Agentic_programming-course playwright
Navigate websites and query page content using Playwright CLI. Use this skill when the user asks to open a URL, extract data from a page, or check UI state.
install
source · Clone the upstream repo
git clone https://github.com/CodelyTV/agentic_programming-course
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/CodelyTV/agentic_programming-course "$T" && mkdir -p ~/.claude/skills && cp -r "$T/05-mcps/3-mcp_vs_cli/4-multiple_cli/.agents/skills/playwright" ~/.claude/skills/codelytv-agentic-programming-course-playwright && rm -rf "$T"
manifest:
05-mcps/3-mcp_vs_cli/4-multiple_cli/.agents/skills/playwright/SKILL.mdsource content
Download the rendered HTML instead of PDF or screenshots. Use the Playwright CLI:
npx playwright open --save-har=/tmp/page.har --save-har-glob="**" <url> --headless
Or more directly, dump the fully rendered DOM:
node -e "const{chromium}=require('playwright');(async()=>{const b=await chromium.launch();const p=await b.newPage();await p.goto(process.argv[1],{waitUntil:'networkidle'});console.log(await p.content());await b.close()})();" <url> > /tmp/page.html
Then read
/tmp/page.html