playbooks

home / skills / composiohq / awesome-claude-skills / agenty-automation

agenty-automation skill

/agenty-automation

This skill automates Agenty tasks via Rube MCP, discovering current tool schemas first to ensure accurate Composio workflows.

npx playbooks add skill composiohq/awesome-claude-skills --skill agenty-automation

Review the files below or copy the command above to add this skill to your agents.

Files (1)
SKILL.md
2.8 KB
---
name: agenty-automation
description: "Automate Agenty tasks via Rube MCP (Composio). Always search tools first for current schemas."
requires:
  mcp: [rube]
---

# Agenty Automation via Rube MCP

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

**Toolkit docs**: [composio.dev/toolkits/agenty](https://composio.dev/toolkits/agenty)

## Prerequisites

- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Agenty connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `agenty`
- 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.

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

## Tool Discovery

Always discover available tools before executing workflows:

```
RUBE_SEARCH_TOOLS
queries: [{use_case: "Agenty 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 Agenty task"}]
session: {id: "existing_session_id"}
```

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["agenty"]
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 Agenty-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `agenty` |
| 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](https://composio.dev)*

Overview

This skill automates Agenty tasks through Composio's Agenty toolkit using the Rube MCP orchestration layer. It standardizes discovery, connection management, and tool execution so you can run Agenty workflows reliably from a Python-based agent environment.

How this skill works

The skill first calls RUBE_SEARCH_TOOLS to retrieve current tool slugs and input schemas. It then verifies or establishes an Agenty connection via RUBE_MANAGE_CONNECTIONS and runs actions with RUBE_MULTI_EXECUTE_TOOL (including memory and session handling). Always query schemas first and reuse session IDs for the duration of a workflow.

When to use it

  • Automating web scraping or data extraction jobs managed by Agenty.
  • Orchestrating multi-step Agenty workflows from an AI agent or script.
  • Running bulk operations or scheduled Agenty tasks programmatically.
  • Integrating Agenty toolsets into larger Composio/Rube MCP pipelines.
  • When you need reliable schema-driven execution and connection checks before run.

Best practices

  • Always call RUBE_SEARCH_TOOLS before executing any tool to get current schemas.
  • Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE for the agenty toolkit before running tools.
  • Include a memory object in RUBE_MULTI_EXECUTE_TOOL calls, even if empty.
  • Reuse a session_id for related steps; generate new sessions for new workflows.
  • Respect exact field names and types returned by the tool search results.

Example use cases

  • Discover Agenty job templates, validate parameters, and launch a scrape run in a single workflow.
  • Perform bulk data extraction across multiple targets using RUBE_REMOTE_WORKBENCH and run_composio_tool().
  • Automate connection setup and refresh if an Agenty token requires reauthorization during pipeline execution.
  • Fetch full tool schemas with RUBE_GET_TOOL_SCHEMAS to build UI forms or automated validators.

FAQ

Do I need API keys to use Rube MCP with this skill?

No API keys are required to add the Rube MCP endpoint; simply configure https://rube.app/mcp as your MCP server.

What happens if I skip RUBE_SEARCH_TOOLS?

Tool schemas and slugs change; skipping search risks schema mismatches and failed executions.