$ ~/registry/skill/composiohq-composio-skills-retailed-automation

SKILL

retailed-automation

Name: retailed-automation
Author: Composio

Automate Retailed workflows via Rube MCP after checking 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 is essentially an open-source prompt/instruction artifact with no direct local secret requirement or fixed declared endpoint, so its inherent risk is low. However, it relies on external Rube MCP/Composio remote tooling and connection flows, meaning actual operations and data may be handled by third-party services and should be reviewed for permissions and data flow.

CredentialsCaution

The material says 'No API keys needed,' but it also requires establishing an ACTIVE `retailed` connection via `RUBE_MANAGE_CONNECTIONS` and completing an auth-link flow, which implies credentials are likely handled by the external MCP/integration layer rather than local environment variables. The skill itself does not expose a local secret requirement, but there is ordinary third-party delegated authorization risk.

Network egressCaution

Users are instructed to add `https://rube.app/mcp` as an MCP server, and tool execution depends on remote Composio/Rube services; despite the system field showing no remote host, the README clearly indicates external network communication. The material does not fully specify which backends or downstream SaaS services receive which business data, so this should be treated as a normal third-party data egress scenario requiring attention.

Code executionLow risk

Based on the provided material, this is a prompt/workflow instruction artifact centered on calling external MCP tools and schemas; it does not state that it starts local processes, executes shell/scripts, or requests system-level execution permissions. On the available facts, there is no local code-execution red flag.

Data accessCaution

The stated purpose is to 'Automate Retailed operations,' and it supports `RUBE_MULTI_EXECUTE_TOOL`, bulk operations, and a remote workbench; this means the effective data-access scope depends on the authorized Retailed toolkit and the connected account permissions. The material does not claim local file access, but the remote business-data access surface may be broad and should be reviewed under least-privilege principles.

Supply chainLow risk

The source is an open-source GitHub repository with strong community adoption (64.7k stars), both of which are meaningful risk-reducing signals; the visible content is mainly README/prompt template material, which is relatively auditable. The missing declared license and unknown maintenance status are minor information gaps, but not enough on their own to justify a high-risk rating.

Recommendations

Before connecting to `rube.app/mcp`, verify its privacy policy, log retention practices, and whether it forwards business data to downstream services.
Grant the `retailed` connection only the minimum account permissions needed for the task, and review/revoke authorizations regularly.
Inspect the actual tool list and schemas returned by `RUBE_SEARCH_TOOLS` before execution to avoid unintended data access or write operations.
Where possible, validate the automation flow in an isolated workspace or test account 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 "retailed-automation" skill from askskill:
1. Download https://raw.githubusercontent.com/ComposioHQ/awesome-claude-skills/master/composio-skills/retailed-automation/SKILL.md
2. Save it as ~/.claude/skills/retailed-automation/SKILL.md
3. Reload skills and tell me it's ready

// download

Download SKILL.mdInstall manifest ↗

// docs

Retailed Automation via Rube MCP

Automate Retailed operations through Composio's Retailed toolkit via Rube MCP.

Toolkit docs: composio.dev/toolkits/retailed

Prerequisites

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

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["retailed"]
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 Retailed-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `retailed`
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 Retently feedback and survey workflows through Rube MCP.

ComposioGet→

$ loading_