Summary
This is a lightweight browser automation setup that talks directly to Chrome via CDP instead of requiring an MCP server. You launch Chrome with remote debugging on port 9222, then use small Node scripts to navigate, run JavaScript, grab screenshots, or visually pick elements. The pick.js script is interesting because it lets you describe what you want in natural language and get back the selector and metadata. Everything runs locally, which matters if you're dealing with authenticated sessions or sensitive data. It's intentionally minimal, just five scripts that return JSON, but that covers most of what you need for scraping or testing workflows without heavyweight dependencies.
Install to Claude Code
npx -y skills add cexll/myclaude --skill browser --agent claude-codeInstalls into .claude/skills of the current project.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Files
SKILL.md
Select a file.
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
