Review ecommerce UI code for practical accessibility regressions in buyer flows.

MITAuto-check passedFrontend & Design

Install Accessibility Audit

skills CLI
$ npx skills add harukiseller-droid/commerce-agent-bench --skill accessibility-audit -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install harukiseller-droid/commerce-agent-bench accessibility-audit --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/harukiseller-droid/commerce-agent-bench.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/accessibility-audit .claude/skills/accessibility-audit && rm -rf skills-src

Use ~/.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/

Facts

Skill name
accessibility-audit
GitHub stars
101
Token cost
~364 tokens
SKILL.md length
167 words
Files
1
Skills in repo
10
Repo updated
First seen
Licence
MIT

At a glance

Review ecommerce UI code for practical accessibility regressions in buyer flows.

  • Tasks that involve Accessibility
  • SKILL.md covers Purpose, When to use, Inputs and Required checks, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Tasks that involve E-commerce operations

What it does

Accessibility Audit is an agent skill from harukiseller-droid/commerce-agent-bench. Review ecommerce UI code for practical accessibility regressions in buyer flows.

Its SKILL.md is about 360 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Frontend & Design, covering Accessibility and E-commerce operations. The licence is MIT.

When your agent uses it

  • Tasks that involve Accessibility
  • Tasks that involve E-commerce operations

Example prompts

  • “/accessibility-audit”

What it can do on your machine

Read from SKILL.md and the folder at commit f818ba8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Accessibility Audit loads about 364 tokens when it runs. Until then it costs about 25 tokens; SKILL.md has 167 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~25
When it runs · the whole SKILL.md, loaded when a task matches
~364

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from harukiseller-droid/commerce-agent-bench at commit f818ba8, republished under its MIT licence (© harukiseller-droid). 167 words, ~364 tokens.

Download SKILL.mdSave it as .claude/skills/accessibility-audit/SKILL.md (or your agent's skills folder).
name
accessibility-audit
description
Review ecommerce UI code for practical accessibility regressions in buyer flows.

Accessibility Audit

Purpose

Review ecommerce UI code for practical accessibility regressions without claiming conformance that was not tested.

When to use

Use for product cards, product pages, cart, filters, navigation, dialogs, and checkout-adjacent UI.

Inputs

  • the changed UI source and nearby components;
  • route, template, or fixture scope;
  • browser evidence when interactive behavior is part of the claim.

Required checks

  • meaningful image alternatives;
  • accessible names for buttons/links/inputs;
  • label/control association;
  • keyboard reachability and focus behavior when code is available;
  • semantic headings and landmarks;
  • state communication for variants, filters, errors, and disabled actions;
  • avoid relying on color alone.

Output contract

Use the finding contract from PROTOCOL.md: status, severity, category, location, finding, evidence, risk, recommended patch, and verification.

Failure conditions

  • Required source or rendered evidence is missing: mark the conclusion UNKNOWN.
  • Do not claim WCAG conformance from static code inspection alone.
  • Do not treat a passing static check as proof of keyboard or screen-reader behavior.

Verification

Run the smallest relevant project tests/evals and state whether browser or assistive-technology testing was performed.

© harukiseller-droid, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/accessibility-audit of harukiseller-droid/commerce-agent-bench.

Open the folder on GitHubat commit f818ba8

Compare with similar skills

Accessibility Audit 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.

Accessibility Audit compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Accessibility Audit this skillharukiseller-droid/commerce-agent-bench101—~364Automated safety check: PassMIT
Product Cardthedaviddias/ux-patterns-for-developers259—~885Automated safety check: PassCustom licence
Scoutqa Testgithub/awesome-copilot40k1 repos~3.5kAutomated safety check: PassMIT
Imagewentorai/Research-Claw858—~1.6kAutomated safety check: PassCustom licence
Web Interface Guidelines Reviewervercel-labs/openreview1.7k97 repos~308Automated safety check: PassNone
Accessibility Reviewmarkmead/hyperui12k1 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • Product Card

    thedaviddias/ux-patterns-for-developers

    A skill your agent uses when implementing product display cards for e-commerce.

    259 GitHub stars~885 tokensUpdated 5 days ago
    Sales & SupportAuto-check passed
  • Scoutqa Test

    github/awesome-copilot

    Official

    This skill should be used when the user asks to "test this website", "run exploratory testing", "check for accessibility issues", "verify the login flow works", "find bugs on this page", or requests…

    40k GitHub starsUsed in 1 repo~3.5k tokens
    Testing & QAAuto-check passed
  • Image

    wentorai/Research-Claw

    Image processing workflow guide for format selection, resizing, cropping, compression, metadata, transparency, color profiles, and destination-specific exports.

