Aller au contenu
TakoAPI
Retour aux skills

agentic-browser-0-1-2

par xyny89

Web & Frontend Development
906Téléchargements rapportés par clawskills.sh
0Vues
0 mention J'aimeConnecte-toi pour aimer ce skill
—Pas encore noté
Ta note

Résumé

Browser automation for AI agents via inference.sh.

Description

Ce que fait ce 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.

Quand l'utiliser

  • 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

Exemple de workflow

ENTRÉE

User asks: search Google for 'weather today' and return the page snapshot

AGENT
  1. 1

    Open a new browser session at https://google.com

  2. 2

    Receive @e refs for interactive elements including the search input

  3. 3

    Fill the search input with 'weather today' and press Enter

  4. 4

    Wait for results to load, then call snapshot to get fresh @e refs

  5. 5

    Close the session and return the snapshot text

SORTIE

Page snapshot with element refs showing weather search results

Prérequis

  • inference.sh account
  • inference.sh CLI (infsh) installed

Installation

clawhub install xyny89/agentic-browser-0-1-2

Exécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.

Liens