Skill UI

This skill provides comprehensive guidance on optimizing operational costs on the Apify platform. It covers analyzing Compute Units (CU) usage, managing proxy consumption (residential vs. datacenter), and optimizing scraping logic (memory, concurrency) to ensure efficient and cost-effective web scraping workflows.

This meta-skill acts as a comprehensive Learning Science Coach, teaching users *how* to learn effectively rather than just *what* to study. It draws upon advanced cognitive science principles—including Spaced Repetition, Active Recall, Metacognition, and Bloom's Taxonomy—to diagnose learning gaps, optimize study methods, and build structured, long-term memory retention systems. Ideal for students, professionals, and lifelong learners seeking systematic methods to accelerate knowledge acquisition.

This comprehensive guide details how to optimize Apify Actors for maximum efficiency, cost-effectiveness, and reliability. Learn to select the appropriate crawler (e.g., Cheerio, Playwright), tune concurrency limits, manage memory consumption, and implement robust proxy rotation strategies for diverse web scraping workloads, ensuring your scraping tasks are fast and stable.

This skill provides advanced strategies for optimizing Canva Connect API performance. It covers implementing robust caching mechanisms (in-memory and Redis) to reduce redundant calls, handling pagination using continuation tokens, and implementing smart polling with progressive backoff for asynchronous operations like exports. It also details connection pooling and concurrency management to maximize request throughput and minimize latency for stable Canva integrations.

A persistent memory kit designed for Claude AI agents. It maintains deep context across multiple sessions and projects using a two-layer architecture (hot cache and knowledge wiki). Features include safety hooks, multi-project context isolation, and a /close-day command for daily synthesis, ensuring agents remember complex information and continuously learn.

This guide provides production-ready patterns for using the @clickhouse/client library in Node.js. It covers critical, real-world scenarios such as safe typed queries, streaming large data inserts (with backpressure handling), robust batch operations with retries, and streaming SELECT queries for low memory consumption. It also includes best practices for comprehensive error handling and connection lifecycle management, ensuring stable and scalable ClickHouse integrations for data pipelines.

This skill provides comprehensive observability for CoreWeave's GPU-intensive workloads running on Kubernetes. It monitors critical operational metrics, including GPU utilization, memory usage, inference latency (p99), and job completion rates. Use it for setting up DCGM metrics dashboards, configuring proactive alerts for underutilization or Out-Of-Memory (OOM) conditions, and ensuring high reliability for AI/ML deployments.

A universal infrastructure for automatically evolving and optimizing AI agents across any domain. Using LLM-driven mutation and iterative solve-observe-evolve cycles, it enhances critical components like prompts, skills, and memory by benchmarking performance against measurable datasets, enabling the creation of self-improving AI systems.

This skill converts complex technical descriptions, such as system architectures, data flow diagrams, flowcharts, and sequence diagrams, into professional, production-quality SVG diagrams. It supports various technical models, including Agent and Memory architectures, and exports the final output as high-resolution PNG files for seamless documentation and presentation use.

This skill helps users create specialized 'steering documents' or project memory for highly specific domains (e.g., API standards, testing strategies, security patterns). By analyzing the existing codebase and following predefined architectural principles, it synthesizes concise, actionable guides that capture technical patterns, best practices, and domain-specific rules, ensuring project consistency and knowledge retention.

A comprehensive guide to ensuring robust state management for LangGraph agents. This skill addresses common checkpointing pitfalls (like missing thread_id or non-JSON serializable state) and details best practices for implementing reliable state persistence using MemorySaver or PostgresSaver. It covers thread discipline, schema migration, and time-travel debugging for production-ready applications.

A tool designed for persistent context management within AI coding sessions. Memory Kit solves the problem of context loss that occurs during compaction or session restarts by saving, loading, updating, and sharing critical session state to a dedicated `MEMORY.md` file. Key functions include creating snapshots of goals and decisions, syncing context across team members via Git, and auditing/pruning stale entries, ensuring continuous workflow and knowledge retention.