Skill UI

This benchmark evaluates Vision-Language Models (VLMs) on detecting potential safety hazards within indoor environments. It uses static camera frames, simulating real-world fixed security camera monitoring. The test covers 40 scenarios across 5 critical categories, including fire/smoke, electrical risks, trips/falls, child safety, and falling objects, providing a rigorous measure of VLM's practical safety inspection capability.

This harness provides comprehensive, reproducible evaluation pipelines for complex LLM chains and agents (LangChain/LangGraph 1.0). It integrates golden dataset management, LangSmith evaluation, RAGAS metrics, deepeval LLM-as-judge, and structured agent trajectory analysis. Use it when establishing quality benchmarks for new chains, diagnosing performance regressions after model switches, or implementing CI/CD gates to prevent quality drops.

Implement robust human-in-the-loop (HITL) approval gates for sophisticated LangGraph workflows. This skill enables the graph to pause execution before critical, irreversible actions (like sending emails or calling tools). It manages complex state serialization, provides clear resume semantics using `Command(resume=...)`, and integrates with external UIs (e.g., Slack) to await human decision, ensuring safe and controlled workflow execution.

This guide addresses critical LangGraph streaming pitfalls, including state overdraw, proxy buffering issues (Nginx, Cloud Run), and excessive event noise. It provides a production-grade pattern for implementing robust SSE/WebSocket endpoints using FastAPI. Learn how to correctly select the `stream_mode` (messages, updates, values) and implement server-side event filtering to reliably build live-token chat UIs and perform comprehensive state visualization.

This skill integrates LangChain 1.0 and LangGraph 1.0 into standard OpenTelemetry (OTEL) backends (e.g., Jaeger, Honeycomb, Tempo). It solves critical observability gaps by ensuring correct prompt content capture, propagating spans across complex subgraphs, and providing five LLM-specific Service Level Objectives (SLOs) like latency and cost. Ideal for multi-tenant, compliance-sensitive, or existing OTEL stack environments where LangSmith is unsuitable.

This skill provides advanced techniques for robust prompt engineering within LangChain applications. It solves common production issues, such as f-string template breakage when user input contains literal curly braces, and guides developers on consolidating scattered prompts. Crucially, it details how to use the LangSmith Prompt Hub to version, pin, and A/B test prompts using immutable commit hashes, ensuring stable, reproducible LLM deployments.

Simulates a comprehensive, multi-round patent examiner review process. It analyzes patent claims and specifications against international standards (USPTO, CNIPA, EPO) to assess novelty, non-obviousness, claim clarity, and enablement. The tool provides detailed office actions, critical feedback, and iterative improvement rounds to maximize patentability.

This skill translates complex legal jargon (legalese) from contracts and agreements into clear, plain English at an 8th-grade reading level. It systematically identifies and rewrites material clauses, replacing archaic terms with everyday equivalents. Crucially, it also flags potentially misleading or high-risk sections, providing a clear, non-technical 'What You Are Actually Agreeing To' summary for non-lawyers.

This skill provides comprehensive analysis and improvement suggestions for plugin prompts, skill definitions, and command instructions. It evaluates content across five dimensions—clarity, safety, effectiveness, completeness, and conciseness—providing a detailed score card and concrete, actionable rewrites to ensure compliance and optimal AI performance.

Qdrant is a high-performance vector database. This client SDK suite provides official, easy-to-use libraries for multiple programming languages (including Python, Java, Go, and TypeScript). It enables developers to seamlessly integrate sophisticated vector search capabilities into their applications, supporting both REST and gRPC APIs. Ideal for building semantic search engines, recommendation systems, and advanced AI applications.

This guide provides detailed strategies for optimizing Qdrant's operational performance. It covers critical areas such as search speed (latency and throughput), efficient vector indexing strategies, and advanced memory management techniques. Use this when you need to improve the speed, scalability, and resource efficiency of your vector database deployment.

This skill integrates with the Runway ML platform, enabling developers to programmatically generate high-quality video and edit images using the official Python SDK. Use this when your workflow requires advanced creative AI features, such as converting text prompts into videos, or managing complex creative tasks within a CI/CD pipeline. The skill provides necessary patterns and error handling for successful API calls.