$ ~/registry/skill/composiohq-composio-skills-re-amaze-automation

SKILL

re-amaze-automation

Name: re-amaze-automation
Author: Composio

Automate Re:amaze support tasks via Rube MCP using current tool schemas.

Stars

★ 67,763

Source

GitHub

Updated

2026-07-15

// securityCaution

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

Summary

This skill itself is an open-source prompt/documentation artifact and does not directly require local secrets or local code execution, so its baseline risk is low. However, it is designed to connect users to remote Rube MCP/Composio services and operate on Re Amaze, which introduces third-party authorization and outbound data-flow considerations.

CredentialsCaution

The material says there are 'no API keys,' but it explicitly requires creating an active `re_amaze` connection via `RUBE_MANAGE_CONNECTIONS` and completing setup through a returned auth link. In practice this still involves third-party account authorization/tokens, likely brokered by the remote MCP, which creates normal delegated-credential exposure.

Network egressCaution

The README explicitly instructs users to add the remote MCP endpoint `https://rube.app/mcp` and references Composio/toolkit docs. When using `RUBE_SEARCH_TOOLS` and `RUBE_MULTI_EXECUTE_TOOL`, task inputs and related business data will likely be sent to Rube/Composio and onward to the connected Re Amaze service. This is expected egress for the stated function, but the data path includes a third-party intermediary.

Code executionLow risk

The system flags this as prompt-only, and the content is primarily usage guidance and call patterns. It does not describe local install scripts, shell commands, or local process execution, so no additional local code-execution capability is evident from the material.

Data accessCaution

The stated purpose is to 'Automate Re Amaze operations,' with tool discovery, bulk execution, and pagination workflows, indicating intended access to and manipulation of Re Amaze business/support data. The material does not show local file access, but the scope of third-party SaaS data access depends on the permissions granted to the Re Amaze connection and should be minimized.

Supply chainCaution

Positive signals include a GitHub open-source source and very high community adoption (64.7k stars), which materially lowers risk. However, the provided repository points to an `awesome-claude-skills` aggregator rather than standalone source for this skill, the license is unspecified, maintenance status is unknown, and the actual functionality depends on external Rube MCP/Composio services, so the audit boundary is not fully contained in the repository.

Recommendations

Enable it only after you trust `rube.app/mcp` and Composio's data-handling path, and verify their privacy and logging/retention practices.
Grant the minimum necessary Re Amaze permissions; prefer a restricted account or test workspace instead of a high-privilege production connection.
Review the specific tools and arguments returned by `RUBE_SEARCH_TOOLS` before execution to avoid sending unnecessary customer or ticket data to third parties.
Prefer independently auditable source, a clear license, and maintenance disclosure; if those are missing, test in an isolated environment first.

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

// download

Download SKILL.mdInstall manifest ↗

// docs

Re Amaze Automation via Rube MCP

Automate Re Amaze operations through Composio's Re Amaze toolkit via Rube MCP.

Toolkit docs: composio.dev/toolkits/re_amaze

Prerequisites

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

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["re_amaze"]
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 Re Amaze-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `re_amaze`
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 AI/ML API workflows via Rube MCP, checking latest tool schemas first.

ComposioGet→

$ loading_