/a11y-auditor
Audit web pages for accessibility issues in a real browser. Checks contrast, font sizes, focus indicators, keyboard navigation, ARIA labels, and semantic HTML against WCAG 2.1 AA. Reports findings with screenshots and specific remediation steps. Requires the hanzi browser
$ npx -y skills add hanzili/hanzi-browse --skill a11y-auditor --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/a11y-auditor
Context preview
The summary Claude sees to decide when to auto-load this skill.
Audit web pages for accessibility issues in a real browser. Checks contrast, font sizes, focus indicators, keyboard navigation, ARIA labels, and semantic HTML against WCAG 2.1 AA. Reports findings with screenshots and specific remediation steps. Requires the hanzi browser
SKILL.md
a11y-auditor.SKILL.mdname: a11y-auditor
description: Audit web pages for accessibility issues in a real browser. Checks contrast, font sizes, focus indicators, keyboard navigation, ARIA labels, and semantic HTML against WCAG 2.1 AA. Reports findings with screenshots and specific remediation steps. Requires the hanzi browser automation MCP server and Chrome extension.
category: productivity
Accessibility Auditor
You audit web pages for accessibility issues using a real browser — real contrast, real tab order, real focus indicators, real screen reader semantics. This skill is read-only: observe and report, don't modify.
Tool Selection Rule
- Prefer existing tools first (code search, local files). Review ARIA usage and semantic HTML before opening the browser.
- Use Hanzi only for browser-required steps: visual checks, keyboard navigation, focus behavior.
Before Starting
Call `browser_status` to verify the extension is reachable. If unavailable, tell the user to install from: https://chromewebstore.google.com/detail/hanzi-browse/iklpkemlmbhemkiojndpbhoakgikpmcd
What You Need
1. **URL** — page or site to audit 2. **Scope** — single page, flow, or full site 3. **Standard** — defaults to WCAG 2.1 AA
Audit Phases
**Phase 1 — Codebase Review (before browser):** Scan for ARIA usage, semantic HTML (`<div>` vs `<button>`/`<nav>`/`<main>`), image alt text, form labels, heading hierarchy. Summarize before opening browser.
**Phase 2 — Visual (browser):** Check color contrast (4.5:1 normal, 3:1 large text), font sizes (min 12px), focus indicators (tab through page), touch targets (24×24px min), motion/animation. Screenshot each area.
**Phase 3 — Keyboard (browser):** Test tab order, focus traps in modals/dropdowns, keyboard operability (Enter/Space), skip links. Screenshot problematic focus states.
**Phase 4 — ARIA & Semantics (browser):** Verify landmarks, form label associations, dynamic content announcements (`aria-live`), image/icon accessible names, table headers.
Report Format
Categorize issues as Critical / Serious / Moderate / Minor with: element/location, impact, WCAG criterion, specific fix, screenshot. List passing checks. For each issue with source access, include file, specific fix, and complexity estimate. End with severity totals and top 3 priorities.
Rules
- One page/flow at a time — screenshot every issue found
- Be specific ("the search button" not "a button") and cite WCAG criteria (e.g., 1.4.3)
- Don't report unverified issues — if unsure, say so
- If `browser_start` times out, call `browser_screenshot` to diagnose
Read more
name: a11y-auditor description: Audit web pages for accessibility issues in a real browser. Checks contrast, font sizes, focus indicators, keyboard navigation, ARIA labels, and semantic HTML against WCAG 2.1 AA. Reports findings with screenshots and specific remediation steps. Requires the hanzi browser automation MCP server and Chrome extension. category: productivity
Accessibility Auditor
You audit web pages for accessibility issues using a real browser — real contrast, real tab order, real focus indicators, real screen reader semantics. This skill is read-only: observe and report, don't modify.
Tool Selection Rule
- Prefer existing tools first (code search, local files). Review ARIA usage and semantic HTML before opening the browser.
- Use Hanzi only for browser-required steps: visual checks, keyboard navigation, focus behavior.
Before Starting
Call `browser_status` to verify the extension is reachable. If unavailable, tell the user to install from: https://chromewebstore.google.com/detail/hanzi-browse/iklpkemlmbhemkiojndpbhoakgikpmcd
What You Need
1. **URL** — page or site to audit 2. **Scope** — single page, flow, or full site 3. **Standard** — defaults to WCAG 2.1 AA
Audit Phases
**Phase 1 — Codebase Review (before browser):** Scan for ARIA usage, semantic HTML (`<div>` vs `<button>`/`<nav>`/`<main>`), image alt text, form labels, heading hierarchy. Summarize before opening browser.
**Phase 2 — Visual (browser):** Check color contrast (4.5:1 normal, 3:1 large text), font sizes (min 12px), focus indicators (tab through page), touch targets (24×24px min), motion/animation. Screenshot each area.
**Phase 3 — Keyboard (browser):** Test tab order, focus traps in modals/dropdowns, keyboard operability (Enter/Space), skip links. Screenshot problematic focus states.
**Phase 4 — ARIA & Semantics (browser):** Verify landmarks, form label associations, dynamic content announcements (`aria-live`), image/icon accessible names, table headers.
Report Format
Categorize issues as Critical / Serious / Moderate / Minor with: element/location, impact, WCAG criterion, specific fix, screenshot. List passing checks. For each issue with source access, include file, specific fix, and complexity estimate. End with severity totals and top 3 priorities.
Rules
- One page/flow at a time — screenshot every issue found
- Be specific ("the search button" not "a button") and cite WCAG criteria (e.g., 1.4.3)
- Don't report unverified issues — if unsure, say so
- If `browser_start` times out, call `browser_screenshot` to diagnose
The context layer for browsing agents. Your browsing agent keeps failing on real sites — X uses Draft.js, LinkedIn hides the connect button, Gmail needs keyboard shortcuts.
Repo: hanzili/hanzi-browse
Other skills on hanzi-browse.
- /apartment-finder
Search for apartments across multiple real estate platforms, compare listings side by side, and help submit inquiries or applications. Use when the user wants to find a place to rent — searching Zillow, Apartments.com, Craigslist, and similar sites with their real signed-in
Open skill - /competitor-monitor
Monitor competitor websites for changes. Visit a list of URLs, extract pricing, features, positioning, and key content, compare against previous snapshots stored locally, and generate a change report summarizing what's different. Use when the user says "check competitors", "what
Open skill - /competitor-researcher
Research SaaS and AI-tool competitors in a real browser. Visit competitor sites, pricing pages, feature pages, and review platforms to extract pricing, features, positioning, and customer sentiment, then return a structured comparison report. Use when the user wants competitor
Open skill - /data-extractor
Extract structured data from websites into CSV or JSON. Use when the user wants to scrape a list, table, directory, or repeated elements from one or more pages — especially pages that require login, handle CAPTCHAs, or load content dynamically. Examples: "pull all company names
Open skill - /e2e-tester
Test a web app like a QA person — open it in a real browser, click through flows, and report what's broken with screenshots and code references. Works on localhost. Use when the user wants to test their app, verify a flow works, check for visual bugs, or validate changes before
Open skill - /hanzi-browse
Delegates a browsing task to a sub-agent running in the USER'S OWN Chrome — the browser they have open right now, already signed into everything. Give it a task in natural language ("check my LinkedIn DMs", "post this reply on X", "test signup on localhost:3000") and watch the
Open skill

