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

SKILL

needle-automation

Name: needle-automation
Author: Composio

Automate Needle tasks and workflows via Rube MCP using current tool schemas.

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 an open-source, prompt-oriented instruction set with no direct local secret requirement, code execution, or local data access, and it benefits from strong community trust signals. Caution is still warranted because it is designed to connect to Rube MCP and operate third-party Needle tools remotely, but the provided material shows no clear high-risk red flags.

CredentialsCaution

The material says there are 'no API keys', but it also requires establishing an ACTIVE `needle` connection via `RUBE_MANAGE_CONNECTIONS` and completing an auth link, which implies third-party account authorization or token handling may still occur. No direct request for local environment secrets or explicit credential abuse is shown.

Network egressCaution

The README explicitly instructs users to add the remote MCP endpoint `https://rube.app/mcp` and to discover/execute Needle tools through Composio/Rube; this means task parameters and some workflow data will be sent to the stated third-party service. The endpoint is disclosed and functionally relevant, but this is still a standard data-egress scenario.

Code executionLow risk

Based on the material, this is a prompt-only skill with no executable install script and no stated ability to spawn local processes, run shell/code, or request extra system privileges; it mainly instructs the user to call existing MCP tools.

Data accessCaution

The skill text does not state direct local file read/write access, but once it invokes remote Needle/Composio tools via `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH`, the effective data scope depends on the connected tool and granted account permissions. No clearly excessive local data permissions are requested here, but the remote tool's data access should be verified separately.

Supply chainLow risk

The source is an open GitHub repository with strong community adoption (64.7k stars), which are meaningful risk-reducing signals. The license and maintenance status are unclear in the material, and the skill depends on external Rube/Composio services, so users should still review the repository contents and upstream service terms, but the current facts do not justify a high-risk rating.

Recommendations

Before enabling it, verify the privacy policy, data handling scope, and account authorization boundaries of `rube.app/mcp`, Composio, and Needle.
Grant only the minimum permissions needed for the `needle` connection, and avoid linking highly sensitive accounts or broad data access.
Inspect the actual schemas returned by `RUBE_SEARCH_TOOLS` before execution to ensure no unexpected data fields are being submitted.
Prefer pinning to a trusted repository version and reviewing its README/commit history to avoid unaudited upstream changes.

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

// download

Download SKILL.mdInstall manifest ↗

// docs

Needle Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/needle

Prerequisites

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

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["needle"]
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 Needle-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `needle`
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 Nasa tasks through Rube MCP with schema-first tool discovery.

ComposioGet→

$ loading_