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

bonsai-automation skill

safe

/bonsai-automation

This skill automates Bonsai tasks via Rube MCP, always discovering current tool schemas before executing workflows to ensure up-to-date automation.

npx playbooks add skill composiohq/awesome-claude-skills --skill bonsai-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: bonsai-automation
description: "Automate Bonsai tasks via Rube MCP (Composio). Always search tools first for current schemas."
requires:
  mcp: [rube]
---

# Bonsai Automation via Rube MCP

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

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

## Prerequisites

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

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["bonsai"]
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 Bonsai-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `bonsai` |
| 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 Bonsai tasks through Composio's Bonsai toolkit using the Rube MCP. It provides a reproducible pattern: discover tools, confirm Bonsai connection, and execute composio tools via RUBE_MULTI_EXECUTE_TOOL. The skill emphasizes dynamic tool discovery and strict schema compliance to avoid runtime errors.

How this skill works

The skill always starts by calling RUBE_SEARCH_TOOLS to fetch current tool slugs, input schemas, recommended execution plans, and pagination tokens. Next it verifies or establishes an active Bonsai connection using RUBE_MANAGE_CONNECTIONS. Finally it runs one or more tools with RUBE_MULTI_EXECUTE_TOOL (including memory and a session ID) or uses RUBE_REMOTE_WORKBENCH for bulk operations.

When to use it

Automating model management, training, or deployment tasks in Bonsai via Composio.
Running multi-step Bonsai workflows that require orchestration across Composio tools.
Building integrations where tool schemas may change frequently and discovery is required.
Performing bulk or batch operations using RUBE_REMOTE_WORKBENCH with run_composio_tool().
When you need reproducible sessions and centralized connection management for Bonsai.

Best practices

Always call RUBE_SEARCH_TOOLS first; never hardcode tool slugs or field names.
Verify Bonsai connection status via RUBE_MANAGE_CONNECTIONS and follow any auth links until status is ACTIVE.
Include an explicit memory object (even {}) in RUBE_MULTI_EXECUTE_TOOL calls.
Reuse session IDs for a single workflow; create new sessions for distinct workflows.
Respect tool schemas exactly: use field names, types, and required fields from the search response.
Handle pagination tokens on search responses and continue fetching until results are complete.

Example use cases

Discovering available Bonsai operations, then launching a training job with schema-compliant arguments.
Checking connection status and completing auth flow before running deployment or inference tools.
Running a sequence of composio tools in one session to provision models, run tests, and deploy.
Executing bulk updates or migrations across multiple Bonsai resources via RUBE_REMOTE_WORKBENCH.
Integrating Bonsai automation into CI/CD pipelines that require dynamic tool lookup.

FAQ

Why must I call RUBE_SEARCH_TOOLS every time?

Tool schemas and available tool slugs can change; a fresh RUBE_SEARCH_TOOLS call ensures you use the current schema and avoid invalid arguments.

What if RUBE_MANAGE_CONNECTIONS shows the toolkit as not ACTIVE?

Follow the provided auth link in the manage connections response to complete authorization, then re-check until the connection status is ACTIVE before executing tools.