skyfire-automation
Scannednpx machina-cli add skill ComposioHQ/awesome-claude-skills/skyfire-automation --openclawFiles (1)
SKILL.md
2.9 KB
Skyfire Automation via Rube MCP
Automate Skyfire operations through Composio's Skyfire toolkit via Rube MCP.
Toolkit docs: composio.dev/toolkits/skyfire
Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Skyfire connection via
RUBE_MANAGE_CONNECTIONSwith toolkitskyfire - 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 toolkitskyfire - 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: "Skyfire 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 Skyfire task"}]
session: {id: "existing_session_id"}
Step 2: Check Connection
RUBE_MANAGE_CONNECTIONS
toolkits: ["skyfire"]
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 Skyfire-specific use case |
| Connect | RUBE_MANAGE_CONNECTIONS with toolkit skyfire |
| 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/skyfire-automation/SKILL.mdView on GitHub Overview
Skyfire Automation via Rube MCP enables automated Skyfire operations using Composio's Skyfire toolkit. By always discovering tool schemas first with RUBE_SEARCH_TOOLS, workflows stay up-to-date and resilient to schema changes.
How This Skill Works
The skill verifies MCP connectivity by calling RUBE_SEARCH_TOOLS, then establishes or verifies a Skyfire connection with RUBE_MANAGE_CONNECTIONS for the skyfire toolkit. It then discovers available tools, selects a tool slug from the results, and executes it with RUBE_MULTI_EXECUTE_TOOL, including a memory payload and reusing session IDs for consistency.
When to Use It
- You need to automate Skyfire operations without hardcoding tool slugs or arguments, ensuring the latest schemas are used.
- You must establish and verify an active Skyfire connection before running any workflows.
- You want to dynamically discover tool schemas before executing workflows to adapt to changes.
- You are coordinating multi-step Skyfire workflows that benefit from session reuse and shared state.
- You are handling large tool sets and need to paginate through available tools to select the right one.
Quick Start
- Step 1: Configure the MCP endpoint https://rube.app/mcp and verify it via RUBE_SEARCH_TOOLS.
- Step 2: Call RUBE_MANAGE_CONNECTIONS with toolkits: ["skyfire"] to establish the Skyfire connection.
- Step 3: Ensure the connection status is ACTIVE before running any Skyfire workflows.
Best Practices
- Always call RUBE_SEARCH_TOOLS first to fetch current Skyfire tool schemas.
- Verify the Skyfire connection is ACTIVE via RUBE_MANAGE_CONNECTIONS before executing tools.
- Use exact field names and types from the search results; avoid hardcoded slugs or arguments.
- Include memory in every RUBE_MULTI_EXECUTE_TOOL call, even if empty.
- Reuse session IDs within a workflow and generate new ones only for separate workflows.
Example Use Cases
- Automate a Skyfire data extraction by discovering the appropriate tool slug with RUBE_SEARCH_TOOLS and executing it in a session.
- Set up a Skyfire connection, then run a sequence of tools in a single session for a coordinated task.
- Update an ongoing Skyfire workflow when tool schemas change by re-fetching with RUBE_SEARCH_TOOLS before execution.
- Batch multiple Skyfire tasks in one run using RUBE_MULTI_EXECUTE_TOOL with a shared memory and session.
- Fetch all available Skyfire tools with RUBE_SEARCH_TOOLS (handling pagination) and choose the best fit.
Frequently Asked Questions
Add this skill to your agents
