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

SKILL

chatfai-automation

Name: chatfai-automation
Author: Composio

Automate Chatfai tasks via Rube MCP with schema lookup first.

Stars

★ 67,763

Source

GitHub

Updated

2026-07-15

// securityCaution

Prompt only, no code
Open source
Community-trusted· 64.9k

Summary

This skill appears to be a prompt/documentation-style wrapper with open-source distribution and strong community adoption, so overall risk is low. However, its instructions explicitly rely on remote Rube MCP and a Chatfai connection, meaning actual use involves external tool discovery, connection management, and remote execution that warrant attention to data egress and third-party authorization scope.

CredentialsCaution

The material says 'No API keys needed' but also requires activating a `chatfai` connection via `RUBE_MANAGE_CONNECTIONS` and completing an external auth link. This suggests the skill does not directly collect local API keys, but it does rely on third-party account authorization/tokens, creating normal caution around third-party connection scope and potential misuse.

Network egressCaution

The instructions require adding the remote MCP endpoint `https://rube.app/mcp` and using Composio/Rube for tool discovery, connection management, and tool execution. As a result, user inputs, session IDs, tool arguments, and possibly Chatfai operation data may be sent to the stated third-party service. The endpoint is explicit and functionally relevant, with no clear sign of unrelated or hidden exfiltration.

Code executionLow risk

Based on the provided material, the skill itself is an instruction/workflow prompt and does not include local scripts, install commands, or direct local code execution requirements. Any execution capability comes from external MCP tools rather than the skill text itself.

Data accessCaution

The material does not state direct read/write access to local files or system resources, but it does pass sessions, parameters, pagination results, and potentially Chatfai account data through remote workflows. The effective data access scope depends on Rube MCP and the authorized Chatfai connection, so least-privilege review is advisable.

Supply chainLow risk

The source is an open GitHub repository and part of the widely adopted `awesome-claude-skills` collection (~64.9k stars), which provides good auditability and source trust. The missing license declaration and unclear maintenance status are minor uncertainties, but not enough on their own to justify a high-risk rating.

Recommendations

Before use, verify the privacy policy and data handling scope of `rube.app/mcp`, Composio, and Chatfai, and only send the minimum necessary data.
When authorizing via `RUBE_MANAGE_CONNECTIONS`, review the Chatfai connection permissions and prefer least-privilege or test accounts.
Avoid placing unnecessary sensitive data in tool arguments, memory, or sessions, and revoke unused connections regularly.
For higher assurance, review the open-source repository content and log the actual tools, inputs/outputs, and external endpoints involved.

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

// download

Download SKILL.mdInstall manifest ↗

// docs

Chatfai Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/chatfai

Prerequisites

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

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["chatfai"]
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 Chatfai-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `chatfai`
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 Recallai workflows through Rube MCP with tool-schema lookup first.

ComposioGet→

$ loading_