Do I always need to call RUBE_SEARCH_TOOLS before executing?

Yes — fetch current schemas with RUBE_SEARCH_TOOLS and avoid hardcoding slugs.

How do I verify the browser_tool connection is ACTIVE?

Use RUBE_MANAGE_CONNECTIONS to check status and follow the auth link if not ACTIVE.

Is memory required in each execute?

Yes, memory must be included in RUBE_MULTI_EXECUTE_TOOL calls, even if empty.

browser-tool-automation

Scanned

npx machina-cli add skill ComposioHQ/awesome-claude-skills/browser-tool-automation --openclaw

Files (1)

SKILL.md

2.9 KB

Browser Tool Automation via Rube MCP

Automate Browser Tool operations through Composio's Browser Tool toolkit via Rube MCP.

Toolkit docs: composio.dev/toolkits/browser_tool

Prerequisites

Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
Active Browser Tool connection via RUBE_MANAGE_CONNECTIONS with toolkit browser_tool
Always call RUBE_SEARCH_TOOLS first to get current tool schemas

Setup

Get Rube MCP: Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.

Verify Rube MCP is available by confirming RUBE_SEARCH_TOOLS responds
Call RUBE_MANAGE_CONNECTIONS with toolkit browser_tool
If connection is not ACTIVE, follow the returned auth link to complete setup
Confirm connection status shows ACTIVE before running any workflows

Tool Discovery

Always discover available tools before executing workflows:

RUBE_SEARCH_TOOLS
queries: [{use_case: "Browser Tool operations", known_fields: ""}]
session: {generate_id: true}

This returns available tool slugs, input schemas, recommended execution plans, and known pitfalls.

Core Workflow Pattern

Step 1: Discover Available Tools

RUBE_SEARCH_TOOLS
queries: [{use_case: "your specific Browser Tool task"}]
session: {id: "existing_session_id"}

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["browser_tool"]
session_id: "your_session_id"

Step 3: Execute Tools

RUBE_MULTI_EXECUTE_TOOL
tools: [{
  tool_slug: "TOOL_SLUG_FROM_SEARCH",
  arguments: {/* schema-compliant args from search results */}
}]
memory: {}
session_id: "your_session_id"

Known Pitfalls

Always search first: Tool schemas change. Never hardcode tool slugs or arguments without calling RUBE_SEARCH_TOOLS
Check connection: Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE status before executing tools
Schema compliance: Use exact field names and types from the search results
Memory parameter: Always include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({})
Session reuse: Reuse session IDs within a workflow. Generate new ones for new workflows
Pagination: Check responses for pagination tokens and continue fetching until complete

Quick Reference

Operation	Approach
Find tools	`RUBE_SEARCH_TOOLS` with Browser Tool-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `browser_tool`
Execute	`RUBE_MULTI_EXECUTE_TOOL` with discovered tool slugs
Bulk ops	`RUBE_REMOTE_WORKBENCH` with `run_composio_tool()`
Full schema	`RUBE_GET_TOOL_SCHEMAS` for tools with `schemaRef`

Powered by Composio

Source

git clone https://github.com/ComposioHQ/awesome-claude-skills/blob/master/composio-skills/browser-tool-automation/SKILL.md

View on GitHub

Overview

This skill automates Browser Tool operations via Composio's Rube MCP integration. It relies on always discovering current tool schemas before running workflows and emphasizes a three-step pattern: discover tools, verify an active connection, then execute.

How This Skill Works

Technically, you call RUBE_SEARCH_TOOLS to fetch tool slugs and schemas, then establish a connection with RUBE_MANAGE_CONNECTIONS for the browser_tool toolkit. After that you execute tools with RUBE_MULTI_EXECUTE_TOOL using the discovered slug and proper arguments, always including memory and reusing a session where possible.

When to Use It

When starting a new browser automation workflow that requires up-to-date tool schemas
When you need to discover available browser tool slugs and schemas before scripting
When you must ensure the browser_tool connection is ACTIVE prior to automation
When executing a sequence of browser actions using RUBE_MULTI_EXECUTE_TOOL with memory and a session
When performing multi-step workflows that benefit from session reuse across steps

Quick Start

Step 1: Get Rube MCP up by adding https://rube.app/mcp as an MCP server and confirm RUBE_SEARCH_TOOLS responds
Step 2: Connect to the browser_tool toolkit with RUBE_MANAGE_CONNECTIONS and complete the auth until ACTIVE
Step 3: Discover a tool with RUBE_SEARCH_TOOLS, select TOOL_SLUG_FROM_SEARCH, and run RUBE_MULTI_EXECUTE_TOOL with memory: {} and a session_id

Best Practices

Always call RUBE_SEARCH_TOOLS first to fetch current schemas
Verify ACTIVE status via RUBE_MANAGE_CONNECTIONS before executing tools
Use exact field names and types from search results for arguments
Always include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty
Reuse session IDs within a workflow and create new ones only for new tasks

Example Use Cases

Discover a login tool and run it with username and password to automate sign-in
Fetch the page title or URL using a tool and store the result for later steps
Fill out and submit a form using a discovered tool slug with proper fields
Execute a multi-step checkout flow by reusing a session across steps
Iterate through paginated pages by using a tool that supports pagination until complete

Frequently Asked Questions

Add this skill to your agents