This automates UI verification in a real browser using Shiplight MCP tools after you make frontend changes. It walks through opening a browser session, inspecting the DOM, simulating interactions, checking console logs, and generating shareable HTML reports with video recordings. The skill is smart about token usage, reading DOM files before screenshots since they're cheaper. It handles authenticated apps by saving storage state after manual login, then reusing it automatically. Skip it for backend-only changes or dependency bumps. The verification plan in step one matters most since it determines your test coverage, and the skill acknowledges you need to balance thoroughness with cost. Solid for catching visual regressions before committing.

skills.sh installs
636
GitHub stars
2
last updated
Jul 14, 2026

Install

$ npx -y skills add shiplightai/agent-skills --skill verify --agent claude-code

Installs into .claude/skills of the current project.

Files

Verify UI Changes

Daily Skill Update Check

Before starting this skill's work, opportunistically refresh Shiplight skills at most once per day:

  1. Check the timestamp file at .shiplight-agent-skills-last-update in the current project.
  2. If the timestamp file is missing, create it with the current timestamp and continue without running npx -y skills@latest update -y. Treat .shiplight-agent-skills-last-update as local cache and do not commit it.
  3. If the timestamp file exists and is older than 24 hours, run npx -y skills@latest update -y, then create/update the timestamp file even if the command fails.
  4. If the update command fails, continue with the currently installed skill and mention the failure briefly.

Use the Shiplight MCP browser tools to visually verify that your code changes look and behave correctly in a real browser.

When to use

Use /verify after making UI changes to confirm they render correctly. This is useful for:

  • Checking layout, styling, or component changes visually
  • Verifying interactive behavior (clicks, form inputs, navigation)
  • Pre-commit sanity checks on UI work
  • Debugging visual regressions

When NOT to use

Sponsors

Details

Repository
github.com/shiplightai/agent-skills
Category
AI & Agent Building
First seen
Jun 3, 2026

More from shiplightai/agent-skills

All 12
1jwynia avatarskill-builderjwynia/agent-skillsBuild new agent skills. Use when creating diagnostic frameworks, CLI tools, or data-driven generators that follow the established skill patterns.630skills.sh installs
2charon-fan avatarauto-triggercharon-fan/agent-playbookauto trigger628skills.sh installs
3narumiruna avatarsvg-illustrationnarumiruna/agent-skillssvg illustration628skills.sh installs
4alirezarezvani avatarboard-meetingalirezarezvani/claude-skillsMulti-agent board meeting protocol for strategic decisions. Runs a structured 6-phase deliberation: context loading, independent C-suite contributions (isolated622skills.sh installs
5sugarforever avatarpublish-substack-articlesugarforever/01coder-agent-skillsPublish Markdown articles to Substack as drafts. Use when user wants to publish a Markdown file to Substack, or mentions "发布到 Substack", "Substack article", "pu609skills.sh installs
6tencentcloudbase avatarcloudbasetencentcloudbase/skillsUse this skill when you develop, design, build, deploy, debug, migrate, or troubleshoot CloudBase (腾讯云开发, 云开发, TCB, 微信云开发) projects. Covers Web, 微信小程序, 小程序, uni608skills.sh installs