deep-research
Conduct deep web research using the openbrowser-ai agent: decompose a query, investigate sub-questions across multiple sources, and produce a cited markdown…
Audit web pages for accessibility issues, WCAG compliance, and screen reader compatibility. Trigger when the user asks to: check accessibility, run an a11y audit, test WCAG compliance, check screen reader support, audit ARIA attributes, verify keyboard navigation, find
$ npx -y skills add billy-enrizky/openbrowser-ai --skill accessibility-audit --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/accessibility-auditContext preview
The summary Claude sees to decide when to auto-load this skill.
Audit web pages for accessibility issues, WCAG compliance, and screen reader compatibility. Trigger when the user asks to: check accessibility, run an a11y audit, test WCAG compliance, check screen reader support, audit ARIA attributes, verify keyboard navigation, find
name: accessibility-audit description: | Audit web pages for accessibility issues, WCAG compliance, and screen reader compatibility. Trigger when the user asks to: check accessibility, run an a11y audit, test WCAG compliance, check screen reader support, audit ARIA attributes, verify keyboard navigation, find accessibility issues, or check for missing alt text or labels. allowed-tools: Bash(openbrowser-ai:*) Bash(curl:*) Bash(uv:*) Bash(irm:*) Read Write
Audit web pages for accessibility issues following WCAG 2.1 guidelines using Python code execution. Checks heading structure, form labels, image alt text, ARIA attributes, landmark regions, and keyboard navigation.
All code runs via `openbrowser-ai -c`. The daemon starts automatically and persists variables across calls. All browser functions are async -- use `await`.
The CLI daemon also persists cookies and login state in `~/.config/openbrowser/profiles/daemon/storage_state.json`, so authenticated sessions can be reused across later runs.
Before running, verify openbrowser-ai is installed:
openbrowser-ai --help
If not found, install:
# macOS/Linux curl -fsSL https://raw.githubusercontent.com/billy-enrizky/openbrowser-ai/main/install.sh | sh # Windows (PowerShell) irm https://raw.githubusercontent.com/billy-enrizky/openbrowser-ai/main/install.ps1 | iex
openbrowser-ai -c - <<'EOF'
await navigate("https://example.com")
state = await browser.get_browser_state_summary()
print(f"Auditing: {state.title} ({state.url})")
# Store all findings
audit = {
"url": state.url,
"title": state.title,
"issues": [],
"checks": {}
}
EOFopenbrowser-ai -c - <<'EOF'
headings_result = await evaluate("""
(function(){
const headings = Array.from(document.querySelectorAll("h1,h2,h3,h4,h5,h6"));
const issues = [];
let prevLevel = 0;
const h1Count = headings.filter(h => h.tagName === "H1").length;
if (h1Count === 0) issues.push("No h1 element found");
if (h1Count > 1) issues.push("Multiple h1 elements: " + h1Count);
headings.forEach(h => {
const level = parseInt(h.tagName[1]);
if (prevLevel > 0 && level > prevLevel + 1)
issues.push("Skipped level: h" + prevLevel + " -> h" + level + " (\"" + h.textContent.trim().substring(0, 50) + "\")");
if (!h.textContent.trim())
issues.push("Empty heading: " + h.tagName);
prevLevel = level;
});
return {
total: headings.length,
h1Count,
hierarchy: headings.map(h => ({ tag: h.tagName, text: h.textContent.trim().substring(0, 80) })),
issues
};
})()
""")
audit["checks"]["headings"] = headings_result
for issue in headings_result.get("issues", []):
audit["issues"].append({"check": "headings", "wcag": "1.3.1", "issue": issue})
print(f"[HEADINGS] {issue}")
if not headings_result.get("issues"):
print("[HEADINGS] PASS")
EOFopenbrowser-ai -c - <<'EOF'
images_result = await evaluate("""
(function(){
const images = Array.from(document.querySelectorAll("img"));
const issues = [];
let withAlt = 0, withEmptyAlt = 0, missingAlt = 0;
images.forEach(img => {
const alt = img.getAttribute("alt");
const src = img.src?.substring(0, 100);
if (alt === null) {
missingAlt++;
issues.push("Missing alt: " + src);
} else if (alt === "") {
withEmptyAlt++;
} else {
withAlt++;
}
});
return { total: images.length, withAlt, withEmptyAlt, missingAlt, issues };
})()
""")
audit["checks"]["images"] = images_result
for issue in images_result.get("issues", []):
audit["issues"].append({"check": "images", "wcag": "1.1.1", "issue": issue})
print(f"[IMAGES] {issue}")
if not images_result.get("issues"):
total = images_result["total"]
with_alt = images_result["withAlt"]
print(f"[IMAGES] PASS ({total} images, {with_alt} with alt)")
EOFopenbrowser-ai -c - <<'EOF'
forms_result = await evaluate("""
(function(){
const inputs = Array.from(document.querySelectorAll("input:not([type=\"hidden\"]),select,textarea"));
const issues = [];
inputs.forEach(input => {
const id = input.id;
const ariaLabel = input.getAttribute("aria-label");
const ariaLabelledBy = input.getAttribute("aria-labelledby");
const title = input.getAttribute("title");
const label = id ? document.querySelector("label[for=\"" + id + "\"]") : null;
const parentLabel = input.closest("label");
const hasLabel = label || parentLabel || ariaLabel || ariaLabelledBy || title;
if (!hasLabel) {
issues.push({
tag: input.tagName,
type: input.type || "text",
name: input.name || "(none)",
placeholder: input.getAttribute("placeholder") || "(none)",
issue: "No label or aria-label"
});
}
});
return { totalInputs: inputs.length, unlabeled: issues.length, issues };
})()
""")
audit["checks"]["forms"] = forms_result
for issue in forms_result.get("issues", []):
tag = issue["tag"]
name = issue["name"]
itype = issue["type"]
audit["issues"].append({"check": "forms", "wcag": "1.3.1", "issue": f"Unlabeled {tag} name={name}"})
print(f"[FORMS] Unlabeled: <{tag}> type={itype} name={name}")
if not forms_result.get("issues"):
total_inputs = forms_result["totalInputs"]
print(f"[FORMS] PASS ({total_inputs} inputs, all labeled)")
EOFopenbrowser-ai -c - <<'EOF'
aria_result = await evaluate("""
(function(){
const issues = [];
const ariaElements = document.querySelectorAll("[role],[aria-label],[aria-labelledby],[aria-describedby],[aria-hidden]");
ariaElements.forEach(el => {
const ariaLabelledBy = el.getAttribute("aria-labelledby");
const ariaDescribedBy = el.getAttribute("aria-describedby");OpenBrowser is a framework for intelligent browser automation. It combines direct CDP communication with a CodeAgent architecture, where the LLM writes Python code executed in a persistent namespace, to navigate, interact with, and extract information from web pages autonomously.
Repo: billy-enrizky/openbrowser-ai
Conduct deep web research using the openbrowser-ai agent: decompose a query, investigate sub-questions across multiple sources, and produce a cited markdown…
Test web applications end-to-end by simulating user interactions and verifying expected outcomes. Trigger when the user asks to: test a web app, verify a user…
Download files from websites, save PDFs, and read downloaded content. Trigger when the user asks to: download a file, save a PDF, export a document, fetch a…
Fill out web forms, submit data, and handle login or registration flows. Trigger when the user asks to: fill a form, submit data on a website, log in to a…
Analyze web page content, structure, and layout to understand what a page contains and how it is organized. Trigger when the user asks to: analyze a page,…
Extract structured data from websites, scrape page content, and collect information across multiple pages. Trigger when the user asks to: extract data from a…