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

SKILL

amara-automation

Name: amara-automation
Author: Composio

Automate Amara tasks through Rube MCP after checking current tool schemas first.

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 prompt-only and open-source, with no direct local secret requirement or local code execution. However, it is designed to connect to remote Rube MCP and operate through Composio/Amara integrations, so external service interaction and third-party connections warrant caution overall.

CredentialsCaution

The material claims there are 'no API keys', but it explicitly requires an active Amara connection via `RUBE_MANAGE_CONNECTIONS` and asks the user to complete an auth link. This implies real third-party account authorization/tokens are involved, even if not exposed as environment variables in the skill itself.

Network egressCaution

The README instructs users to add the remote MCP endpoint `https://rube.app/mcp` and execute actions through Composio's Amara toolkit. Task content, tool arguments, and session data may therefore be sent to these declared external services. The stated endpoints appear aligned with the described purpose, with no obvious unrelated exfiltration red flags in the material.

Code executionLow risk

Per the objective checks, this skill is prompt-only. The material does not describe the skill itself spawning local processes, running scripts, or requesting system-level execution privileges. The mentioned `RUBE_MULTI_EXECUTE_TOOL`/`RUBE_REMOTE_WORKBENCH` are descriptions of remote tool usage, not direct local code execution by this skill.

Data accessCaution

The skill text itself does not claim direct local file read/write access, but through the remote MCP/Composio/Amara workflow, user requests, session IDs, and potentially business data will be used by third-party tools. The material does not show a clear least-privilege boundary or exact data scope, so the connected account's authorization scope should be reviewed carefully.

Supply chainLow risk

The source is a GitHub open-source repository with strong community adoption (64.7k stars), which is a meaningful positive trust signal. This item is also marked open-source and prompt-only, improving auditability. Remaining concerns are the undeclared license, unknown maintenance status, and the fact that the external Rube/Composio services are not fully auditable from this repository alone.

Recommendations

Before connecting, verify that `rube.app`, Composio, and the Amara authorization pages are legitimate and review exactly what account permissions are being granted.
Grant only the minimum Amara permissions necessary for the intended automation, avoiding broader access unrelated to the task.
Test with a sandbox account or non-sensitive project first to confirm what data is sent to external services and what responses are returned.
Review the exact skill contents and recent maintenance status in the open-source repository 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 "amara-automation" skill from askskill:
1. Download https://raw.githubusercontent.com/ComposioHQ/awesome-claude-skills/master/composio-skills/amara-automation/SKILL.md
2. Save it as ~/.claude/skills/amara-automation/SKILL.md
3. Reload skills and tell me it's ready

// download

Download SKILL.mdInstall manifest ↗

// docs

Amara Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/amara

Prerequisites

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

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["amara"]
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 Amara-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `amara`
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 Amazon tasks through Rube MCP after checking current tool schemas.

ComposioGet→

$ loading_