Skip to content
TakoAPI
Back to skills

webcli

by erdinccurebal

Web & Frontend Development
460Downloads reported by clawskills.sh
0Views
0 likesSign in to like this skill
—Not yet rated
Your rating

Brief

Browse the web, read page content, click buttons, fill forms, take screenshots, and get accessibility snapshots.

Description

What This Skill Does

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.

When to Use It

  • 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

Example Workflow

INPUT

User asks: go to example.com/login, log in with my credentials, and screenshot the dashboard

AGENT
  1. 1

    Run webcli go https://example.com/login

  2. 2

    Run webcli snapshot to get accessibility refs for the email and password fields

  3. 3

    Run webcli fill @e1 'user@example.com' and webcli fill @e2 'password123'

  4. 4

    Run webcli click 'Log in' then webcli sleep 1500

  5. 5

    Run webcli screenshot -o dashboard.png to capture the result

OUTPUT

Screenshot saved to dashboard.png showing the authenticated dashboard page

Requirements

  • npx playwright install chromium (one-time browser binary install)

Installation

clawhub install erdinccurebal/webcli

Run the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.

Links