Saltar al contenido
TakoAPI
Volver a skills

midscene-computer-browser

por quanru

Web & Frontend Development
305Descargas según clawskills.sh
1Vistas
0 me gustaInicia sesión para dar me gusta a esta skill
—Aún sin valoraciones
Tu valoración

Resumen

Vision-driven browser automation using Midscene.

Descripción

Qué hace esta skill

Vision-driven browser automation that operates from screenshots alone, without needing DOM access or accessibility labels. Launches headless Chrome via Puppeteer and interacts with any visible page element using natural language instructions. Works across any frontend technology stack.

Works from screenshots alone, so it handles any frontend stack without needing DOM access, custom selectors, or accessibility attributes.

Cuándo usarla

  • Scraping product prices from e-commerce pages
  • Filling and submitting multi-step online forms
  • Taking screenshots of web pages for review or archiving
  • Verifying UI behavior after a deployment
  • Extracting data from paginated tables or dashboards

Flujo de trabajo de ejemplo

ENTRADA

User asks: Get the titles of the top 5 articles on Hacker News

AGENTE
  1. 1

    Connect to https://news.ycombinator.com

  2. 2

    Take a screenshot to confirm the page has loaded

  3. 3

    Act: read the titles of the top 5 articles from the page

  4. 4

    Close the browser

SALIDA

List of the top 5 Hacker News article titles extracted from the page

Requisitos

  • MIDSCENE_MODEL_API_KEY environment variable (API key from a supported vision model provider)
  • MIDSCENE_MODEL_NAME environment variable
  • MIDSCENE_MODEL_BASE_URL environment variable
  • MIDSCENE_MODEL_FAMILY environment variable

Instalación

clawhub install quanru/midscene-computer-browser

Ejecuta el comando de la CLI o pega el prompt en Claude Code, Cursor, Codex o el agente de programación que uses.

Enlaces