skills.rest
haxlys
haxlysCOMMUNITY
Explore all skills by this author →
GitHub

core

Provide compact element references and deterministic controls for browser automation.

1|Updated Apr 27, 2026
Search Tags:#automation#cli#web-testing#browser#agent-browser#snapshot-refs
One-click install
npx skills add https://github.com/haxlys/skills --skill core-haxlys
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: core
Source: https://github.com/haxlys/skills/tree/main/vendored/agent-browser/skill-data/core
Command: npx skills add https://github.com/haxlys/skills --skill core-haxlys

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

The skill reduces the cognitive and token burden for AI agents when driving web tasks by providing compact, navigable references and deterministic browser controls.

Core Features & Use Cases

  • Compact refs for fast, low-cost interactions with web pages.
  • Core commands for navigating, clicking, filling forms, extracting data, and taking screenshots.
  • Use Case: Automate QA checks, data extraction from pages, and rapid-web task automation across multiple sessions.

Quick Start

Open a page, take an interactive snapshot, and interact with the discovered refs to automate a browser task.

Frequently Asked Questions about core

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

FAQPage Schema
How do I reduce token usage when automating web browser tasks with AI agents?▼

You can reduce token usage in browser automation by using compact element references that provide deterministic controls for navigating, clicking, and filling forms. This approach lowers the cognitive and token burden on AI agents during web interactions.

What is the best way to automate QA checks and data extraction across multiple browser sessions?▼

Automating QA checks and data extraction across multiple sessions is best handled by taking interactive snapshots of pages and interacting with discovered references to execute deterministic browser controls across tabs.

How do I start automating web testing tasks using agent-browser snapshots?▼

To start web testing automation, open a target page, take an interactive snapshot to discover elements, and interact with the discovered references to execute clicks, form fills, and data extraction.

Do I need an agent-browser tool to use compact element references for web interactions?▼

Yes, the agent-browser tool is required to use compact element references for web interactions. You also need a SKILL.md frontmatter with a name and description, with optional references to scripts or assets.

Can I manage multiple tabs and sessions when automating web tasks with AI agents?▼

Yes, you can manage multiple tabs and sessions when automating web tasks. The skill provides deterministic browser controls that work across multiple sessions for activities like navigating and capturing screenshots.

Why does guiding AI agents through browser interactions consume so many tokens?▼

Guiding AI agents through browser interactions consumes many tokens because standard page elements lack compact navigable references. Providing deterministic browser controls and compact refs directly reduces this cognitive and token burden.

Related Skills

Explore More Software Engineering Skills→
hendripermanahendripermana

agent-browser

Drive a headless browser via inference.sh for web navigation and element interaction.

Community
Advanced
shynlee04shynlee04

web-search

Search the web and extract content via Tavily and Exa using the inference.sh CLI.

Community
Intermediate
mmcmediammcmedia
2

workflows

Organize reusable micro-workflows for browser automation, data tasks, and file operations.

Community
Intermediate
platonaiplatonai
1.1k

browser4-cli

Automate browser interactions for web testing, form filling, screenshots, and data extraction.

Community
Advanced