    858 GitHub stars~1.6k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • Web Interface Guidelines Reviewer

    vercel-labs/openreview

    Official

    Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my…

    1.7k GitHub starsUsed in 97 repos~308 tokens
    Frontend & DesignAuto-check passed
  • Accessibility Review

    markmead/hyperui

    Run a WCAG 2.1 AA accessibility audit on a design or page. An agent skill from markmead/hyperui.

    12k GitHub starsUsed in 1 repo~1.1k tokens
    Frontend & DesignAuto-check passed
  • Web Animation Design

    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.

    11k GitHub starsUsed in 2 repos~2.7k tokens
    Frontend & DesignAuto-check passed

More from harukiseller-droid/commerce-agent-bench

All 10 skills in this repo
  • Commerce Fact Safety

    harukiseller-droid/commerce-agent-bench

    Classify ecommerce claims as FACT, INFERENCE, or UNKNOWN using traceable evidence.

    101 GitHub stars~470 tokensUpdated 1 mo ago
    Auto-check passed
  • Ecommerce PR Review

    harukiseller-droid/commerce-agent-bench

    Review ecommerce pull requests in a fixed evidence-first order.

    101 GitHub stars~413 tokensUpdated 1 mo ago
    Auto-check passed
  • Code Change Verification

    harukiseller-droid/commerce-agent-bench

    Verify a source change, its tests, its diff boundaries, and remaining risk.

    101 GitHub stars~370 tokensUpdated 1 mo ago
    Auto-check passed
  • PR Draft Summary

    harukiseller-droid/commerce-agent-bench

    Produce a factual pull-request summary from verified changes and checks.

    101 GitHub stars~350 tokensUpdated 1 mo ago
    Auto-check passed
  • Woocommerce Code Review

    harukiseller-droid/commerce-agent-bench

    Review WooCommerce hooks, product data, template overrides, escaping, and regression risks.

    101 GitHub stars~415 tokensUpdated 1 mo ago
    Auto-check passed
  • Pinterest Content Generator

    harukiseller-droid/commerce-agent-bench

    Generate ecommerce Pinterest metadata grounded in verified product or page facts.

    101 GitHub stars~382 tokensUpdated 1 mo ago
    Auto-check passed

Questions about Accessibility Audit

What does Accessibility Audit do?

Review ecommerce UI code for practical accessibility regressions in buyer flows. Accessibility Audit is an agent skill from harukiseller-droid/commerce-agent-bench. Review ecommerce UI code for practical accessibility regressions in buyer flows.

When should I use Accessibility Audit?

Accessibility Audit fits situations like: tasks that involve Accessibility; tasks that involve E-commerce operations.

How do I install Accessibility Audit in Claude Code?

Run `npx skills add harukiseller-droid/commerce-agent-bench --skill accessibility-audit -a claude-code`. Or copy the skill folder (.agents/skills/accessibility-audit in harukiseller-droid/commerce-agent-bench) into .claude/skills/accessibility-audit in your project. Claude Code loads it when a task matches its description.

How do I install Accessibility Audit in Codex?

Run `npx skills add harukiseller-droid/commerce-agent-bench --skill accessibility-audit -a codex`. Or copy the skill folder (.agents/skills/accessibility-audit in harukiseller-droid/commerce-agent-bench) into .agents/skills/accessibility-audit in your project. Codex loads it when a task matches its description.

Can I use Accessibility Audit in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add harukiseller-droid/commerce-agent-bench --skill accessibility-audit -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-audit, .gemini/skills/accessibility-audit, .github/skills/accessibility-audit and .opencode/skills/accessibility-audit in your project.

What does Accessibility Audit need to run?

SKILL.md names no scripts, command-line tools or credentials: Accessibility Audit is instructions for the agent only.

Does Accessibility Audit access the network?

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.

Is Accessibility Audit safe to install?

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.

What licence does Accessibility Audit use?

Accessibility Audit is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Accessibility Audit use?

About 364 tokens (SKILL.md is roughly 1.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Accessibility Audit?

Skills that share tags, products or a category with Accessibility Audit: Product Card (thedaviddias/ux-patterns-for-developers, 259 stars), Scoutqa Test (github/awesome-copilot, 40k stars), Image (wentorai/Research-Claw, 858 stars) and Web Interface Guidelines Reviewer (vercel-labs/openreview, 1.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Accessibility Audit?

harukiseller-droid (a GitHub user) maintains it in harukiseller-droid/commerce-agent-bench, which has 101 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on August 12, 2026.

Source: harukiseller-droid/commerce-agent-bench on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.