Skill UI

A comprehensive framework for rigorously testing and benchmarking LLM agents. It moves beyond simple pass/fail checks to assess complex behaviors, reliability metrics, and capability consistency across multiple runs. Ideal for production monitoring and identifying subtle failure modes in advanced AI agents.

A systematic workflow designed to significantly improve the reliability and performance of existing AI agents. It covers detailed performance analysis, including gathering metrics (e.g., task success rate, latency), classifying failure modes, and advanced prompt engineering techniques (like Chain-of-Thought and Constitutional AI). The process culminates in structured A/B testing and controlled deployment, ensuring measurable, robust improvements.

This skill defines structured behavioral frameworks (e.g., Brainstorm, Implement, Debug, Review, Teach, Ship) to guide the AI's output and approach based on the specific task phase. It optimizes performance by ensuring the AI adopts the correct mindset and output format—from initial ideation to final deployment—guaranteeing systematic, high-quality results across the entire development lifecycle.

This skill provides a comprehensive guide to the credit-based pricing model of Kling AI. It details costs for video generation (Standard/Professional modes), image creation (Kolors), and API resource packs. Users can utilize this guide to accurately budget, estimate total project costs, and implement cost-saving strategies, ensuring the efficient and economical execution of their AI content generation workflow.

Utilize the Kling AI API to generate high-quality, cinematic videos directly from descriptive text prompts. This advanced tool supports professional modes, camera movement control (pan, tilt, zoom), negative prompting, and synchronized native audio, making it ideal for professionals building robust text-to-video pipelines and creative content generation.

A comprehensive guide for troubleshooting and resolving Langfuse-related incidents and outages. It provides step-by-step procedures for initial triage, severity assessment, implementing fallback modes, and resolving common issues like missing traces or rate limits, ensuring continuous observability monitoring for LLM applications.

A structured playbook for rapidly diagnosing and resolving production incidents related to Lokalise localization services. It guides users through essential quick diagnostics (API health, token validity, rate limits) and provides a decision tree for common failure modes, such as missing or stale translations, API outages, and upload failures, ensuring swift mitigation and postmortem readiness.

Simulates a highly structured, sequential peer-review process using multiple specialized AI agents (e.g., Skeptic, Constraint Guardian, User Advocate). This skill is designed to rigorously stress-test a design, surface hidden assumptions, identify potential failure modes, and enforce non-functional constraints before implementation. It transforms initial concepts into robust, validated specifications by simulating formal critique and achieving consensus via a mandatory Decision Log.

Guides writing JavaScript inside n8n Code nodes, covering modes, data access patterns, webhook structure, return formats, helper utilities, and best practices for HTTP requests and DateTime handling.

Guides writing Python code inside n8n Code nodes, covering recommended use cases, helper data access patterns, Beta vs Native modes, and webhook/data handling rules so you can safely script workflow transformations with Python.

Operation-aware guidance for n8n nodes that clarifies required fields, property dependencies, and get_node detail modes, helping builders configure HTTP, Slack, and other integrations through progressive validation.

This skill generates Mermaid diagrams to create visual organizational tools specifically designed for neurodivergent individuals, particularly those with ADHD. It helps externalize executive functions, reducing cognitive overwhelm by breaking down complex tasks into compassionate, manageable micro-steps. The tool auto-detects signs of distress and supports multiple accessibility modes (e.g., colorblind-safe, monochrome), making it useful for project planning, decision mapping, and personal productivity tracking.