agent-browser · eyadsibai — Claude Code skill: browser automation, install
This skill gives an AI agent CLI control over a browser for form entry, page scraping, screenshots, and PDF output. Use it for browser automation tasks.
no license 166 installs ★ 7 updated 2026-01-15
npx skills add eyadsibai/ltk --skill agent-browser -a claude-codeWhat agent-browser does
This skill guides an agent through browser work from the CLI. It opens a page, reads an accessibility snapshot, and uses element references such as @e1 for actions. A fresh snapshot is needed after navigation or page changes.
The agent-browser commands cover navigation, clicks, text entry, dropdowns, waits, page data, screenshots, and PDF files. Snapshots can be limited to interactive elements or returned as JSON. Separate sessions allow more than one browser to be managed.
The CLI needs the agent-browser npm package, and agent-browser install downloads Chromium. The workflow is built around Bash commands; the source positions Playwright MCP as the option for deeper MCP tool integration and larger automation pipelines.
What it helps with
- navigate through pages from a CLI
- fill and submit web forms
- extract page text and attributes
- save screenshots or PDFs
- run separate browser sessions
Example prompts for the agent
- Open the page, inspect its interactive elements, and fill the form using the returned references.
- Visit the page and save a full-page screenshot as
output.png. - Collect the page text and links, then return the result as JSON.
How to install agent-browser
1Skills CLI (Vercel)
npx skills add eyadsibai/ltk --skill agent-browser -a claude-code2Manually: put the files in place
~/.claude/skills/agent-browser/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/agent-browser/
1Skills CLI (Vercel)
npx skills add eyadsibai/ltk --skill agent-browser -a codex2Manually: put the files in place
.agents/skills/agent-browser/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add eyadsibai/ltk --skill agent-browser -a cursor2Manually: put the files in place
.cursor/skills/agent-browser/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install eyadsibai/ltk plugins/ltk-devops/skills/agent-browser2Manually: put the files in place
.github/skills/agent-browser/SKILL.md1Skills CLI (Vercel)
npx skills add eyadsibai/ltk --skill agent-browser -a gemini-cli2Platform CLI
gemini skills install https://github.com/eyadsibai/ltk --path plugins/ltk-devops/skills/agent-browserManually: put the files in place
.devin/skills/agent-browser/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add eyadsibai/ltk --skill agent-browser -a opencodeClaude.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 agent-browser
How do I install agent-browser in Claude Code?
Run npx skills add eyadsibai/ltk --skill agent-browser -a claude-code. The skill is placed at ~/.claude/skills/agent-browser/SKILL.md.
What does agent-browser do?
It gives an agent a CLI workflow for browser control: inspect a snapshot, act on element references, read page data, and create screenshots or PDFs.
How is agent-browser different from Playwright MCP?
agent-browser targets Bash-based commands and small automation jobs. Playwright MCP is presented for deeper MCP tool integration and complex automation pipelines.
Similar skills
All skills for Browser and scraping →agent-browser by other authors comes first.