What is crowdin-automation?

A workflow to automate Crowdin tasks through Rube MCP and Composio's Crowdin toolkit, with dynamic tool discovery to stay in sync with current schemas.

Do I need to search tools first every time?

Yes. RUBE_SEARCH_TOOLS returns the current tool slugs and argument schemas, preventing hardcoded references that may become stale.

How do I ensure the connection remains ACTIVE?

Use RUBE_MANAGE_CONNECTIONS with toolkits: ["crowdin"] and check the status. Proceed only when the connection is ACTIVE.

crowdin-automation

Scanned

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

Files (1)

SKILL.md

2.9 KB

Crowdin Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/crowdin

Prerequisites

Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
Active Crowdin connection via RUBE_MANAGE_CONNECTIONS with toolkit crowdin
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 crowdin
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: "Crowdin 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 Crowdin task"}]
session: {id: "existing_session_id"}

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["crowdin"]
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 Crowdin-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `crowdin`
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/crowdin-automation/SKILL.mdView on GitHub

Overview

Automate Crowdin operations through Composio's Crowdin toolkit using Rube MCP. Always search tools first to obtain current tool schemas, avoiding hardcoded slugs and arguments. This keeps workflows resilient to schema changes and enables scalable localization automation.

How This Skill Works

The automation flow connects Rube MCP to Crowdin via the Crowdin toolkit, then discovers available tools with RUBE_SEARCH_TOOLS and checks the connection with RUBE_MANAGE_CONNECTIONS. You execute a selected tool using RUBE_MULTI_EXECUTE_TOOL, supplying the discovered input fields and a memory object, while reusing session IDs for continuity.

When to Use It

Automate recurring Crowdin workflows (uploads, exports, and status checks) across projects.
Adapt to tool schema changes without hardcoding slugs or arg names.
Coordinate multi-step localization tasks in a single session.
Validate and maintain an ACTIVE Crowdin connection before running workflows.
Batch process multiple files or projects efficiently with discovered tools.

Quick Start

Step 1: Verify MCP connection and confirm that RUBE_SEARCH_TOOLS responds.
Step 2: Discover available Crowdin tools with RUBE_SEARCH_TOOLS (use_case: Crowdin operations) and start a session.
Step 3: Execute a chosen tool with RUBE_MULTI_EXECUTE_TOOL, passing the discovered slug, arguments, memory, and the active session_id.

Best Practices

Always call RUBE_SEARCH_TOOLS first to fetch current tool schemas.
Ensure RUBE_MANAGE_CONNECTIONS shows ACTIVE before execution.
Use exact field names and types from the search results.
Include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty.
Reuse session IDs for related steps and paginate responses as needed.

Example Use Cases

Discover a tool for exporting Crowdin translations and run it for a specific project, then download the result.
Batch-check translation statuses across multiple Crowdin projects and generate a consolidated report.
Upload updated source files to Crowdin by discovering and executing an upload tool with file paths.
Synchronize translations across languages by running a sync tool across several projects.
Maintain a multi-step localization workflow by reusing a session_id across steps and tools.

Frequently Asked Questions

Add this skill to your agents