$ ~/registry/skill/composiohq-composio-skills-claid-ai-automation

SKILL

claid-ai-automation

Name: claid-ai-automation
Author: Composio

Automate Claid AI image enhancement workflows through Rube MCP tools.

Stars

★ 67,763

Source

GitHub

Updated

2026-07-15

// securityCaution

Prompt only, no code
Open source
Community-trusted· 64.7k

Summary

This skill appears to be primarily prompt/documentation-like, with an open-source source and strong community adoption; the materials do not show it directly requiring local high privileges, secrets, or fixed outbound endpoints. Caution is still warranted because it explicitly depends on Rube MCP and an external Claid AI connection, shifting actual data egress, authentication, and execution boundaries to those external tools.

CredentialsCaution

The material says 'No API keys needed,' but it also requires establishing an ACTIVE `claid_ai` connection via `RUBE_MANAGE_CONNECTIONS` and following an auth link, indicating credentials are likely delegated to an external connection flow rather than absent. The skill itself does not declare collecting secrets, but real authorization and token handling occur on the Rube/Claid AI side and should be reviewed for scope and storage.

Network egressCaution

The README explicitly requires adding the remote MCP endpoint `https://rube.app/mcp` and performing operations through Composio/Claid AI tooling, so user inputs and workflow arguments may be sent to those declared external services. The material does not provide detailed data minimization or flow details, but there is no concrete red flag showing exfiltration to unknown or unrelated endpoints.

Code executionLow risk

The system flags it as `prompt-only`, and the provided content is mainly usage guidance and invocation patterns; it does not show the skill itself spawning local processes, running scripts, or requesting system-level execution privileges. Any execution capability mentioned belongs to external MCP tool semantics rather than local executable logic contained in this skill.

Data accessLow risk

The material does not state that this skill itself can directly read or write local files, databases, or other sensitive resources; its main role is to instruct users to discover tool schemas before invoking external tools. Data access scope therefore depends on the downstream Rube/Claid AI tools, not on this prompt-only skill itself.

Supply chainLow risk

The source is an open GitHub repository with very high community adoption (64.7k stars), both of which materially lower supply-chain risk; the present material is auditable and does not include obfuscated install scripts. Still, the license is unspecified, maintenance status is unknown, and actual operation depends on external services such as `rube.app` and Composio/Claid AI, so the supply-chain boundary extends beyond this repository.

Recommendations

Before connecting to `https://rube.app/mcp`, review the privacy policy, data retention, and token-handling practices of Rube MCP, Composio, and Claid AI.
When completing `RUBE_MANAGE_CONNECTIONS` authorization, use least-privilege accounts and regularly review/revoke connections that are no longer needed.
Do not provide unnecessary sensitive data to this workflow; verify the exact tool schema and field meanings before sending business content.
Prefer pinned and reviewed external tool versions/docs to reduce mistakes caused by schema changes.

Audited by: gpt-5.4 · 2026-06-17

// install

Copy the install command and let the AI configure it · recommended for beginners

Please install the "claid-ai-automation" skill from askskill:
1. Download https://raw.githubusercontent.com/ComposioHQ/awesome-claude-skills/master/composio-skills/claid-ai-automation/SKILL.md
2. Save it as ~/.claude/skills/claid-ai-automation/SKILL.md
3. Reload skills and tell me it's ready

// download

Download SKILL.mdInstall manifest ↗

// docs

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

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.

Verify Rube MCP is available by confirming RUBE_SEARCH_TOOLS responds
Call RUBE_MANAGE_CONNECTIONS with toolkit claid_ai
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: "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

Automate Alttext AI workflows through Rube MCP for image alt text tasks.

ComposioGet→

$ loading_