Do I always need to call RUBE_SEARCH_TOOLS before executing?

Yes — to obtain current tool slugs and input schemas; tool schemas can change.

What must I include in RUBE_MULTI_EXECUTE_TOOL?

Memory parameter (even if empty {}) and the correct session_id.

How should I manage sessions?

Reuse in a workflow; generate a new session_id for new workflows; ensure the session_id persists while the workflow runs.

browseai-automation

Scanned

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

Files (1)

SKILL.md

2.9 KB

Browseai Automation via Rube MCP

Automate Browseai operations through Composio's Browseai toolkit via Rube MCP.

Toolkit docs: composio.dev/toolkits/browseai

Prerequisites

Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
Active Browseai connection via RUBE_MANAGE_CONNECTIONS with toolkit browseai
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 browseai
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: "Browseai 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 Browseai task"}]
session: {id: "existing_session_id"}

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["browseai"]
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 Browseai-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `browseai`
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/browseai-automation/SKILL.mdView on GitHub

Overview

Automate Browseai operations through Composio's Browseai toolkit via Rube MCP. Always search tools first to get current schemas, then orchestrate discovery, connection validation, and execution.

How This Skill Works

Core flow: use RUBE_SEARCH_TOOLS to discover available Browseai tools and their input schemas, then verify the Browseai connection with RUBE_MANAGE_CONNECTIONS and ensure ACTIVE. Finally, execute a chosen tool with RUBE_MULTI_EXECUTE_TOOL, providing memory and the session_id, using the discovered tool_slug and schema fields.

When to Use It

Discover available Browseai tools before running any workflow.
Set up or verify an ACTIVE Browseai connection via RUBE_MANAGE_CONNECTIONS.
Always fetch current tool schemas with RUBE_SEARCH_TOOLS before execution.
Execute a tool using RUBE_MULTI_EXECUTE_TOOL with memory and a session_id.
Perform bulk or batch operations using RUBE_REMOTE_WORKBENCH for multiple tools.

Quick Start

Step 1: Ensure RUBE MCP is connected by adding https://rube.app/mcp and verify RUBE_SEARCH_TOOLS.
Step 2: Manage the Browseai connection with RUBE_MANAGE_CONNECTIONS and confirm ACTIVE.
Step 3: Discover tools with RUBE_SEARCH_TOOLS, then execute a discovered tool using RUBE_MULTI_EXECUTE_TOOL with memory and a session_id.

Best Practices

Always call RUBE_SEARCH_TOOLS first to fetch current tool schemas.
Check that RUBE_MANAGE_CONNECTIONS shows ACTIVE before executing tools.
Use exact field names and types from the search results; don't hardcode slugs.
Include memory: {} in RUBE_MULTI_EXECUTE_TOOL calls.
Reuse session IDs within a workflow; generate a new session_id for new workflows and monitor pagination.

Example Use Cases

Discover tools with use_case: 'Browseai operations', retrieve tool_slugs and input schemas, then execute a discovered slug with proper arguments.
Establish a Browseai connection via RUBE_MANAGE_CONNECTIONS and confirm the status is ACTIVE before running any tool.
Reuse a single session_id across multiple Browseai tool executions within one automation workflow.
Handle pagination when listing tools by continuing RUBE_SEARCH_TOOLS calls until no tokens remain.
Run multiple tools in a batch using RUBE_REMOTE_WORKBENCH and run_composio_tool() for bulk operations.

Frequently Asked Questions

Add this skill to your agents