Skill UI

This skill guides users through building a minimal yet comprehensive working application on the Replit platform. It demonstrates how to integrate and use core platform services such as the built-in Key-Value Database, Object Storage for file handling, user Authentication, and standard web frameworks (Express/Flask). Use this guide when starting a new Replit project or when learning the foundational infrastructure services provided by the platform.

This skill provides a comprehensive, expert guide to the entire reverse engineering lifecycle. It covers advanced techniques for binary analysis, including static analysis (disassembly, metadata extraction, control flow mapping) and dynamic analysis (API hooking, memory tracing). Mastery includes utilizing industry-leading tools such as IDA Pro, Ghidra, radare2, and specialized frameworks like pwntools and angr. The methodology is structured for secure research, CTF challenges, and vulnerability assessment, emphasizing best practices and ethical use.

Provides a comprehensive guide and framework for executing end-to-end (E2E) tests. It simulates real user interactions across the entire application stack, covering browser UI, API calls, and database operations. The guide details best practices like implementing the Page Object Model (POM), configuring multi-browser environments (Playwright, Cypress, Selenium), and establishing robust error handling mechanisms to ensure high application stability and quality.

This comprehensive guide details the expertise needed for a Senior Data Engineer. It covers building, optimizing, and governing scalable data pipelines and robust ETL/ELT systems using modern tools like Spark, Kafka, Airflow, and dbt. Includes decision frameworks for architecting data solutions (Batch vs Streaming, Lakehouse vs Warehouse) and implementing advanced data modeling patterns.

A comprehensive guide detailing the foundational principles of modern SEO. It covers critical areas such as E-E-A-T framework, Core Web Vitals, technical SEO implementation (e.g., sitemaps, structured data), and advanced content quality strategies. This skill helps users build sustainable, high-trust online visibility by focusing on user experience and search engine understanding, not temporary hacks.

A comprehensive skill to identify, analyze, prioritize, and track technical debt across large codebases. It provides three interconnected tools: a Debt Scanner, a Debt Prioritizer (using cost-of-delay frameworks), and a Debt Dashboard. This system helps engineering teams make data-driven decisions to balance new features with necessary maintenance and refactoring work, ensuring the long-term sustainability of software systems.

Test Data Builder Guidance auto-activates when you ask about test data strategies, best practices, or configuration for automation frameworks, delivering step-by-step patterns, production-ready samples, and validation against common standards.

This skill automates the creation of comprehensive test suites for any codebase. Utilizing advanced AI capabilities, it analyzes function signatures, automatically identifies potential edge cases, generates meaningful assertions, and produces necessary mock data and fixture files. It is essential for developers needing robust unit tests, increasing code coverage, and adopting Test-Driven Development (TDD) workflows across various frameworks like Jest or pytest.

LaminDB is a Python-driven open-source framework for managing biological datasets, ensuring traceable, reproducible, FAIR data through lineage tracking, schema validation, ontology annotation, workflow integration, and lakehouse-style querying.

Produces 50+-page market research dossiers with consulting-style LaTeX formatting, deep data lookups, strategic frameworks, and automated visual assets for investment and planning briefs.

This skill runs the ScholarEval framework to score academic submissions across problem setting, methodology, data, analysis, writing, and references, providing structured strengths/weaknesses, numeric ratings, and guidance for visualizing the evaluation.

Probabilistic deep-learning framework built on PyTorch for single-cell omics; handles batch correction, integration, multimodal and spatial data, differential expression, and transfer learning with unified APIs.