agentic-browser-0-1-2
por xyny89
Web & Frontend DevelopmentResumen
Browser automation for AI agents via inference.sh.
Descripción
Qué hace esta skill
Browser automation for AI agents via inference.sh. Uses Playwright under the hood with an @e ref system that assigns short identifiers to interactive page elements. Supports clicking, form filling, drag-and-drop, file upload, JavaScript execution, screenshots, and video recording.
The @e ref system abstracts away CSS selectors and XPaths, making element targeting simpler to use in agent workflows without managing a local browser environment.
Cuándo usarla
- Auto-filling and submitting web forms on behalf of a user
- Scraping product prices or listings from e-commerce pages
- Recording browser sessions to debug UI regressions
- Logging into sites and extracting data from authenticated pages
- Running scripted browser workflows from the command line
Flujo de trabajo de ejemplo
User asks: search Google for 'weather today' and return the page snapshot
- 1
Open a new browser session at https://google.com
- 2
Receive @e refs for interactive elements including the search input
- 3
Fill the search input with 'weather today' and press Enter
- 4
Wait for results to load, then call snapshot to get fresh @e refs
- 5
Close the session and return the snapshot text
Page snapshot with element refs showing weather search results
Requisitos
- inference.sh account
- inference.sh CLI (infsh) installed
Instalación
clawhub install xyny89/agentic-browser-0-1-2Ejecuta el comando de la CLI o pega el prompt en Claude Code, Cursor, Codex o el agente de programación que uses.