🌐
AutomationPython

Hive Browser Automation

by aden-hive

Hive Browser Automation is an Automation skill for Claude Code, published by aden-hive in hive.

10.9K stars5.7K forkson aden-hive/hiveAdded 2026/08/15Repository updated 2026/08/13
agentagent-frameworkagent-skillsanthropicautomationautonomous-agentsclaudeharnessharness-engineeringhuman-in-the-loopopenaipythonself-hostedself-improving
Install in seconds
Install Hive Browser Automation
Copy Hive Browser Automation into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/aden-hive/hive/tree/main/core/framework/skills/_default_skills/browser-automation ~/.claude/skills/browser-automation

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/aden-hive/hive.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
core/framework/skills/_default_skills/browser-automation/SKILL.md in aden-hive/hive
Installs to
~/.claude/skills/browser-automation
Collection
One of 24 skills cataloged from this repository
Category
Automation1523 skills

What Hive Browser Automation does

Hive Browser Automation drives a real Chrome instance through the Beeline extension and CDP using the hive-browser CLI, covering lifecycle, screenshots, viewport-fraction coordinates, shadow-DOM inputs, and CSP quirks.

Hive Browser Automation is cataloged under Automation on DirSkills. Hive Browser Automation comes from a repository tagged agent, agent-framework, agent-skills, anthropic and automation.

Documentation

README

GCU Browser Automation

All GCU browser automation drives a real Chrome instance through the Beeline extension and Chrome DevTools Protocol (CDP). You drive it from the terminal: every command is hive-browser <command> ... --json, run through terminal_exec. Always pass --json so the result is machine-readable. That means clicks, keystrokes, and screenshots are processed by the actual browser's native hit testing, focus, and layout engines — not a synthetic event layer. Understanding this unlocks strategies that make hard sites easy.

Browser lifecycle & recovery — read this before "fixing" anything

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Hive Browser Automation

  • What else does aden-hive publish alongside Hive Browser Automation?

    Hive Browser Automation is one of 24 skills that DirSkills catalogs from aden-hive/hive, the repository it ships in. Its siblings there include Background Job Control, Browser Edge Cases and Chart Creation Foundations. Each one is a separate skill with its own page in this directory, installs the same way Hive Browser Automation does, and is maintained by aden-hive in that same repository. The rest of the collection is listed on the aden-hive/hive page.

  • How does Hive Browser Automation compare to other Automation skills?

    Hive Browser Automation ranks #159 by stars among the 1523 Automation skills in this catalog. The most-starred ones next to it are Autonomous Loops, Autonomous Agent Harness and Automation Audit Ops. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Hive Browser Automation against them. Open each page to compare what they document and how they install.

More from aden-hive/hive

Hive Browser Automation is one of 24 skills cataloged on DirSkills from aden-hive/hive.

See all 24 skills
2w ago

Background Job Control

Background Job Control manages long-running terminal jobs using start, poll, wait, and signal tools. Use it before launching builds, deploys, streaming logs, or taking over auto-backgrounded processes from terminal_exec.
Automation
10.9K5.7K
🔍
2w ago

Browser Edge Cases

Browser Edge Cases provides a standard operating procedure for debugging browser automation failures on complex websites. Use it when browser tools fail on LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
Automation
10.9K5.7K
📊
2w ago

Chart Creation Foundations

Chart Creation Foundations teaches the one-tool embedding contract for rendering BI/financial-grade ECharts and Mermaid charts that appear live in chat and save as high-DPI PNGs. Use it whenever chart_* tools are available to avoid chartjunk and missing downloads.
Data
10.9K5.7K
📋
2w ago

Colony Progress Tracker

Colony Progress Tracker claims tasks, records step progress, and verifies SOP gates in a shared SQLite queue. Use when your spawn message includes db_path and colony_id fields.
Automation
10.9K5.7K
🧠
2w ago

Context Preservation

Context Preservation proactively extracts critical values from tool results into working notes before automatic context pruning destroys them. Use it when an agent must retain URLs, API fields, IDs, and analysis conclusions across long tasks.
AI Engineering
10.9K5.7K
🔁
2w ago

Error Recovery

Error Recovery guides an agent through a decision tree for tool call failures: retry transient errors once, fix and retry structural ones, or escalate if blocking. It switches tools after repeated failures and logs failed tasks to a database.
AI Engineering
10.9K5.7K