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

SKILL

supportivekoala-automation

Name: supportivekoala-automation
Author: Composio

Automate Supportivekoala workflows through Rube MCP for scalable personalized tasks.

Stars

★ 67,763

Source

GitHub

Updated

2026-07-15

// securityCaution

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

Summary

This skill appears to be primarily prompt/instruction content for using the Rube MCP/Composio toolchain, with no embedded secrets or native local execution logic of its own. The main considerations are outbound use of an external MCP service and delegated access to a Supportivekoala account, so it should be used with least-privilege controls.

CredentialsCaution

The material states the skill itself requires no API keys, but actual use requires creating a Supportivekoala connection via `RUBE_MANAGE_CONNECTIONS` and completing authorization through a returned auth link. So while there is no static key to configure, third-party account tokens/session authorization are still involved and should be reviewed for OAuth scope and token handling.

Network egressCaution

The README explicitly instructs adding `https://rube.app/mcp` as an MCP server and using Composio/Rube to search tools, manage connections, and execute operations; this means task requests, tool arguments, and potentially business data are sent to an external service. The endpoint is clearly declared and aligned with stated functionality, but users should verify what data is transmitted and where the boundaries are.

Code executionLow risk

Based on the provided material, this is a prompt-only skill whose content is mainly workflow and parameter guidance; there is no indication that it itself runs local scripts, installs binaries, or requests extra system-level execution privileges. Any execution capability comes from the external MCP toolchain rather than from the skill text itself.

Data accessCaution

The skill is intended to 'Automate Supportivekoala operations' and, through an authorized connection, can query or perform bulk actions in Supportivekoala; this typically implies access to or modification of data within that SaaS account. The material does not provide a granular permission list, so the effective data scope should be treated as constrained by the external tool schemas and the granted authorization settings.

Supply chainLow risk

The source is an open-source GitHub repository with strong community adoption (64.7k stars), both of which materially reduce supply-chain risk; being prompt-only also lowers the chance of hidden binaries or malicious dependencies. Remaining caveats are that the license is undeclared and maintenance status is unknown, so repository activity and upstream Composio/Rube documentation should still be reviewed.

Recommendations

Before connecting Supportivekoala, review the exact OAuth/authorization scopes requested and grant only the minimum needed.
Treat `https://rube.app/mcp` as an external data processor and avoid sending unnecessary sensitive content in tool arguments.
Use a read-only or test account first to validate the schemas returned by `RUBE_SEARCH_TOOLS` and the actual actions available before enabling production access.
Review repository activity, commit history, and official Composio/Rube documentation to confirm the skill instructions are not outdated.

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

// download

Download SKILL.mdInstall manifest ↗

// docs

Supportivekoala Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/supportivekoala

Prerequisites

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

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["supportivekoala"]
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 Supportivekoala-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `supportivekoala`
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 Mailcoach email marketing and subscriber workflows through Rube MCP.

ComposioGet→

$ loading_