Skill UI

A comprehensive guide for assessing the scope and significance of high-quality, cross-disciplinary research. This skill helps authors determine the optimal publishing venue—whether it should be PNAS Nexus, flagship PNAS, or a specialized field journal—by evaluating how broadly the findings resonate across biological, physical, social, and engineering sciences. It is crucial for submissions and for judging transfer opportunities following a PNAS decline.

PR code reviews identify decay risks, design smells, and maintainability issues. Uses findings structured as Symptom, Source, Consequence, and Remedy based on twelve classic engineering books. Applies the Iron Law to every finding. Outputs a standardized report for software engineering tasks requiring deep code quality analysis.

This skill reviews test suite quality using established testing literature to identify brittleness, mock abuse, unclear fixtures, weak assertions, slow feedback, and maintenance risks. It diagnoses structural problems in existing test suites based on classic engineering books like xUnit Test Patterns and The Art of Unit Testing, ensuring robust and maintainable testing practices.

Quality-gate review tool for reverse-engineering or assessment case packages. Verifies scope readiness, Evidence-to-Finding-to-Path traceability, work-item coverage, timeline consistency, and artifact hashes before report delivery. Ensures defensible handoff for security analysis, forensics, CTF, or authorized security cases without modifying targets. Supports Markdown or JSON output formats for CI integration.

This skill specializes in code refactoring using clean code principles and SOLID design patterns. It helps analyze and refactor code to improve quality, maintainability, and performance. Ideal for cleaning large codebases, removing duplication, and preparing for new features while aligning with modern software engineering best practices.

Expert data engineer specializing in scalable data pipelines, modern data warehouses, lakehouse architectures, and real-time streaming. Proficient in Apache Spark, dbt, Airflow, Kafka, and cloud-native platforms (AWS, Azure, GCP). Focuses on reliable, performant, and cost-effective data solutions with strong emphasis on data quality and governance.

Expert guidance for designing scalable batch and streaming data pipelines, covering ETL/ELT, orchestration, dbt transformations, data quality, lakehouse storage, monitoring, and cost optimization.

This comprehensive workflow covers the entire database lifecycle, including design, implementation, optimization, migration, and data engineering. It supports SQL and NoSQL technologies like PostgreSQL and MongoDB. Key phases include schema design, ORM setup, query performance tuning, data pipeline creation, quality assurance, and operational management. Ideal for developers and data engineers managing modern data platforms.

This skill guides users in designing and reviewing polished user interfaces with a focus on animation, interaction feedback, component craftsmanship, and accessibility. It helps implement motion reviews and ensure keyboard accessibility and reduced-motion behavior. Suitable for frontend development tasks requiring high-quality UI polish and adherence to safety boundaries.

This skill enables the creation of robust evaluation frameworks for AI agent systems. It is used for systematically testing agent performance, validating context engineering choices, and measuring improvements over time. The approach accounts for non-determinism and multiple valid paths, utilizing multi-dimensional rubrics, LLM-as-judge methods, and human evaluation to ensure quality gates and catch regressions before deployment.

This skill provides comprehensive techniques for optimizing prompts used with any Large Language Model (LLM). It teaches proven methodologies—including Role definition (R), Context setting (S), Constraints (C), Instructions (I), and Templates (T)—to transform vague inputs into precision-engineered instructions. Users can reliably achieve structured JSON output, implement Chain-of-Thought reasoning, reduce hallucinations, and minimize token usage, ensuring consistent and high-quality results across different AI platforms.

Squirrel is an advanced, full-cycle AI coding skill designed to guide software development from concept to production. It automatically detects the current project state (greenfield, in-progress, or mature) and adapts an 8-phase engineering pipeline. This comprehensive workflow covers planning, building, rigorous testing, bug hunting, code polishing, documentation, and deployment readiness, ensuring high-quality, maintainable results.