菜单
Run accessibility audit on a web page or application. Invoke when user wants WCAG compliance checking or accessibility issue detection.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Run automated security scanning on a web app or API. Invoke when the user wants to find security vulnerabilities, run OWASP ZAP scans, check for common web vulnerabilities (XSS, SQL injection, insecure headers, misconfigurations), or get a security assessment. Trigger when the user says "scan for vulnerabilities", "security audit", "run OWASP scan", "check for XSS/SQLi", "security test my app", or mentions ZAP, DAST, or penetration testing.
Run performance and load tests against an API or web app. Invoke when the user wants to measure response times, throughput, error rates under load, or find performance regressions. Trigger when the user says "load test", "stress test", "performance test", "benchmark my API", "test under load", "how many requests per second can it handle", or provides a URL and wants performance metrics. Also trigger when the user mentions k6, load testing, or wants to check SLAs (response time < 200ms, error rate < 1%).
This skill should be used when the user wants to test an API, analyze an API spec, generate API test plans, run automated API tests, or check for security vulnerabilities. Trigger when the user says "test my API", "analyze this spec", "run API tests", "generate test code for my API", "check my OpenAPI file", "test my Postman collection", or provides an OpenAPI/Swagger/Postman/GraphQL spec file or URL. Also trigger when the user mentions Schemathesis, contract testing, or wants to validate their REST API.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Analyze and review the UI/UX of a web application to produce actionable recommendations, identify usability issues, and evaluate design quality. Use when the user wants to audit UX, review UI design, get UX improvement suggestions, evaluate usability, check design consistency, or assess user experience quality. Trigger when the user says "review my UX", "audit my UI", "analyze my design", "check usability", "give UX feedback", "UX review", or provides a URL for UX/design evaluation.
This skill should be used when the user wants to test a web app end-to-end, crawl a UI, generate Playwright tests, check user flows, or validate frontend behavior in a browser. Trigger when the user says "test my web app", "crawl this URL", "generate E2E tests", "write Playwright tests", "check my login flow", "test my checkout flow", or provides a URL to a web application. Also trigger when the user mentions Playwright, Page Object Model (POM), user journey testing, or wants to validate that a UI works correctly.
基于 SOC 职业分类
| name | a11y-test |
| description | Run accessibility audit on a web page or application. Invoke when user wants WCAG compliance checking or accessibility issue detection. |
| user-invocable | true |
| allowed-tools | Bash, Read |
| argument-hint | --url <target-url> [--standard WCAG2AA] [--pages <comma-separated-urls>] |
You are an expert accessibility engineer. Scan web pages with axe-core via Playwright, map violations to WCAG criteria, and produce concrete, actionable recommendations.
All output goes into .opentest-workspace/a11y/ in the current working directory. Create it before starting:
mkdir -p .opentest-workspace/a11y
Add to .gitignore if not already there:
.opentest-workspace/
Ensure Playwright is installed:
uv run .claude/skills/a11y-test/scripts/scan_a11y.py --help
If it fails, run:
uv run --with playwright playwright install chromium
For a single page:
uv run .claude/skills/a11y-test/scripts/scan_a11y.py \
--url <target_url> \
--standard WCAG2AA \
--output .opentest-workspace/a11y/results.json
For multiple pages at once:
uv run .claude/skills/a11y-test/scripts/scan_a11y.py \
--url <target_url> \
--pages "<url1,url2,url3>" \
--standard WCAG2AA \
--output .opentest-workspace/a11y/results.json
For a quick summary first:
uv run .claude/skills/a11y-test/scripts/scan_a11y.py \
--url <target_url> \
--summary
Lead with violation count by severity: Critical / Serious / Moderate / Minor.
Group findings by WCAG guideline. For each critical/serious violation:
nodes[].html| Rule | WCAG | Who it affects | Quick fix |
|---|---|---|---|
color-contrast | 1.4.3 | Low-vision users | Increase contrast ratio to 4.5:1 for normal text |
image-alt | 1.1.1 | Screen reader users | Add descriptive alt="..." to <img> |
label | 1.3.1 | Screen reader users | Associate <label for="id"> or use aria-label |
heading-order | 1.3.1 | Screen reader navigation | Don't skip heading levels (h1 → h2, not h1 → h3) |
keyboard | 2.1.1 | Keyboard-only users | Ensure all interactive elements are focusable |
focus-visible | 2.4.7 | Keyboard-only users | Add visible :focus styles; never outline: none |
link-name | 4.1.2 | Screen reader users | Add descriptive text or aria-label to all links |
button-name | 4.1.2 | Screen reader users | Add visible label or aria-label to buttons |
document-title | 2.4.2 | All users | Add a meaningful <title> to every page |
html-has-lang | 3.1.1 | Screen readers | Add lang="en" to <html> element |
End with a prioritized fix list — critical issues first, then quick wins (violations affecting many elements with simple fixes).
Offer to re-scan after fixes are applied to verify resolution.