home / skills / composiohq / awesome-claude-skills / claid-ai-automation

claid-ai-automation skill

safe

This skill automates Claid AI tasks via Rube MCP, prioritizing tool discovery and current schemas to streamline workflows.

npx playbooks add skill composiohq/awesome-claude-skills --skill claid-ai-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: claid-ai-automation
description: "Automate Claid AI tasks via Rube MCP (Composio). Always search tools first for current schemas."
requires:
  mcp: [rube]
---

# Claid AI Automation via Rube MCP

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

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

## Prerequisites

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

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["claid_ai"]
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 Claid AI-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `claid_ai` |
| 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 Claid AI tasks using Composio's Claid AI toolkit through a Rube MCP connection. It orchestrates tool discovery, connection checks, and multi-tool execution to run reliable Claid workflows. Always query the MCP for current tool schemas before taking action.

How this skill works

The agent first calls RUBE_SEARCH_TOOLS to retrieve available tool slugs, input schemas, and recommended execution plans. It then verifies an active Claid AI connection via RUBE_MANAGE_CONNECTIONS. Workflows run by sending schema-compliant requests to RUBE_MULTI_EXECUTE_TOOL (including a memory parameter) or by using RUBE_REMOTE_WORKBENCH for bulk operations. Session IDs are reused within a workflow and pagination tokens are handled when fetching results.

When to use it

Running any Claid AI operation that requires up-to-date tool schemas
Orchestrating multi-step Claid workflows across discovered tools
Automating bulk or scheduled Claid tasks via the remote workbench
Integrating Claid AI operations into larger agent-led pipelines
Validating and executing schema-driven calls against Claid tooling

Best practices

Always call RUBE_SEARCH_TOOLS at the start to fetch current tool schemas and slugs
Verify toolkit connection state with RUBE_MANAGE_CONNECTIONS and follow any auth links until status is ACTIVE
Use exact field names and types from the search results; never hardcode argument shapes
Include a memory object in every RUBE_MULTI_EXECUTE_TOOL call, even if empty ({}). Reuse session IDs within a single workflow
Handle pagination by checking for continuation tokens and fetching until complete
Generate a new session ID for distinct workflows to avoid cross-run state bugs

Example use cases

Discover and run a Claid model tool to analyze documents using the discovered schema
Automate batch inference by invoking RUBE_REMOTE_WORKBENCH with run_composio_tool() for many inputs
Set up a scheduled workflow that re-checks tool schemas then executes approved operations
Build an agent that validates connection state and transparently prompts for auth if Claid toolkit is not ACTIVE
Fetch full tool schemas via RUBE_GET_TOOL_SCHEMAS before building a custom UI or input form

FAQ

Do I need API keys to use Rube MCP?

No API keys are required; add https://rube.app/mcp as an MCP server in your client configuration to connect.

What must I do if a connection is not ACTIVE?

Call RUBE_MANAGE_CONNECTIONS for the claid_ai toolkit, follow any returned auth link to complete setup, then confirm the status changes to ACTIVE before executing tools.