humanloop-automation
Scannednpx machina-cli add skill ComposioHQ/awesome-claude-skills/humanloop-automation --openclawHumanloop Automation via Rube MCP
Automate Humanloop operations through Composio's Humanloop toolkit via Rube MCP.
Toolkit docs: composio.dev/toolkits/humanloop
Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Humanloop connection via
RUBE_MANAGE_CONNECTIONSwith toolkithumanloop - 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 toolkithumanloop - 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: "Humanloop 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 Humanloop task"}]
session: {id: "existing_session_id"}
Step 2: Check Connection
RUBE_MANAGE_CONNECTIONS
toolkits: ["humanloop"]
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 Humanloop-specific use case |
| Connect | RUBE_MANAGE_CONNECTIONS with toolkit humanloop |
| 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/humanloop-automation/SKILL.mdView on GitHub Overview
Automate Humanloop operations through Composio's Humanloop toolkit via Rube MCP. This skill emphasizes discovering current tool schemas first, establishing an ACTIVE Humanloop connection, and executing tools with schema-accurate inputs. Use RUBE_SEARCH_TOOLS, RUBE_MANAGE_CONNECTIONS, and RUBE_MULTI_EXECUTE_TOOL to run tasks reliably.
How This Skill Works
First, call RUBE_SEARCH_TOOLS to fetch available Humanloop tool slugs and their input schemas. Next, establish or verify the Humanloop connection using RUBE_MANAGE_CONNECTIONS and confirm the status is ACTIVE. Finally, run the selected tool with RUBE_MULTI_EXECUTE_TOOL, passing exact schema fields and a memory payload, reusing the session_id for related steps.
When to Use It
- Automating recurring Humanloop tasks with up-to-date tool schemas
- Integrating Humanloop tasks into larger automation workflows with session reuse
- Onboarding or reconnecting a Humanloop toolkit when new tools are added
- Batch processing of multiple Humanloop subtasks in sequence
- Recovery from a disconnected or expired session by re-authenticating and resuming
Quick Start
- Step 1: Get Rube MCP set up by adding https://rube.app/mcp as an MCP server in your client configuration and verify RUBE_SEARCH_TOOLS responds.
- Step 2: Manage the Humanloop connection with RUBE_MANAGE_CONNECTIONS using toolkits: ["humanloop"] and confirm the status is ACTIVE (follow the auth link if not).
- Step 3: Discover tools with RUBE_SEARCH_TOOLS for your use case, then execute a selected tool with RUBE_MULTI_EXECUTE_TOOL, providing memory and a session_id.
Best Practices
- Always search tools first to fetch current tool schemas; tool slugs and arguments can change.
- Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE before executing any tools.
- Use exact field names and types from search results; avoid hardcoding slugs or args.
- Always include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({}).
- Reuse session IDs within a workflow and handle pagination tokens when listing tools.
Example Use Cases
- Weekly data-labeling automation: discover tools, start a session, execute a labeling task, and reuse the session for the next run.
- Onboarding a new Humanloop integration: connect via RUBE_MANAGE_CONNECTIONS, validate with a test tool, then run production tasks.
- Schema-change resilience: monitor for updated tool schemas with RUBE_SEARCH_TOOLS and auto-adjust arguments accordingly.
- Batch task orchestration: run 3-5 Humanloop subtasks in sequence using a single session to maintain context.
- Auto-recovery after disconnect: re-auth via the provided auth link and resume workflow from the last session.
