trio-stream-visionAnalyze any YouTube livestream or RTSP camera feed using natural language — ask what's happening, detect specific events, or get periodic summaries. Powered...
Install via ClawdBot CLI:
clawdbot install drandrewlaw/trio-stream-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.com/api-reference/AI Analysis
The skill legitimately sends video stream URLs and user queries to Trio's documented API endpoint for analysis, which is consistent with its stated purpose of video stream analysis. While external data transmission occurs, it's to the service provider's own API (trio.machinefi.com) as explicitly described in the skill documentation, not to unauthorized or hidden endpoints. No credential harvesting, hidden instructions, or obfuscation patterns were detected.
Audited Apr 16, 2026 · audit v1.0
Generated Mar 20, 2026
Homeowners can use this skill to monitor security cameras via RTSP feeds, asking questions like 'Is there a person at my front door?' or setting up alerts for specific events such as package deliveries. It enables real-time detection without constant manual watching, integrating with webhooks for instant notifications to mobile devices.
Construction managers can analyze live feeds from site cameras to detect unauthorized access, monitor equipment usage, or check for safety compliance (e.g., 'Are workers wearing hard hats?'). Periodic summaries provide daily activity reports, helping track progress and ensure site security without on-site supervision.
Retailers can use YouTube Live or RTSP streams to analyze customer behavior, such as detecting crowd levels, monitoring checkout lines, or identifying specific events like shoplifting. This allows for data-driven decisions on staffing and layout, with live monitoring for immediate response to incidents.
Conservationists can stream camera feeds from remote locations to detect animal presence, track migration patterns, or monitor for poaching activities. Natural language queries like 'Is there an elephant in the frame?' enable efficient analysis, with periodic summaries compiling observations over time for research purposes.
Warehouse operators can monitor live video feeds to track inventory movement, detect anomalies like misplaced items, or ensure safety protocols are followed. Using check-once for quick snapshots or live-monitor for continuous alerts helps optimize logistics and reduce operational errors.
Offer a SaaS platform where users pay a monthly fee for access to the skill, including API credits and premium features like higher frequency monitoring or advanced analytics. Revenue is generated through tiered pricing based on usage levels, such as number of streams or minutes monitored.
Sell API credits directly to developers and businesses, charging per action (e.g., $0.01 per check-once, $0.02 per minute for live-monitor). This model attracts users with variable needs, allowing them to scale costs based on actual usage without long-term commitments.
License the skill to other companies, such as security firms or IoT platforms, who integrate it into their own products under their brand. Revenue comes from licensing fees and ongoing support contracts, leveraging the skill's capabilities to enhance third-party offerings.
💬 Integration Tip
Start by testing with a free API key and simple check-once queries to validate stream compatibility before setting up more complex live-monitor workflows with webhooks for automation.
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.