Do I need to connect Strava first?

Yes; ensure RUBE_MANAGE_CONNECTIONS reports ACTIVE before running workflows.

Can tool slugs be hardcoded?

No; always search first; tool schemas can change and slugs may be updated.

What about memory in execute?

Memory must be included in RUBE_MULTI_EXECUTE_TOOL calls, even if empty.

strava-automation

Scanned

npx machina-cli add skill ComposioHQ/awesome-claude-skills/strava-automation --openclaw

Files (1)

SKILL.md

2.8 KB

Strava Automation via Rube MCP

Automate Strava operations through Composio's Strava toolkit via Rube MCP.

Toolkit docs: composio.dev/toolkits/strava

Prerequisites

Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
Active Strava connection via RUBE_MANAGE_CONNECTIONS with toolkit strava
Always call RUBE_SEARCH_TOOLS first 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_TOOLS responds
Call RUBE_MANAGE_CONNECTIONS with toolkit strava
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: "Strava 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 Strava task"}]
session: {id: "existing_session_id"}

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["strava"]
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_CONNECTIONS shows ACTIVE status before executing tools
Schema compliance: Use exact field names and types from the search results
Memory parameter: Always include memory in RUBE_MULTI_EXECUTE_TOOL calls, 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 Strava-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `strava`
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/strava-automation/SKILL.mdView on GitHub

Overview

Automate Strava operations through Composio's Strava toolkit using Rube MCP. The skill centers on discovering current tool schemas with RUBE_SEARCH_TOOLS and managing Strava connections with RUBE_MANAGE_CONNECTIONS to execute workflows reliably.

How This Skill Works

First discover available tools with RUBE_SEARCH_TOOLS to get up-to-date input schemas. Then verify the Strava connection is ACTIVE with RUBE_MANAGE_CONNECTIONS, and finally execute the chosen tool using RUBE_MULTI_EXECUTE_TOOL, including a memory payload and the session_id. Tool schemas change, so never hardcode slugs or arguments.

When to Use It

When you need to automate a Strava operation but want the latest tool schemas from the ecosystem
When establishing a Strava connection in a workflow and ensuring it's ACTIVE before actions
When you have a discovered tool slug and want to execute it with proper arguments
When chaining multiple Strava steps in a single session and reusing session IDs
When performing bulk or advanced tasks via RUBE_REMOTE_WORKBENCH or paginated results and needing memory and schemas

Quick Start

Step 1: RUBE_SEARCH_TOOLS with use_case: "Strava operations"
Step 2: RUBE_MANAGE_CONNECTIONS for toolkit "strava"
Step 3: RUBE_MULTI_EXECUTE_TOOL with tool_slug from search results and memory: {}

Best Practices

Always call RUBE_SEARCH_TOOLS before any workflow to get current tool schemas
Verify ACTIVE status with RUBE_MANAGE_CONNECTIONS before executing tools
Use exact field names and types from the search results; do not guess
Include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({})
Reuse session IDs within a workflow; create new sessions for new flows

Example Use Cases

Discover Strava tools with RUBE_SEARCH_TOOLS, connect using RUBE_MANAGE_CONNECTIONS, then run a discovered tool slug to fetch recent activities
After discovering a tool, verify ACTIVE status and execute with the required arguments and memory
Chain: fetch activities (session X) then update an activity using the same session to avoid duplication
Handle pagination by inspecting tokens in tool responses and continuing fetches until complete
Use RUBE_REMOTE_WORKBENCH to run multiple composio tools in bulk with run_composio_tool

Frequently Asked Questions

Add this skill to your agents