Responsiveness Check
Test how a website's layout responds to viewport width changes. Resizes through breakpoints in a single browser session, screenshots each width, compares adjacent sizes, and reports where layouts break.
What this tests: Layout responsiveness — overflow, stacking, navigation transitions, content reflow.
What this does NOT test: General accessibility (ARIA, semantic HTML, heading hierarchy, colour contrast). Those don't vary by viewport width — use the ux-audit skill instead.
Browser Tool Priority
Before starting, detect available browser tools:
- playwright-cli (preferred) — supports resize, named sessions, and sub-agent parallelism. If installed, run
/playwright-clifirst to load the full command reference. - Playwright MCP (
mcp__plugin_playwright_playwright__*) —browser_resizefor viewport changes. - Chrome MCP (
mcp__claude-in-chrome__*) —resize_windowfor viewport changes. Uses the user's logged-in Chrome session.
If none are available, inform the user and suggest installing playwright-cli or Playwright MCP.
Operating Modes
Mode 1: Standard Check
When: "check responsive", "responsiveness check", "test breakpoints"
Test 8 key breakpoints that cover the device spectrum:
Process:
- Open the URL in a single browser session (height: 900px)
- Start at 320px. For each breakpoint width: a. Resize the viewport b. Wait briefly for CSS reflow (layout transition) c. Screenshot the above-fold area d. If the page has significant below-fold content, scroll and screenshot e. Run the 8 layout checks (see matrix below) f. Note any issues with severity
- Compare adjacent widths — identify where layout transitions occur
- Write the report
Mode 2: Sweep
When: "responsive sweep", "sweep all breakpoints", "find where it breaks"
Test every 160px from 320 to 2560 (15 widths total). Same single-session approach as Standard — just more data points. This is the mode for finding the exact width where a layout breaks.
Widths: 320, 480, 640, 800, 960, 1120, 1280, 1440, 1600, 1760, 1920, 2080, 2240, 2400, 2560
Briefly confirm before starting sweep mode (15 screenshots is a meaningful session).
Mode 3: Targeted Range
When: "check between 768 and 1024", "test tablet breakpoints", "focus on mobile widths"
Test a user-specified range at 80px increments. Use when a known trouble zone needs detailed investigation.
Example: "check between 768 and 1024" tests: 768, 848, 928, 1008 (plus 1024 as endpoint).
Multi-URL
When testing multiple URLs (e.g., "check the homepage, about page, and contact page"):
- Launch parallel sub-agents, one per URL (not per breakpoint)
- Each sub-agent runs a standard check on its URL in its own named session
- Combine results into a single report
Layout Check Matrix
These 8 checks target issues that actually vary by viewport width:
Transition Detection
The unique value of this skill is finding where layout transitions happen and whether they're clean.
When comparing screenshots at adjacent widths, flag any width where:
- Column count changes (3-col → 2-col → 1-col grid)
- Navigation mode switches (full nav → hamburger, or vice versa)
- Sidebar appears/disappears (content width jumps)
- Grid reflows (cards wrap to next row)
Report the exact width range where each transition occurs:
This tells the developer exactly where to set (or fix) their CSS breakpoints.
Severity Levels
Consistent with ux-audit:
Autonomy Rules
- Just do it: Resize viewport, take screenshots, analyse layout, compare widths
- Brief confirmation: Before sweep mode (15 viewports), before testing 4+ URLs in parallel
- Ask first: Before interacting with forms or clicking through authentication flows
Report Output
Write report to docs/responsiveness-check-YYYY-MM-DD.md (or inline for single-page quick checks).
See references/report-template.md [blocked] for the report structure.


