responsive-reviewer — Claude Code skill: review and install
responsive-reviewer is a Claude Code skill that checks matching desktop and mobile interface states. It focuses on whether the main task stays clear and usable across screen sizes.
MIT ★ 529 updated 2026-11-17
npx skills add ShuaiMXu/happyhands --skill responsive-reviewer -a claude-codeWhat responsive-reviewer does
The skill compares content order and action visibility, looks for overflow and touch-target issues, and flags regressions tied to specific breakpoints. A review needs matching viewport states, a critical task, and the responsive source rules.
Its output contains structured evidence, findings, suggested changes, and limitations. When inputs or professional review are missing, it marks the result needs-evidence. Two viewports cannot represent every device or input method. The skill does not fabricate an Experience Score or turn one project observation into a universal rule.
What it helps with
- compare content order across desktop and mobile states
- find hidden actions and overflowing content
- check touch targets and breakpoint-specific regressions
- record limits in a responsive interface review
Example prompts for the agent
- Compare the main task across these desktop and mobile states using the responsive source rules.
- Check these matched views for hidden actions, overflow, and breakpoint regressions.
- Return a structured responsive review and flag any missing evidence.
How to install responsive-reviewer
1Skills CLI (Vercel)
npx skills add ShuaiMXu/happyhands --skill responsive-reviewer -a claude-code2Manually: put the files in place
~/.claude/skills/responsive-reviewer/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/responsive-reviewer/
1Skills CLI (Vercel)
npx skills add ShuaiMXu/happyhands --skill responsive-reviewer -a codex2Manually: put the files in place
.agents/skills/responsive-reviewer/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add ShuaiMXu/happyhands --skill responsive-reviewer -a cursor2Manually: put the files in place
.cursor/skills/responsive-reviewer/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install ShuaiMXu/happyhands skills/product-design/responsive-reviewer2Manually: put the files in place
.github/skills/responsive-reviewer/SKILL.md1Skills CLI (Vercel)
npx skills add ShuaiMXu/happyhands --skill responsive-reviewer -a gemini-cli2Platform CLI
gemini skills install https://github.com/ShuaiMXu/happyhands --path skills/product-design/responsive-reviewerManually: put the files in place
.devin/skills/responsive-reviewer/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about responsive-reviewer
How do I install responsive-reviewer in Claude Code?
Run npx skills add ShuaiMXu/happyhands --skill responsive-reviewer -a claude-code. The skill file is placed at ~/.claude/skills/responsive-reviewer/SKILL.md.
What does responsive-reviewer do?
It compares matched desktop and mobile interface states, checking content order, action visibility, overflow, touch targets, and breakpoint regressions. Its report includes evidence, findings, proposed changes, and limitations.
What does responsive-reviewer need for a review?
It needs matched viewport states, a critical task, and responsive source rules. If required inputs or professional review are missing, it marks the result needs-evidence.
Source text
SKILL.md · MIT
--- name: responsive-reviewer description: "Review task continuity, layout and content priority across matched desktop and mobile states." --- # Responsive Reviewer Ensure the critical task remains understandable and operable across screen sizes. ## Required evidence - matched viewports - critical task - responsive source rules ## Decisions - Compare content order and action visibility - Check overflow and touch targets - Identify breakpoint-specific regressions ## Boundary Two viewports do not cover every device or input mode. Return structured evidence, findings, proposed updates and limitations. Use `needs-evidence` when required inputs or professional review are missing. Never invent an Experience Score or promote a project observation into a universal rule.
© ShuaiMXu · MIT · ShuaiMXu/happyhands