webcli
por erdinccurebal
Web & Frontend DevelopmentResumen
Browse the web, read page content, click buttons, fill forms, take screenshots, and get accessibility snapshots.
Descripción
Qué hace esta skill
webcli is a headless browser CLI tool that lets agents navigate websites, read page content, interact with elements, and capture screenshots or PDFs. It runs a persistent browser daemon and exposes commands for clicks, form fills, accessibility snapshots, and JavaScript evaluation.
Unlike raw Playwright scripts, webcli exposes browser control as simple shell commands that an AI agent can chain without writing or managing code files.
Cuándo usarla
- Scraping product prices from an e-commerce site
- Filling and submitting a web form automatically
- Taking screenshots of a dashboard for reporting
- Logging into a web app and extracting account data
- Testing a web UI flow without writing Playwright code
Flujo de trabajo de ejemplo
User asks: go to example.com/login, log in with my credentials, and screenshot the dashboard
- 1
Run
webcli go https://example.com/login - 2
Run
webcli snapshotto get accessibility refs for the email and password fields - 3
Run
webcli fill @e1 'user@example.com'andwebcli fill @e2 'password123' - 4
Run
webcli click 'Log in'thenwebcli sleep 1500 - 5
Run
webcli screenshot -o dashboard.pngto capture the result
Screenshot saved to dashboard.png showing the authenticated dashboard page
Requisitos
- npx playwright install chromium (one-time browser binary install)
Instalación
clawhub install erdinccurebal/webcliEjecuta el comando de la CLI o pega el prompt en Claude Code, Cursor, Codex o el agente de programación que uses.