skills.rest
LeroyAdonis
LeroyAdonisCOMMUNITY
Explore all skills by this author →
GitHub

agent-browser

Automate browser navigation, form filling, and data extraction via CLI commands.

Updated Mar 2, 2026
Search Tags:#screenshots#cli#browser automation#session management#web scraping#form filling#playwright
One-click install
npx skills add https://github.com/LeroyAdonis/kitfix-2.0 --skill agent-browser-leroyadonis
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/LeroyAdonis/kitfix-2.0/tree/main/.github/skills/agent-browser
Command: npx skills add https://github.com/LeroyAdonis/kitfix-2.0 --skill agent-browser-leroyadonis

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? AI agents and automation scripts need a programmatic way to interact with websites—clicking buttons, filling forms, and extracting data—without parsing raw HTML or writing verbose Playwright code for every task. ## Core Features & Use Cases - Snapshot-Based Interaction: Get compact element references (@e1, @e2) from pages and use them to click, fill, select, and scroll with minimal token usage. - Session & State Management: Run isolated parallel sessions, save and restore authentication state, and persist cookies across runs. - Capture & Debugging: Take screenshots, record video, save pages as PDF, and capture Chrome DevTools performance profiles. - Use Case: Automate a login flow once, save the auth state to a file, then reuse it across future scraping or testing runs without re-entering credentials. ## Quick Start Ask the agent to open a website, snapshot the interactive elements, fill in the login form, and take a screenshot of the result.

Frequently Asked Questions about agent-browser

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate form filling with agent-browser?▼

Open the page with agent-browser open, run snapshot -i to get element refs like @e1, then use fill, select, and check commands with those refs before clicking the submit button. Re-snapshot after any navigation since refs are invalidated on page changes.

How do I save and reuse login sessions in browser automation?▼

After completing a login flow, run agent-browser state save auth.json to persist cookies and storage. Later, load it with agent-browser state load auth.json and navigate directly to protected pages without logging in again.

Can agent-browser run multiple browser sessions in parallel?▼

Yes, use the --session flag to create isolated sessions with separate cookies, storage, and tabs. Each session operates independently, enabling concurrent scraping or A/B testing across multiple sites.

Why does agent-browser report ref not found errors?▼

Refs are invalidated whenever the page changes through navigation, form submission, or dynamic content updates. Run snapshot -i again after any page change to obtain fresh element references before interacting.

Does agent-browser support proxies and mobile device testing?▼

Yes, it supports HTTP, HTTPS, and SOCKS proxies via flags or environment variables, plus proxy bypass rules. It can also drive Mobile Safari on iOS simulators through Appium on macOS with Xcode installed.

Related Skills

Explore More Software Engineering Skills→
zerobias-orgzerobias-org

dotenv-patterns

Load credentials from .env files using dotenv patterns for tests.

Official
Intermediate
agentic-inagentic-in
577

OCR and Documents

Extracts searchable text from scanned and image-heavy documents via OCR processing.

Official
Intermediate
mahmoud20138mahmoud20138
10

ip-rotation

Rotate IP addresses via proxies or Tor to bypass rate limits and retry blocked requests.

Community
Intermediate
HouseGarofaloHouseGarofalo
3

browserless

Automate headless Chrome browser tasks via REST API and WebSocket.

Official
Intermediate