Skill UI

Apify Actorization is a process that transforms existing, standalone software or scripts (like CLI tools) into standardized, reusable serverless applications called Actors. Actors are packaged as Docker images, accepting structured JSON inputs and producing structured JSON outputs. This skill guides developers on migrating projects to the Apify platform, ensuring compatibility, and enabling scalable, event-driven data processing pipelines.

A comprehensive guide and methodology for identifying, measuring, and fixing performance bottlenecks across the entire stack. This skill covers optimizing database queries (e.g., N+1 problems, missing indexes), improving API efficiency (caching, parallel processing), and enhancing frontend performance (memoization, code splitting, image optimization). It emphasizes the critical 'Measure First' principle to ensure all optimizations are data-driven and effective.

Process videos, audio, images, and documents on Transloadit’s cloud using 86+ robots to encode formats, generate thumbnails, resize/watermark, run OCR, speech-to-text, moderation, and chain multi-step pipelines for scalable media automation.

Modal is a serverless cloud platform for running Python code on demand, including GPU-accelerated AI/ML workloads. Use for deploying models, serving web APIs, batch processing, and scaling Python applications to cloud containers with automatic scaling from zero to thousands of instances. Supports custom container images, persistent storage, and sub-second cold starts for low-latency inference.

A comprehensive guide for debugging complex Claude integration issues beyond basic error handling. It covers advanced patterns such as managing inconsistent outputs (temperature control), validating tool use calls, recovering from streaming connection drops, handling max_tokens truncation, and correctly processing image/vision inputs. Essential for building robust, production-grade AI applications with Anthropic's API.

This guide outlines production-ready patterns for integrating SerpApi into robust search services. It covers essential best practices, including defining typed result interfaces for type safety, implementing LRU caching to conserve API credits, and building multi-engine abstractions to handle various search types (web, news, images). It also demonstrates asynchronous search processing for non-blocking operations.

A comprehensive toolkit designed for reading, reviewing, and programmatically creating high-fidelity PDF documents. It supports content extraction from existing PDFs, generating professionally formatted reports, and validating visual quality through rendering to PNG images. Ideal for tasks requiring precise typography, layout integrity, and polished final deliverables.

A comprehensive guide and methodology for identifying, measuring, and fixing performance bottlenecks across the entire stack. This skill covers optimizing database queries (e.g., N+1 problems, missing indexes), improving API efficiency (caching, parallel processing), and enhancing frontend performance (memoization, code splitting, image optimization). It emphasizes the critical 'Measure First' principle to ensure all optimizations are data-driven and effective.

Privacy Mask is a CLI utility for detecting and redacting sensitive PII in screenshots and images locally. It supports various detection engines including regex and NER to identify IDs, financial data, and API keys. All processing is offline to ensure data security. Users can run dry-runs before masking. Ideal for debugging and sharing images without exposing private credentials or secrets.

This skill enables adding visual effects like bloom, depth of field, and color grading to Three.js 3D scenes. It utilizes EffectComposer and custom shaders for screen-space enhancements, suitable for final image rendering optimization and artistic styling in web-based 3D applications.

Xberg is a document intelligence library supporting 107 formats including PDF, Office, and images. It extracts text, tables, and metadata using OCR and chunking. Available for Python, Node.js, Rust, and CLI. Ideal for developers building document processing applications with multi-language bindings and structured output.

This skill provides guidance on extracting tabular data from PDFs, spreadsheets, and images using the xberg tool. It covers layout-aware table detection, selection of table models (TATR, SLANet variants), output formats (Markdown or JSON), and known limitations. Useful for processing financial statements, invoices, and scientific tables.