breeze-automation
Scannednpx machina-cli add skill ComposioHQ/awesome-claude-skills/breeze-automation --openclawBreeze Automation via Rube MCP
Automate Breeze operations through Composio's Breeze toolkit via Rube MCP.
Toolkit docs: composio.dev/toolkits/breeze
Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Breeze connection via
RUBE_MANAGE_CONNECTIONSwith toolkitbreeze - Always call
RUBE_SEARCH_TOOLSfirst 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_TOOLSresponds - Call
RUBE_MANAGE_CONNECTIONSwith toolkitbreeze - 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: "Breeze 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 Breeze task"}]
session: {id: "existing_session_id"}
Step 2: Check Connection
RUBE_MANAGE_CONNECTIONS
toolkits: ["breeze"]
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_CONNECTIONSshows ACTIVE status before executing tools - Schema compliance: Use exact field names and types from the search results
- Memory parameter: Always include
memoryinRUBE_MULTI_EXECUTE_TOOLcalls, 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 Breeze-specific use case |
| Connect | RUBE_MANAGE_CONNECTIONS with toolkit breeze |
| 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/breeze-automation/SKILL.mdView on GitHub Overview
This skill enables automating Breeze operations through Composio's Breeze toolkit using Rube MCP. It emphasizes discovering current tool schemas before execution to avoid hardcoding tool slugs and arguments. This approach supports repeatable Breeze workflows from setup to execution.
How This Skill Works
Technically it starts with RUBE_SEARCH_TOOLS to fetch available Breeze tools and their input schemas, then uses RUBE_MANAGE_CONNECTIONS to ensure an active Breeze connection. Tools are executed via RUBE_MULTI_EXECUTE_TOOL with the discovered tool slug and schema compliant arguments, along with a memory object and a session_id to tie steps together.
When to Use It
- You need to automate recurring Breeze tasks and want up to date tool schemas
- You want to avoid hardcoding tool slugs by always discovering tools first
- You are integrating Breeze workflows into a larger automation pipeline
- You must verify the Breeze connection is ACTIVE before running tools
- You want to debug or adapt Breeze automation when tool schemas change
Quick Start
- Step 1: Add https://rube.app/mcp as an MCP server in your client configuration; no API keys are needed
- Step 2: Verify RUBE_SEARCH_TOOLS responds and then run RUBE_MANAGE_CONNECTIONS with toolkit breeze to establish an ACTIVE Breeze connection
- Step 3: Discover tools with RUBE_SEARCH_TOOLS to get a tool_slug and input schema, then execute with RUBE_MULTI_EXECUTE_TOOL using memory and a session_id
Best Practices
- Always call RUBE_SEARCH_TOOLS before executing any Breeze tool to get current slugs and input schemas
- Check that RUBE_MANAGE_CONNECTIONS reports ACTIVE before running tools
- Use exact field names and types from the search results rather than guessing
- Include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty
- Reuse the same session_id for related steps and handle pagination tokens when discovery returns multiple pages
Example Use Cases
- Discover a Breeze tool slug for a data export and execute it with the required arguments using RUBE_MULTI_EXECUTE_TOOL
- Build a Breeze automation that establishes a connection once and reuses the session_id for subsequent tasks
- When tool schemas update, re search tools to fetch new slugs and adapt the automation
- Chain multiple Breeze tasks in a single workflow using a shared session and discovered tool slugs
- Debug a failed run by verifying the connection status and re fetching tool schemas
