trio-visionTurn any live camera into a smart camera — describe what to watch for in plain English, get alerts in your chat when it happens. Ask questions about any live...
Install via ClawdBot CLI:
clawdbot install drandrewlaw/trio-visionGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → https://trio.machinefi.com/api/check-onceCalls external URL not in known-safe list
https://docs.machinefi.comAI Analysis
The skill sends camera stream data and user-defined conditions to a third-party API (Trio by MachineFi) for AI analysis, which is consistent with its stated purpose of smart camera monitoring. While this represents a legitimate privacy consideration (external processing of potentially sensitive video data), there's no evidence of credential harvesting, hidden instructions, or obfuscation. The API endpoint and documentation URLs match the service described.
Audited Apr 17, 2026 · audit v1.0
Generated Mar 20, 2026
Homeowners use Trio Vision to monitor front door cameras for package deliveries or unauthorized entry. They set up live-monitor with conditions like 'a person approaches the door' and receive alerts via webhook to their phone, reducing false alarms from shadows or pets.
Retail managers monitor store cameras to track customer traffic patterns and detect shoplifting. They use live-digest for periodic summaries of busy hours and check-once to verify if specific items are out of stock, optimizing staff deployment and inventory management.
Construction companies set up cameras on remote sites to monitor for theft or safety violations. They use live-monitor with conditions like 'unauthorized vehicle enters site' and receive alerts, ensuring site security without constant manual oversight.
Streaming platforms like Twitch use Trio Vision to monitor live streams for inappropriate content. They implement live-monitor with conditions such as 'violence or nudity detected' and trigger automatic takedowns or moderator alerts, enhancing community safety.
Warehouse operators monitor loading docks and storage areas to track inventory movement. They use check-once to verify if specific pallets are present and live-digest for summaries of daily activity, improving logistics efficiency and reducing manual checks.
Offer tiered subscription plans based on credit usage, such as a free tier with 100 credits and paid tiers for higher volumes. This model provides predictable revenue from businesses needing continuous monitoring, with upsell opportunities for advanced features like hybrid input mode.
Sell credits directly to users for one-off tasks like check-once queries or short-term monitoring. This appeals to casual users or small businesses with sporadic needs, generating revenue from microtransactions without long-term commitments.
License the technology to large companies for integration into their own security or analytics platforms. This includes custom branding and support, targeting industries like retail or construction for scalable deployments and higher-value contracts.
💬 Integration Tip
Start by testing with check-once to validate stream URLs and conditions before setting up live-monitor, ensuring API key is properly exported to avoid authentication errors.
Scored Jun 19, 2026
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.