Why must I search tools first?

Tool schemas change over time. Never hardcode tool slugs or arguments; always call RUBE_SEARCH_TOOLS to obtain current schemas.

What if my connection isn't ACTIVE?

Follow the returned auth link to complete setup and verify that the status shows ACTIVE before running any workflows.

perigon-automation

Scanned

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

Files (1)

SKILL.md

2.9 KB

Perigon Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/perigon

Prerequisites

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

Step 2: Check Connection

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

Overview

Automate Perigon operations through Composio's Perigon toolkit via Rube MCP. The workflow emphasizes discovering current tool schemas with RUBE_SEARCH_TOOLS, establishing an ACTIVE Perigon connection, and executing tools with RUBE_MULTI_EXECUTE_TOOL. This approach makes Perigon workflows repeatable, scalable, and resilient to schema changes.

How This Skill Works

Discover available Perigon tools using RUBE_SEARCH_TOOLS to obtain current input schemas. Next, verify and establish an ACTIVE connection with RUBE_MANAGE_CONNECTIONS for the perigon toolkit. Finally, execute the chosen tool with RUBE_MULTI_EXECUTE_TOOL, including a memory payload and the active session_id, ensuring you reference up-to-date schemas rather than hardcoded values.

When to Use It

Automating recurring Perigon tasks that rely on current tool schemas
Setting up and validating a Perigon connection before running workflows
Orchestrating multi-step Perigon workflows within a single session
Executing multiple Perigon tools in bulk via RUBE_MULTI_EXECUTE_TOOL
Iterating on Perigon capabilities by re-discovering tool schemas instead of hardcoding slugs

Quick Start

Step 1: Discover tools with RUBE_SEARCH_TOOLS for Perigon tasks and review input schemas
Step 2: Manage connection with RUBE_MANAGE_CONNECTIONS for toolkit perigon and ensure ACTIVE
Step 3: Execute a tool with RUBE_MULTI_EXECUTE_TOOL using the discovered slug and a session_id

Best Practices

Always call RUBE_SEARCH_TOOLS first to fetch current tool schemas
Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE before executing tools
Use exact field names and types from the search results
Include memory in every RUBE_MULTI_EXECUTE_TOOL call, even if empty
Reuse session IDs within a workflow; generate new IDs for new workflows

Example Use Cases

Automate a Perigon data extraction task by discovering tools, validating the connection, and executing the selected tool with a prepared session
Set up a fresh Perigon workflow from scratch by querying tools with RUBE_SEARCH_TOOLS and then connecting
Chain several Perigon tools in a single session to complete a complex operation
Perform bulk Perigon operations via RUBE_REMOTE_WORKBENCH using run_composio_tool
Validate tool schemas with RUBE_GET_TOOL_SCHEMAS to ensure compatibility before execution

Frequently Asked Questions

Add this skill to your agents