zeplin-automation
Scannednpx machina-cli add skill ComposioHQ/awesome-claude-skills/zeplin-automation --openclawZeplin Automation via Rube MCP
Automate Zeplin operations through Composio's Zeplin toolkit via Rube MCP.
Toolkit docs: composio.dev/toolkits/zeplin
Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Zeplin connection via
RUBE_MANAGE_CONNECTIONSwith toolkitzeplin - 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 toolkitzeplin - 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: "Zeplin 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 Zeplin task"}]
session: {id: "existing_session_id"}
Step 2: Check Connection
RUBE_MANAGE_CONNECTIONS
toolkits: ["zeplin"]
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 Zeplin-specific use case |
| Connect | RUBE_MANAGE_CONNECTIONS with toolkit zeplin |
| 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/zeplin-automation/SKILL.mdView on GitHub Overview
Zeplin Automation via Rube MCP enables programmatic Zeplin operations using Composio's Zeplin toolkit. It relies on live tool schemas retrieved by RUBE_SEARCH_TOOLS and requires an active Zeplin connection. Always query current tools before running workflows to avoid broken payloads.
How This Skill Works
First, discover available Zeplin tool slugs and schemas with RUBE_SEARCH_TOOLS. Then verify an ACTIVE Zeplin connection with RUBE_MANAGE_CONNECTIONS and run tools via RUBE_MULTI_EXECUTE_TOOL within a session. Include the memory field in calls and reuse session IDs for cohesive workflows.
When to Use It
- When you need to perform a Zeplin operation (export, sync, or manage components) via an automated workflow.
- Before any execution, you must discover current tool schemas to avoid outdated slugs.
- When a Zeplin tool requires an ACTIVE connection established via RUBE_MANAGE_CONNECTIONS.
- When running multiple Zeplin actions in a single session using RUBE_MULTI_EXECUTE_TOOL.
- When performing bulk or batch Zeplin tasks with RUBE_REMOTE_WORKBENCH or handling paginated tool listings.
Quick Start
- Step 1: Add the Rube MCP endpoint (https://rube.app/mcp) as your MCP server and verify RUBE_SEARCH_TOOLS.
- Step 2: Run RUBE_SEARCH_TOOLS for Zeplin to fetch current tool slugs and schemas.
- Step 3: Manage connections with RUBE_MANAGE_CONNECTIONS (zeplin) and execute tools via RUBE_MULTI_EXECUTE_TOOL in a session.
Best Practices
- Always run RUBE_SEARCH_TOOLS first to fetch current schemas.
- Check that RUBE_MANAGE_CONNECTIONS reports ACTIVE before executing tools.
- Use exact field names/types from the tool schemas returned by search results.
- Always include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty.
- Reuse session IDs within a workflow and avoid hardcoding tool slugs.
Example Use Cases
- Discover Zeplin tasks and run a tool to export a component to a spec sheet.
- Establish a Zeplin connection, then execute a sequence of edits across screens in one session.
- Batch export assets from Zeplin using RUBE_REMOTE_WORKBENCH run_composio_tool.
- Handle pagination when listing available tools to process large Zeplin projects.
- Update a workflow by re-discovering tool schemas before each run to adapt to changes.
