askill
browser-agent

browser-agentSafety 95Repository

Autonomous browser agent for complex multi-step web tasks. WHEN: User needs complex web automation, multi-page workflows, form filling sequences, tasks requiring multiple browser actions. WHEN NOT: Simple single-action tasks like one click (use browser_click), one navigation (use browser_navigate), one extraction (use browser_extract_text).

0 stars
1.2k downloads
Updated 12/26/2025

Package Files

Loading files...
SKILL.md

browser_agent - Autonomous Web Automation

Core Concept

mcp__plugin_kg_kodegen__browser_agent is an autonomous agent that performs complex multi-step web tasks. It:

  • Plans and executes browser actions autonomously
  • Handles dynamic content and SPAs
  • Supports session management for parallel tasks
  • Runs in background with progress monitoring

Uses session-based execution. Actions: PROMPT, READ, KILL.

Key Parameters

action (required)

  • PROMPT: Start agent with a task
  • READ: Check agent progress
  • KILL: Terminate agent session

task (required for PROMPT)

Natural language description of what to accomplish.

agent (optional, default: 0)

Agent slot number for parallel execution.

start_url (optional)

Initial URL to navigate to before starting task.

max_steps (optional, default: 10)

Maximum iterations the agent will perform.

await_completion_ms (optional, default: 600000)

Timeout in ms. 0 = fire-and-forget.

temperature (optional, default: 0.7)

LLM creativity (0.0-2.0).

max_actions_per_step (optional, default: 3)

Actions per iteration.

additional_info (optional)

Extra context for the agent.

Usage Examples

Start Agent Task

browser_agent({
  "action": "PROMPT",
  "task": "Find the latest Rust release notes and extract key features",
  "start_url": "https://www.rust-lang.org",
  "max_steps": 8
})

Form Filling Workflow

browser_agent({
  "action": "PROMPT",
  "task": "Fill out the contact form with name 'John Doe' and email 'john@example.com', then submit",
  "start_url": "https://example.com/contact",
  "temperature": 0.5,
  "max_actions_per_step": 2
})

Check Progress

browser_agent({
  "action": "READ",
  "agent": 0
})

Fire and Forget

browser_agent({
  "action": "PROMPT",
  "task": "Download the PDF from the resources page",
  "start_url": "https://example.com",
  "await_completion_ms": 0
})
// Returns immediately, agent works in background

Kill Agent

browser_agent({
  "action": "KILL",
  "agent": 0
})

Response Format

{
  "agent": 0,
  "task": "Find latest Rust release notes",
  "steps_taken": 5,
  "completed": true,
  "summary": "Found release notes for Rust 1.75...",
  "history": [
    {"step": 1, "actions": ["navigate"], "summary": "Navigated to rust-lang.org"},
    {"step": 2, "actions": ["click"], "summary": "Clicked releases link"}
  ]
}

When to Use What

ComplexityToolUse Case
Single actionbrowser_click/type/etcClick a button, type text
2-3 actionsManual tool callsLogin form, simple search
4+ actionsbrowser_agentMulti-page workflows
Researchbrowser_researchTopic research with summaries

Configuration Guide

ScenarioSettings
Web researchtemperature: 0.8, max_steps: 12
Form fillingtemperature: 0.5, max_actions_per_step: 2
Complex workflowmax_steps: 15-20
Quick taskmax_steps: 5, await_completion_ms: 60000

Remember

  • Use for complex multi-step tasks only
  • Simple tasks are faster with direct tool calls
  • Agent runs in background (check with READ)
  • Provide clear task descriptions
  • Include start_url when known
  • Kill agent when done to free resources

Install

Download ZIP
Requires askill CLI v1.0+

AI Quality Score

82/100Analyzed 2/22/2026

High-quality technical skill documentation for an autonomous browser agent. Provides comprehensive coverage of all parameters, clear JSON examples for each action type, and useful comparison tables. Includes both WHEN and WHEN NOT to use guidance. The skill is well-structured and actionable, though somewhat specialized to the kodegen plugin context. Tags appear mismatched but content quality is strong."

95
90
75
88
90

Metadata

Licenseunknown
Version0.1.0
Updated12/26/2025
Publishercyrup-ai

Tags

github-actionsllmobservabilityprompting