home / skills / composiohq / awesome-claude-skills / plasmic-automation

plasmic-automation skill

safe

/plasmic-automation

This skill automates Plasmic operations via Rube MCP, always discovering current tool schemas to ensure accurate workflow execution.

npx playbooks add skill composiohq/awesome-claude-skills --skill plasmic-automation

Review the files below or copy the command above to add this skill to your agents.

Files (1)

SKILL.md

2.9 KB

---
name: plasmic-automation
description: "Automate Plasmic tasks via Rube MCP (Composio). Always search tools first for current schemas."
requires:
  mcp: [rube]
---

# Plasmic Automation via Rube MCP

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

**Toolkit docs**: [composio.dev/toolkits/plasmic](https://composio.dev/toolkits/plasmic)

## Prerequisites

- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Plasmic connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `plasmic`
- 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.

1. Verify Rube MCP is available by confirming `RUBE_SEARCH_TOOLS` responds
2. Call `RUBE_MANAGE_CONNECTIONS` with toolkit `plasmic`
3. If connection is not ACTIVE, follow the returned auth link to complete setup
4. Confirm connection status shows ACTIVE before running any workflows

## Tool Discovery

Always discover available tools before executing workflows:

```
RUBE_SEARCH_TOOLS
queries: [{use_case: "Plasmic 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 Plasmic task"}]
session: {id: "existing_session_id"}
```

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["plasmic"]
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 Plasmic-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `plasmic` |
| 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](https://composio.dev)*

Overview

This skill automates Plasmic tasks through Composio’s Rube MCP integration, letting agents discover and run Plasmic toolkit operations programmatically. It enforces a discover-first pattern so you always use current tool schemas and connection status before executing workflows. The skill is designed for reliable, repeatable bulk or single-step Plasmic automation.

How this skill works

The agent calls RUBE_SEARCH_TOOLS first to fetch current tool slugs, input schemas, and execution guidance for Plasmic tasks. It then verifies an active Plasmic connection via RUBE_MANAGE_CONNECTIONS and runs operations using RUBE_MULTI_EXECUTE_TOOL (or RUBE_REMOTE_WORKBENCH for bulk flows), always supplying schema-compliant arguments, a session_id, and a memory object.

When to use it

Automate content or component deployments in Plasmic
Run batch updates or migrations across Plasmic projects
Integrate Plasmic operations into larger CI/CD or agent-driven workflows
Perform repeatable administrative tasks like syncing or publishing assets
When tool schemas may change and you need dynamic discovery before execution

Best practices

Always call RUBE_SEARCH_TOOLS first — do not hardcode tool slugs or argument shapes
Check RUBE_MANAGE_CONNECTIONS for an ACTIVE Plasmic connection before running tools
Reuse session_id within a workflow; generate new IDs for new workflows
Include memory (even empty {}) in RUBE_MULTI_EXECUTE_TOOL calls
Respect exact field names and types returned in tool schemas and handle pagination tokens

Example use cases

Discover and publish a set of Plasmic pages programmatically using discovered tool slugs and arguments
Bulk-update component properties across projects via RUBE_REMOTE_WORKBENCH and composio run_composio_tool() calls
Automate authentication and verify ACTIVE connection status before scheduled Plasmic sync jobs
Integrate Plasmic publish steps into an AI-driven deployment pipeline that first validates schemas with RUBE_SEARCH_TOOLS
Migrate assets by fetching schemas, paginating through items, and invoking multi-execute calls with appropriate memory

FAQ

What should I call first when using this skill?

Always call RUBE_SEARCH_TOOLS first to fetch current tool slugs and schemas before any other operation.

Do I need API keys to use Rube MCP?

No API keys are required when adding https://rube.app/mcp as an MCP server; you just configure the endpoint in your client.