c-browser — Claude Code skill: browser automation and install
This skill guides an agent through page navigation, clicks, form entry, screenshots, and content collection. Use it for browser tasks and web-page checks.
npx skills add daxaur/openpaw --skill c-browser -a claude-codeWhat c-browser does
c-browser describes browser work with agent-browser and playwright-cli. The former reads structured snapshots with references to interactive elements; the latter supports structured automation and testing flows. An agent can open a page, inspect its snapshot, click a control, or enter text into a field.
Check a fresh snapshot before clicking: element references can change as you move between pages. For sign-in flows, the skill recommends proceeding one page at a time and verifying that each page loads. Scraping guidance also calls for respecting robots.txt and request limits.
With playwright-cli, install the browser first using playwright-cli install-browser. Both tools have commands for screenshots, while navigation and page actions use their respective command sets.
What it helps with
- inspect a page’s interactive controls
- enter and submit a web form
- capture an annotated page screenshot
- collect site content while respecting request limits
Example prompts for the agent
- Open the page and show its interactive elements before clicking anything.
- Enter this search term in the form and capture the results page.
- Complete the sign-in flow one page at a time, checking that each page loads.
How to install c-browser
1Skills CLI (Vercel)
npx skills add daxaur/openpaw --skill c-browser -a claude-code2Manually: put the files in place
~/.claude/skills/c-browser/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/c-browser/
1Skills CLI (Vercel)
npx skills add daxaur/openpaw --skill c-browser -a codex2Manually: put the files in place
.agents/skills/c-browser/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add daxaur/openpaw --skill c-browser -a cursor2Manually: put the files in place
.cursor/skills/c-browser/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install daxaur/openpaw c-browser2Manually: put the files in place
.github/skills/c-browser/SKILL.md1Skills CLI (Vercel)
npx skills add daxaur/openpaw --skill c-browser -a gemini-cli2Platform CLI
gemini skills install https://github.com/daxaur/openpaw --path skills/c-browserManually: put the files in place
.devin/skills/c-browser/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add daxaur/openpaw --skill c-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 c-browser
How do I install c-browser in Claude Code?
Run npx skills add daxaur/openpaw --skill c-browser -a claude-code. The skill file is placed at ~/.claude/skills/c-browser/SKILL.md.
What does c-browser do?
It guides an agent through browser tasks such as navigating pages, clicking controls, filling fields, taking screenshots, and collecting page content.
How do agent-browser and playwright-cli differ in c-browser?
agent-browser uses snapshots and references for interactive elements. playwright-cli is intended for structured automation and testing flows.
Source text
SKILL.md · MIT
--- name: c-browser description: Headless browser automation — navigate pages, click elements, fill forms, take screenshots, scrape content using agent-browser or playwright-cli. tags: [browser, automation, scraping, web] --- # Browser Automation ## agent-browser (Vercel) Navigate and interact with web pages using structured snapshots: ```bash # Open a URL agent-browser open "https://example.com" # Get interactive element snapshot (shows clickable refs) agent-browser snapshot -i # Click an element by ref agent-browser click @e2 # Fill a form field agent-browser fill @e5 "search query" # Take annotated screenshot agent-browser screenshot --annotate # Type text agent-browser type "hello world" # Press keys agent-browser press Enter ``` ## playwright-cli (Microsoft) Token-efficient browser automation designed for AI agents: ```bash # Install browser (first time) playwright-cli install-browser # Navigate to URL playwright-cli navigate "https://example.com" # Get page snapshot playwright-cli snapshot # Click element playwright-cli click "Submit button" # Fill input playwright-cli fill "Search" "query text" # Screenshot playwright-cli screenshot ``` ## Guidelines - Use agent-browser for AI-driven web interaction (snapshot-ref pattern) - Use playwright-cli for structured automation and testing flows - Always check snapshots before clicking — element refs change between pages - For login flows, navigate step by step and verify each page loads - Respect robots.txt and rate limits when scraping
© daxaur · MIT · daxaur/openpaw
