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

adobe-automation skill

safe

/adobe-automation

This skill automates Adobe tasks via Rube MCP, discovering current tool schemas before execution to ensure accurate, up-to-date workflows.

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

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

Files (1)

SKILL.md

2.8 KB

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

# Adobe Automation via Rube MCP

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

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

## Prerequisites

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

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["adobe"]
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 Adobe-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `adobe` |
| 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 Adobe tasks by orchestrating Composio's Adobe toolkit through the Rube MCP. It provides a repeatable workflow pattern for discovering tools, validating connections, and executing operations safely. The skill emphasizes always querying Rube for current tool schemas and using session-aware executions to avoid runtime errors.

How this skill works

First, call RUBE_SEARCH_TOOLS to discover available Adobe tool slugs, input schemas, recommended plans, and pagination tokens. Then verify or create an active Adobe connection via RUBE_MANAGE_CONNECTIONS. Finally, run operations using RUBE_MULTI_EXECUTE_TOOL (or RUBE_REMOTE_WORKBENCH for bulk tasks), supplying schema-compliant arguments, a session_id, and a memory object.

When to use it

Automating repetitive Adobe tasks like asset uploads, metadata updates, or project orchestration.
Building multi-step workflows that must adapt to changing tool schemas or capabilities.
Running bulk operations where tools returned by Composio provide batch primitives.
Integrating Adobe actions into broader agent-driven pipelines that require session state.
Validating tool availability and schemas before executing critical production changes.

Best practices

Always call RUBE_SEARCH_TOOLS first; never hardcode tool slugs or input fields.
Use RUBE_MANAGE_CONNECTIONS to confirm the Adobe connection is ACTIVE before execution.
Include a memory object (even {}) in RUBE_MULTI_EXECUTE_TOOL calls and reuse session_id across the workflow.
Respect exact schema field names and types returned by the search results; use RUBE_GET_TOOL_SCHEMAS for full definitions.
Handle pagination tokens from search responses and iterate until you have complete results.

Example use cases

Discover and run the current Adobe asset upload tool with schema-driven arguments to push a batch of images.
Check connection status, then update metadata across multiple Adobe assets using a multi-execute tool call.
Run a bulk export workflow via RUBE_REMOTE_WORKBENCH to render and export project files in parallel.
Automate connector onboarding: use RUBE_MANAGE_CONNECTIONS to guide a user through the auth link and confirm ACTIVE status.
Fetch the latest tool schema with RUBE_GET_TOOL_SCHEMAS before transforming inputs for a downstream automation.

FAQ

What is the first API call I should make in a workflow?

Always start with RUBE_SEARCH_TOOLS to fetch current tool slugs and input schemas for your use case.

What if the Adobe connection is not ACTIVE?

Call RUBE_MANAGE_CONNECTIONS for the adobe toolkit, follow the returned auth link to complete setup, then confirm ACTIVE before proceeding.