felt-automation
Scannednpx machina-cli add skill ComposioHQ/awesome-claude-skills/felt-automation --openclawFelt Automation via Rube MCP
Automate Felt operations through Composio's Felt toolkit via Rube MCP.
Toolkit docs: composio.dev/toolkits/felt
Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Felt connection via
RUBE_MANAGE_CONNECTIONSwith toolkitfelt - 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 toolkitfelt - 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: "Felt 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 Felt task"}]
session: {id: "existing_session_id"}
Step 2: Check Connection
RUBE_MANAGE_CONNECTIONS
toolkits: ["felt"]
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 Felt-specific use case |
| Connect | RUBE_MANAGE_CONNECTIONS with toolkit felt |
| 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/felt-automation/SKILL.mdView on GitHub Overview
Automate Felt operations through Composio's Felt toolkit via Rube MCP. This skill guides you to discover current tool schemas first, ensure an ACTIVE Felt connection, and execute workflows using up-to-date slugs.
How This Skill Works
Discover tools with RUBE_SEARCH_TOOLS to fetch available Felt operations and their input schemas. Then verify the connection with RUBE_MANAGE_CONNECTIONS and execute the chosen tool via RUBE_MULTI_EXECUTE_TOOL, including the memory payload and the session. Always reference the discovered tool slug from the search results rather than hardcoding.
When to Use It
- When starting a Felt automation, first search for current tool schemas before any execution.
- When setting up or validating a Felt connection, verify ACTIVE status with RUBE_MANAGE_CONNECTIONS.
- When you need to run a discovered Felt tool, use the slug and its required arguments from the search results.
- When handling tool lists at scale, perform repeated RUBE_SEARCH_TOOLS queries to keep schemas up to date and manage pagination.
- When integrating Felt workflows into larger Composio automation, reuse session IDs and avoid hardcoding tool details.
Quick Start
- Step 1: Add https://rube.app/mcp as an MCP server in your client configuration.
- Step 2: Run RUBE_SEARCH_TOOLS with a Felt use_case to discover available tools.
- Step 3: Use RUBE_MANAGE_CONNECTIONS to ensure the Felt toolkit is ACTIVE, then run RUBE_MULTI_EXECUTE_TOOL with the discovered tool slug and a memory payload.
Best Practices
- Always call RUBE_SEARCH_TOOLS before workflows.
- Check that RUBE_MANAGE_CONNECTIONS shows ACTIVE before executing tools.
- Use exact field names and types from search results.
- Include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty.
- Reuse session IDs within a workflow and generate new ones for new runs.
Example Use Cases
- Discover a Felt operation with RUBE_SEARCH_TOOLS and execute its slug with the required arguments via RUBE_MULTI_EXECUTE_TOOL.
- Set up Rube MCP at the provided endpoint and confirm RUBE_SEARCH_TOOLS returns tools.
- Check the connection status with RUBE_MANAGE_CONNECTIONS before running a tool.
- Run a sequence of tools using the session flow to reuse IDs.
- Perform bulk operations with RUBE_REMOTE_WORKBENCH and run_composio_tool() when needed.