refiner-automation
Scannednpx machina-cli add skill ComposioHQ/awesome-claude-skills/refiner-automation --openclawRefiner Automation via Rube MCP
Automate Refiner operations through Composio's Refiner toolkit via Rube MCP.
Toolkit docs: composio.dev/toolkits/refiner
Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Refiner connection via
RUBE_MANAGE_CONNECTIONSwith toolkitrefiner - 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 toolkitrefiner - 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: "Refiner 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 Refiner task"}]
session: {id: "existing_session_id"}
Step 2: Check Connection
RUBE_MANAGE_CONNECTIONS
toolkits: ["refiner"]
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 Refiner-specific use case |
| Connect | RUBE_MANAGE_CONNECTIONS with toolkit refiner |
| 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/refiner-automation/SKILL.mdView on GitHub Overview
Automate Refiner operations through Composio's Refiner toolkit using Rube MCP. This skill emphasizes always searching for current tool schemas first and ensuring an ACTIVE connection before running workflows to keep automation reliable.
How This Skill Works
First discover available tools with RUBE_SEARCH_TOOLS, then verify the connection with RUBE_MANAGE_CONNECTIONS and ensure it is ACTIVE. Finally execute the chosen tool with RUBE_MULTI_EXECUTE_TOOL, providing the required arguments and a memory payload, reusing a session_id when appropriate. Tool schemas come from the search results and should be used as the source of truth; do not hardcode slugs or argument names.
When to Use It
- Automate recurring Refiner workflows without manual steps.
- When tool schemas may have changed, fetch current slugs and schemas first.
- Before running any tool, confirm the connection status is ACTIVE.
- Need to run multiple tools in sequence in a single session.
- Reuse session IDs within a workflow to improve efficiency.
Quick Start
- Step 1: Add https://rube.app/mcp as an MCP server and run RUBE_SEARCH_TOOLS to verify availability and fetch tool slugs and schemas.
- Step 2: Call RUBE_MANAGE_CONNECTIONS with toolkits: [refiner] and ensure the session shows ACTIVE (complete any auth flow if prompted).
- Step 3: Execute a discovered tool with RUBE_MULTI_EXECUTE_TOOL using the provided tool slug, exact input fields from the search results, a memory object, and the session_id.
Best Practices
- Always call RUBE_SEARCH_TOOLS first to fetch current tool slugs and input schemas.
- Verify RUBE_MANAGE_CONNECTIONS reports ACTIVE before executing tools.
- Use exact field names and types from the search results instead of hardcoding.
- Include a memory object in every RUBE_MULTI_EXECUTE_TOOL call, even if empty.
- Reuse session IDs within a workflow and generate new ones only for new workflows.
Example Use Cases
- Daily Refiner health check: discover tools, ensure ACTIVE connection, then run a lightweight health_check tool.
- Batch refinement for a monthly report: fetch schemas, start a session, and execute several tools in sequence.
- Schema change adaptation: when tool schemas update, re run workflow with updated inputs.
- Bulk operations: run multiple tools in one session using RUBE_MULTI_EXECUTE_TOOL and memory.
- Pagination aware discovery: handle large catalogs by paging through RUBE_SEARCH_TOOLS results until complete.
