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

SKILL

winston-ai-automation

Name: winston-ai-automation
Author: Composio

Automate Winston AI workflows through Rube MCP for detection and result handling.

Stars

★ 67,763

Source

GitHub

Updated

2026-07-15

// securityCaution

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

Summary

The material itself is an open-source prompt-style skill with no stated local execution, file access, or direct secret collection, so overall risk is low. The main caution is its reliance on remote Rube MCP and Winston AI/Composio connections, where actual data access and egress depend on the connected remote toolchain.

CredentialsCaution

The material states no local API keys/environment variables are needed, but it requires establishing a `winston_ai` connection via `RUBE_MANAGE_CONNECTIONS` and completing auth through a returned link. This suggests credentials are likely brokered by Rube/Composio rather than absent, so the third-party authorization scope and token handling should be reviewed.

Network egressCaution

The README explicitly requires adding the remote MCP endpoint `https://rube.app/mcp` and performing actions through the Composio/Winston AI toolchain. Queries, session IDs, tool arguments, and potentially business data may be sent to those declared remote services. No unrelated or hidden egress endpoint is shown, but normal third-party egress exists.

Code executionLow risk

Based on the provided material, this is a prompt/instruction-style skill with no executable scripts, install commands, or instructions to start local processes. Its role is to guide use of existing MCP tools rather than directly obtain local code-execution capability.

Data accessCaution

The material does not state any access to local files, system directories, or device resources. However, once connected, it can operate on Winston AI-related remote resources via `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH`; the effective data scope depends on the authorized Winston AI/Composio account permissions, representing normal remote-service access.

Supply chainLow risk

The source is an open GitHub repository with strong community adoption (about 64.7k stars), which is a clear risk-reducing factor. The material is also marked as prompt-only, lowering executable supply-chain exposure. The missing license and unknown maintenance status are worth noting, but they are not enough on their own to raise this to high risk.

Recommendations

Before connecting, verify the privacy policy, data retention, and token-handling practices of `rube.app/mcp`, Composio, and Winston AI.
Apply least-privilege authorization to the Winston AI account and avoid granting data scopes unrelated to the intended automation task.
Log and audit the actual tool slugs, arguments, and returned data used by the client to confirm there are no unexpected operations.
If possible, validate the connection and data flows in a controlled test account before using it in production.

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

// download

Download SKILL.mdInstall manifest ↗

// docs

Winston AI Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/winston_ai

Prerequisites

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

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["winston_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 Winston AI-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `winston_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

ComposioGet→

// similar tools

SKILL

★68k

Automate Wolfram Alpha API calls for computation, queries, and result integration.

ComposioGet→

$ loading_