Summary
You get two tools here: agent-browser from Vercel for general web UI testing, and a Playwright wrapper baked into the Eve Horizon repo itself. Use agent-browser for most automation work, install it globally, then follow the snapshot-interact-assert cycle with interactive refs instead of brittle selectors. Inside the Eve Horizon codebase, skip the install and use the repo-pinned wrapper that already knows how to inject auth tokens and hit the local dashboard. Both options give you the same workflow: open a page, snapshot for refs, click or fill forms, capture screenshots, repeat. The documentation is thorough on session isolation and CI setup, which matters if you're running these checks in pipelines and don't want state bleeding between runs.
Install to Claude Code
npx -y skills add incept5/eve-skillpacks --skill eve-web-ui-testing-agent-browser --agent claude-codeInstalls into .claude/skills of the current project.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Files
SKILL.md
Select a file.
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →First SeenJun 3, 2026
