable up to 200% without loss of content or functionality. Test:
Use relative units (rem, em, %) for type sizes; avoid px for body text. Use vw/vh cautiously — they don't scale with text size.
WCAG 1.4.10 (Level AA): content reflows to a 320 CSS-pixel-wide viewport without requiring horizontal scrolling. Equivalent to 400% zoom on a 1280px viewport.
Practical test: open the design in DevTools at 320px wide and 1280px wide. Anything that requires sideways scroll for primary content fails.
Avoid embedding text in images (which can't be resized, restyled, or read by screen readers). Render text as text wherever possible. SVG with <text> elements is OK because it scales and can be read; raster images of text aren't.
Patterns, textures, position, shape — non-color signals carry meaning for color-blind users:
<!-- Chart series with color + pattern -->
<svg>
<rect fill="url(#solid-blue)" /> <!-- Series A: solid blue -->
<rect fill="url(#striped-blue)" /> <!-- Series B: striped blue -->
<rect fill="url(#dotted-blue)" /> <!-- Series C: dotted blue -->
</svg>Even users who can perceive color benefit from redundant signals.
<style>
.badge { display: inline-flex; align-items: center; gap: 4px;
padding: 2px 8px; border-radius: 9999px;
font-size: 12px; font-weight: 500; }
.badge--success { background: hsl(142 70% 95%); color: hsl(142 70% 22%); }
.badge--warning { background: hsl(38 95% 95%); color: hsl(38 90% 25%); }
.badge--error { background: hsl(0 80% 95%); color: hsl(0 75% 32%); }
</style>
<span class="badge badge--success">
<CheckIcon aria-hidden="true" /> Paid
</span>
<span class="badge badge--warning">
<ClockIcon aria-hidden="true" /> Pending
</span>
<span class="badge badge--error">
<AlertIcon aria-hidden="true" /> Overdue
</span>What's working:
aria-hidden since the text already conveys meaning.alt="image" or alt="" on informative images. Screen reader users get nothing.<h2> for "I want this size" rather than for structural meaning. Leaves <h1> missing or <h2> skipped.<img>. Alt text describes what the user needs to know. Decorative images have empty alt.accessibility (parent).accessibility-operable — keyboard reach and target size.accessibility-understandable — labels, copy, predictability.accessibility-robust — semantic markup and ARIA.color and hierarchy-color-and-tone (perception) — color decisions that respect contrast.legibility and readability (perception) — type decisions that aid perception.© hashgraph-online, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file (references) in plugins/HDeibler/universal-design-principles/plugins/process-and-robustness-principles/skills/accessibility-perceivable of hashgraph-online/awesome-codex-plugins.
Open the folder on GitHubat commit 78497e5
Accessibility Perceivable 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Accessibility Perceivable this skillhashgraph-online/awesome-codex-plugins | 1.2k | — | ~2.9k | Automated safety check: Pass | Apache-2.0 | |
| Web Interface Guidelines Reviewervercel-labs/openreview | 1.7k | 98 repos | ~308 | Automated safety check: Pass | None | |
| Accessibility Reviewmarkmead/hyperui | 12k | 1 repos | ~1.1k | Automated safety check: Pass | MIT | |
| Web Animation DesignbaptisteArno/typebot.io | 11k | 2 repos | ~2.7k | Automated safety check: Pass | Custom licence | |
| Accessibility Fixeribelick/ui-skills | 9.5k | 4 repos | ~1.2k | Automated safety check: Pass | MIT | |
| Wcag Audit PatternsvmDeshpande/ai-agent-automation | 178 | 11 repos | ~610 | Automated safety check: Pass | Apache-2.0 |
vercel-labs/openreview
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my…
markmead/hyperui
Run a WCAG 2.1 AA accessibility audit on a design or page. An agent skill from markmead/hyperui.
baptisteArno/typebot.io
Guides easing, timing and animation choices for UI motion, based on a web animation course, and reviews existing animations in a before-and-after table.
ibelick/ui-skills
Audits and fixes HTML accessibility problems such as ARIA labels, keyboard navigation, focus management, contrast and form errors with minimal changes.
vmDeshpande/ai-agent-automation
Conduct WCAG 2.2 accessibility audits with automated testing, manual verification, and remediation guidance.
ibelick/ui-skills
Applies a fixed set of UI rules for stack, components, interaction, animation, typography and layout, or reviews a file against them with concrete fixes.
hashgraph-online/awesome-codex-plugins
Create original anime-style reaction stickers as looping GIFs and MP4 previews, using generated character pose sheets and timed key poses.
hashgraph-online/awesome-codex-plugins
Manage and query Calibre libraries with the calibredb CLI (local paths or Calibre Content server URLs).
hashgraph-online/awesome-codex-plugins
A skill your agent uses when adding, changing, testing, or debugging Rust HTTP APIs and services, especially when Codex needs black-box integration tests, random-port app startup, real database test…
hashgraph-online/awesome-codex-plugins
Make a studio's game look like something at build time — a cover from a real frame of the game (free), painted covers, backdrops, textures and character plates from image models through the…
hashgraph-online/awesome-codex-plugins
Balance game difficulty, resources, rewards, probability, progression, economies, and dominant strategies.
hashgraph-online/awesome-codex-plugins
Analyze nonfiction manuscripts for reader engagement signals, including heading-level word counts, slow starts, long slogs, weak takeaway titles, value pacing, beta-reader comment dropoff, and…
Categories
A skill your agent uses when the question is whether users can perceive the content — see it, hear it, or feel it — regardless of impairment. Accessibility Perceivable is an agent skill from hashgraph-online/awesome-codex-plugins. Use this skill when the question is whether users can perceive the content — see it, hear it, or feel it — regardless of impairment.
Accessibility Perceivable fits situations like: the question is whether users can perceive the content — see it; feel it — regardless of impairment; designing color systems; picking text sizes.
Run `npx skills add hashgraph-online/awesome-codex-plugins --skill accessibility-perceivable -a claude-code`. Or copy the skill folder (plugins/HDeibler/universal-design-principles/plugins/process-and-robustness-principles/skills/accessibility-perceivable in hashgraph-online/awesome-codex-plugins) into .claude/skills/accessibility-perceivable in your project. Claude Code loads it when a task matches its description.
Run `npx skills add hashgraph-online/awesome-codex-plugins --skill accessibility-perceivable -a codex`. Or copy the skill folder (plugins/HDeibler/universal-design-principles/plugins/process-and-robustness-principles/skills/accessibility-perceivable in hashgraph-online/awesome-codex-plugins) into .agents/skills/accessibility-perceivable in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add hashgraph-online/awesome-codex-plugins --skill accessibility-perceivable -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/accessibility-perceivable, .gemini/skills/accessibility-perceivable, .github/skills/accessibility-perceivable and .opencode/skills/accessibility-perceivable in your project.
SKILL.md names no scripts, command-line tools or credentials: Accessibility Perceivable is instructions for the agent only.
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.
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.
Accessibility Perceivable is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.9k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.3k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Accessibility Perceivable: Web Interface Guidelines Reviewer (vercel-labs/openreview, 1.7k stars), Accessibility Review (markmead/hyperui, 12k stars), Web Animation Design (baptisteArno/typebot.io, 11k stars) and Accessibility Fixer (ibelick/ui-skills, 9.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
hashgraph-online (a GitHub organization) maintains it in hashgraph-online/awesome-codex-plugins, which has 1,242 GitHub stars. The repository holds 686 skills in this directory. The repository was last updated on October 8, 2026.
Source: hashgraph-online/awesome-codex-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.