$ loading_
Automate Amazon tasks through Rube MCP after checking current tool schemas.
This skill is an open-source, prompt-only instruction artifact with relatively strong source credibility, and it does not directly require local secrets or local code execution, so overall risk is low. However, it directs users to connect to the third-party Rube MCP service and authorize an Amazon connection, which introduces account-level actions and data flow through an external service, so those aspects warrant caution.
The material states no API keys or environment variables are needed, but it requires creating an Amazon connection via `RUBE_MANAGE_CONNECTIONS` and completing an external auth-link flow, which implies Amazon account tokens or session-based authorization are still involved. Secrets are not configured in the skill repo itself, reducing direct exposure, but the third-party connector may act on the user's behalf in Amazon, so its granted scope should be reviewed.
The README explicitly requires adding `https://rube.app/mcp` as an MCP server and using Composio/Rube to discover and execute Amazon tools; this means user requests, session IDs, tool arguments, and some Amazon-related data may transit through an external service. The endpoint is a declared, relevant service rather than an obviously unrelated destination, so this is typical third-party tool traffic, but it is still external data egress.
Based on the provided material, the skill itself is a prompt-only document with no executable install scripts and no stated need to spawn local processes, run shell commands, or access system-level capabilities. Its behavior is mainly to instruct the client to call existing MCP tool interfaces rather than directly execute code locally.
The skill's stated purpose is to 'Automate Amazon operations,' and it executes workflows through a connected Amazon toolkit, so the main reachable data/resources are the user's Amazon account data and actions within the granted scope rather than the local filesystem. The material does not show local read/write permissions beyond its stated purpose, but the actual access surface depends on the scope granted to the connector.
Positive signals include that the skill comes from a GitHub open-source repository with high community adoption (64.7k stars), which materially lowers supply-chain risk. However, the material only shows the skill instructions, does not provide a license or maintenance status, and actual operation depends on external Rube/Composio services whose server-side implementation cannot be audited from this README alone, so caution is more appropriate than a purely low-risk rating.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "amazon-automation" skill from askskill: 1. Download https://raw.githubusercontent.com/ComposioHQ/awesome-claude-skills/master/composio-skills/amazon-automation/SKILL.md 2. Save it as ~/.claude/skills/amazon-automation/SKILL.md 3. Reload skills and tell me it's ready
Automate Amazon operations through Composio's Amazon toolkit via Rube MCP.
Toolkit docs: composio.dev/toolkits/amazon
RUBE_MANAGE_CONNECTIONS with toolkit amazonRUBE_SEARCH_TOOLS first to get current tool schemasGet 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.
RUBE_SEARCH_TOOLS respondsRUBE_MANAGE_CONNECTIONS with toolkit amazonAlways discover available tools before executing workflows:
RUBE_SEARCH_TOOLS
queries: [{use_case: "Amazon operations", known_fields: ""}]
session: {generate_id: true}
This returns available tool slugs, input schemas, recommended execution plans, and known pitfalls.
RUBE_SEARCH_TOOLS
queries: [{use_case: "your specific Amazon task"}]
session: {id: "existing_session_id"}
RUBE_MANAGE_CONNECTIONS
toolkits: ["amazon"]
session_id: "your_session_id"
RUBE_MULTI_EXECUTE_TOOL
tools: [{
tool_slug: "TOOL_SLUG_FROM_SEARCH",
arguments: {/* schema-compliant args from search results */}
}]
memory: {}
session_id: "your_session_id"
RUBE_SEARCH_TOOLSRUBE_MANAGE_CONNECTIONS shows ACTIVE status before executing toolsmemory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({})| Operation | Approach |
|---|---|
| Find tools | RUBE_SEARCH_TOOLS with Amazon-specific use case |
| Connect | RUBE_MANAGE_CONNECTIONS with toolkit amazon |
| 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 Beaconstac tasks through Rube MCP to streamline QR and marketing workflows.
Automate Cal scheduling and booking tasks through Rube MCP efficiently.
Automate Proofly workflows via Rube MCP using current tool schemas first.
Automate Mem tasks through Rube MCP after checking current tool schemas first.
Automate Beaconchain queries and blockchain operations through Rube MCP.
Automate Bitwarden vault search, creation, updates, and credential management tasks.
Automate Autom workflows via Rube MCP while checking current tool schemas first.
Automate AI/ML API workflows via Rube MCP, checking latest tool schemas first.
Automate Retailed workflows via Rube MCP after checking current tool schemas.
Automate Moz SEO tasks via Rube MCP using current tool schemas first.
Automate Composio tasks via Rube MCP with tool schema lookup first.
Automate Ambee workflows via Rube MCP using current tool schemas first.