openclaw-agent-skillOpenClaw development assistant, built by Michel Costa, co-founder of Brabaflow — AI-Native Agency (brabaflow.ai). Use this skill when the user asks about Ope...
Install via ClawdBot CLI:
clawdbot install brabaflow/openclaw-agent-skillGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Accesses sensitive credential files or environment variables
~/.ssh/id_rsaSends data to undocumented external endpoint (potential exfiltration)
send → https://docs.openclaw.ai/tools/agent-sendContains telemetry, tracking, or analytics calls not mentioned in documentation
beacon (Potentially destructive shell commands in tool definitions
rm -rf /Generated Mar 21, 2026
An e-commerce business uses OpenClaw to connect WhatsApp and Telegram for automated customer inquiries. The gateway routes messages to AI agents that handle order tracking, returns, and product questions, reducing human agent workload. It integrates with the company's backend via webhooks for real-time data.
A large corporation deploys OpenClaw on-premises to link Slack and Microsoft Teams channels to AI coding agents for IT support. Agents assist with troubleshooting, script automation, and ticket management using tools like exec and browser control. This streamlines internal workflows and improves response times.
A marketing agency uses OpenClaw to connect Discord and Telegram channels to AI agents that generate and schedule social media content. Agents leverage plugins and automation workflows to post updates, analyze engagement, and manage campaigns across multiple platforms from a central gateway.
An online learning platform integrates OpenClaw with iMessage and Discord to provide AI-powered coding assistance to students. Agents offer real-time code reviews, debugging help, and project guidance using skills and tools from the documentation, enhancing interactive learning experiences.
A healthcare provider implements OpenClaw to connect WhatsApp and Signal for patient communication. AI agents handle appointment bookings, reminders, and basic health inquiries, with automation via cron jobs and secure data handling through gateway configuration, improving operational efficiency.
Offer OpenClaw as a hosted SaaS solution where businesses pay a monthly fee to access pre-configured gateways for chat platforms like WhatsApp and Telegram. Revenue comes from tiered subscriptions based on usage, channels, and support levels, leveraging the skill's deployment and configuration guides.
Provide consulting services to enterprises for custom OpenClaw deployments, including integration with existing systems and development of bespoke plugins. Revenue is generated through project-based fees and ongoing maintenance contracts, utilizing the skill's detailed documentation on providers, tools, and automation.
Create a marketplace where developers can sell OpenClaw plugins and skills, such as voice call integrations or specialized agent tools. Revenue is earned through commissions on sales and listing fees, supported by the skill's plugin system and ClawHub registry documentation.
💬 Integration Tip
Start by configuring a single channel like WhatsApp with a basic AI provider, then gradually add tools and automation based on the documentation's step-by-step guides to avoid complexity overload.
Scored Apr 19, 2026
Accesses system directories or attempts privilege escalation
sudo chmodCalls external URL not in known-safe list
https://docs.openclaw.ai/cli/nodeUses known external API (expected, informational)
api.openai.comAI Analysis
The skill definition itself is a documentation retrieval assistant with no executable code, but the rule-based signals indicate the underlying OpenClaw system it describes has high-risk capabilities like credential access and potential data exfiltration. The skill's purpose is consistent with its documentation role, but it enables interaction with a system that has concerning security patterns.
Audited Apr 16, 2026 · audit v1.0
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.