home / skills / composiohq / awesome-claude-skills / bigpicture-io-automation

bigpicture-io-automation skill

safe

/bigpicture-io-automation

This skill automates Bigpicture IO tasks via Rube MCP, ensuring tool discovery first and validated connections for reliable workflows.

npx playbooks add skill composiohq/awesome-claude-skills --skill bigpicture-io-automation

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

Files (1)

SKILL.md

2.9 KB

---
name: bigpicture-io-automation
description: "Automate Bigpicture IO tasks via Rube MCP (Composio). Always search tools first for current schemas."
requires:
  mcp: [rube]
---

# Bigpicture IO Automation via Rube MCP

Automate Bigpicture IO operations through Composio's Bigpicture IO toolkit via Rube MCP.

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

## Prerequisites

- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Bigpicture IO connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `bigpicture_io`
- 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 `bigpicture_io`
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: "Bigpicture IO 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 Bigpicture IO task"}]
session: {id: "existing_session_id"}
```

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["bigpicture_io"]
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 Bigpicture IO-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `bigpicture_io` |
| 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 Bigpicture IO tasks by driving Composio’s Bigpicture IO toolkit through a Rube MCP connection. It guides discovery of available tools, validates connections, and executes toolkit operations using RUBE_* actions while enforcing schema compliance. It emphasizes always searching for current tool schemas before running workflows.

How this skill works

The skill orchestrates a three-step pattern: call RUBE_SEARCH_TOOLS to discover current tool slugs and input schemas, verify the Bigpicture IO connection via RUBE_MANAGE_CONNECTIONS, and run operations with RUBE_MULTI_EXECUTE_TOOL or RUBE_REMOTE_WORKBENCH. Every execute call includes memory and a session_id; session reuse is encouraged within a workflow and new sessions are generated for separate workflows.

When to use it

Automate project or visualization tasks in Bigpicture IO programmatically
Run batch or bulk operations that require discovered tool schemas
Integrate Bigpicture IO actions into larger agent workflows or pipelines
Ensure safe execution when tool schemas may change frequently
Perform remote workbench operations for complex multi-step jobs

Best practices

Always call RUBE_SEARCH_TOOLS first to fetch current tool slugs and full input schemas
Confirm RUBE_MANAGE_CONNECTIONS shows ACTIVE for toolkit bigpicture_io before executing tools
Provide schema-compliant arguments exactly as returned by the search results
Include a memory object (even {}) in RUBE_MULTI_EXECUTE_TOOL calls
Reuse session_id across related steps; generate a new session_id for distinct workflows
Handle pagination tokens in responses and iterate until results are complete

Example use cases

Discover available Bigpicture IO actions and run a create or update operation using RUBE_MULTI_EXECUTE_TOOL
Batch-update visualizations via RUBE_REMOTE_WORKBENCH with run_composio_tool() for bulk operations
Embed Bigpicture IO steps inside an automated deployment pipeline that first verifies connection status
Fetch full tool schemas with RUBE_GET_TOOL_SCHEMAS when building UI bindings or strict validators
Run multi-step workflows using discovered tool slugs and session reuse to maintain context

FAQ

What must I do before executing any tool?

Always call RUBE_SEARCH_TOOLS to get current tool slugs and input schemas, then verify the Bigpicture IO connection is ACTIVE with RUBE_MANAGE_CONNECTIONS.

Do I need API keys to connect to Rube MCP?

No API keys are required; add the MCP endpoint (https://rube.app/mcp) to your client configuration and follow the connection flow returned by RUBE_MANAGE_CONNECTIONS.

What happens if tool schemas change?

Schemas can change often; avoid hardcoding slugs or argument shapes. Always search for the current schema and use exact field names and types from the search response.