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

SKILL

browserless-automation

Name: browserless-automation
Author: Composio

Automate browser tasks, web flows, and scraping with Browserless tooling.

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 a prompt/documentation wrapper for using Browserless/Composio via Rube MCP; the material does not declare local code execution, required secrets, or direct remote endpoints. Overall risk is relatively low, but it depends on external MCP services and follow-up connection flows, so real data egress and permission boundaries should be verified on the Rube/Browserless side.

CredentialsCaution

The material says 'No API keys needed,' but it also requires activating a browserless connection via `RUBE_MANAGE_CONNECTIONS` and completing setup through a returned auth link, which implies possible third-party account authorization or session tokens; credential storage and scope are not described.

Network egressCaution

The skill depends on the external MCP service `https://rube.app/mcp` and performs remote operations through Composio/Browserless tools; although the top-level metadata lists no endpoint, the README explicitly points to external services, so task inputs and execution results may leave the local environment. No evidence of unusual or unrelated exfiltration endpoints is shown.

Code executionLow risk

Per the system checks, this project is prompt-only; the material mainly describes call order and parameter conventions, with no executable install script and no claim of starting local processes or executing local code.

Data accessCaution

The skill itself does not declare reading local files or system resources, but its purpose is to 'Automate Browserless operations,' and it executes browser-related tasks through remote tools, potentially handling user-provided web content, session data, or automation outputs. The material does not specify least privilege, data retention, or access boundaries.

Supply chainLow risk

The source is an open-source GitHub repository with strong community adoption (64.7k stars), which are meaningful risk-reducing signals; the visible content looks like skill documentation rather than a closed-source binary. Still, the repository license is undeclared and maintenance status is unknown, so upstream Rube/Composio docs and code should be verified.

Recommendations

Before connecting to `https://rube.app/mcp`, verify its privacy policy, logging retention, and data handling scope.
When completing browserless authorization, check the auth link domain, requested scopes, and whether least-privilege access is supported.
Only provide the minimum web data needed for the task; avoid sharing sensitive accounts, cookies, or production data.
Before real use, separately review the official Rube MCP and Browserless/Composio documentation to confirm endpoints and data flows.

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

// download

Download SKILL.mdInstall manifest ↗

// docs

Browserless Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/browserless

Prerequisites

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

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["browserless"]
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 Browserless-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `browserless`
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 ScrapingBee scraping tasks and web data workflows via Rube MCP.

ComposioGet→

$ loading_