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

SKILL

wit-ai-automation

Name: wit-ai-automation
Author: Composio

Automate Wit AI workflows via Rube MCP using current tool schemas first.

Stars

★ 73,665

Source

GitHub

Updated

2026-08-28

// securityCaution

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

Summary

This skill is essentially a prompt/workflow wrapper for using Rube MCP/Composio, and its open-source origin with strong community adoption lowers overall risk. The main caution is that it explicitly depends on an external MCP endpoint and third-party connection flow, so network egress and delegated authorization should be verified carefully.

CredentialsCaution

The material says “no API keys needed,” but the README also requires establishing an ACTIVE `wit_ai` connection via `RUBE_MANAGE_CONNECTIONS` and completing an auth link, indicating delegated third-party account authorization/tokens even if not exposed as environment variables; watch for misuse or unclear permission scope.

Network egressCaution

The README explicitly instructs adding `https://rube.app/mcp` as an MCP server and using Composio’s Wit AI toolkit for operations; this means task inputs, tool arguments, and potentially business data may be sent to Rube/Composio and the connected Wit AI service. This is normal for such tools, but data flows and privacy boundaries should be verified.

Code executionLow risk

Based on the provided material, this is a prompt-style skill that mainly describes how to call remote tools such as `RUBE_SEARCH_TOOLS`, `RUBE_MANAGE_CONNECTIONS`, and `RUBE_MULTI_EXECUTE_TOOL`; there is no indication that it itself starts local processes, runs scripts, or requests system-level execution privileges.

Data accessLow risk

The material does not state any direct read/write access to local files, system directories, databases, or other local resources; it focuses on remote tool discovery, connection status, and execution flow. Although data sent through remote tools may include user content, there is no sign of excessive local access in the documentation.

Supply chainLow risk

The source is an open GitHub repository with high community adoption (64.7k stars), which materially lowers supply-chain risk; the skill also appears to be documentation/prompt content rather than a standalone executable binary. Still, the missing license declaration and unknown maintenance status warrant follow-up review of repository activity and changes.

Recommendations

Review the data handling terms of `rube.app/mcp`, Composio, and Wit AI before use, and avoid sending sensitive content.
Verify the exact permission scope during `RUBE_MANAGE_CONNECTIONS` authorization and prefer least-privileged accounts.
Enable this skill only in trusted clients and log tool calls and parameters sent through Rube MCP.
Check recent commits, maintainer identity, and release history of the referenced GitHub repository.

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

// download

Download SKILL.mdInstall manifest ↗

// docs

Wit AI Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/wit_ai

Prerequisites

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

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["wit_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 Wit AI-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `wit_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

Automate Wati messaging and customer communication tasks through Rube MCP.

ComposioGet→

$ loading_