Skip to main content
ClaudeWave
Skill470 estrellas del repoactualizado 3d ago

ai-ml-api-automation

This Claude Code skill automates AI and machine learning API operations through Composio's AI ML API toolkit via Rube MCP, enabling users to discover and execute available tools for tasks like model inference and API integrations. Use this skill when you need to programmatically interact with multiple AI ML APIs without manually managing individual API credentials or schemas.

Instalar en Claude Code
Copiar
git clone --depth 1 https://github.com/openteams-lab/openteams /tmp/ai-ml-api-automation && cp -r /tmp/ai-ml-api-automation/assets/skills/ai-ml-api-automation ~/.claude/skills/ai-ml-api-automation
Después abre una sesión nueva de Claude Code; el skill carga automáticamente.

SKILL.md

# AI ML API Automation via Rube MCP

Automate AI ML API operations through Composio's AI ML API toolkit via Rube MCP.

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

## Prerequisites

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

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["ai_ml_api"]
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 AI ML API-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `ai_ml_api` |
| 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)*