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

SKILL

apipie-ai-automation

Name: apipie-ai-automation
Author: Composio

Automate Apipie AI workflows via Rube MCP with schema-first tool discovery.

Stars

★ 67,763

Source

GitHub

Updated

2026-07-15

// securityCaution

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

Summary

This skill is an open-source prompt-style wrapper and does not directly declare local code execution, file access, or fixed built-in endpoints, so overall risk is relatively low. However, it is designed around external Rube MCP and an Apipie AI connection, which means real usage involves third-party tool discovery, connection management, and remote actions that require attention to data flow and authorization scope.

CredentialsCaution

The material claims 'no keys', but the README explicitly requires an ACTIVE `apipie_ai` connection via `RUBE_MANAGE_CONNECTIONS` and asks the user to complete an auth link, implying third-party account authorization or tokens in practice, even if the skill itself does not directly collect credentials.

Network egressCaution

Although no remote host is declared at the top, the README explicitly requires connecting to `https://rube.app/mcp` and using Composio/Rube for tool discovery, connection checks, and remote execution; task content, arguments, and session data provided by the user may be sent to that third-party service.

Code executionLow risk

Based on the provided material, this is a prompt/workflow instruction-style skill and does not declare local process spawning, script execution, or system command execution by itself; any execution capability would come from the external MCP/remote tools rather than from this skill text.

Data accessCaution

The material does not declare direct local file read/write or local data access, but via external capabilities such as `RUBE_SEARCH_TOOLS`, `RUBE_MULTI_EXECUTE_TOOL`, and `RUBE_REMOTE_WORKBENCH`, it can perform operations on Apipie AI-related resources; the actual data access scope depends on the discovered tool schemas and the user's granted authorization.

Supply chainLow risk

The source is an open GitHub repository with high community adoption (64.7k stars), both of which are strong risk-reducing signals; the visible content appears to be skill documentation rather than a closed executable component. The missing license declaration and unknown maintenance status slightly reduce transparency, but not enough on their own to justify a high-risk rating.

Recommendations

Before enabling it, verify the actual data processor, privacy policy, and permission scope behind the Rube MCP and Apipie AI authorization flow.
Grant Apipie AI connection access only when needed, preferably using least-privilege accounts or a test environment.
Review the tool schemas returned by `RUBE_SEARCH_TOOLS` before execution and avoid sending sensitive business data to unnecessary tools.
Log and monitor operations and sessions sent through `rube.app/mcp`, and periodically revoke third-party connections if needed.

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

// download

Download SKILL.mdInstall manifest ↗

// docs

Apipie AI Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/apipie_ai

Prerequisites

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

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["apipie_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 Apipie AI-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `apipie_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 API Labz tasks via Rube MCP using current tool schemas.

ComposioGet→

$ loading_