Skill UI

A sophisticated, multi-agent workflow designed for comprehensive code reviews of GitHub Pull Requests. It performs deep analysis by simulating multiple specialized perspectives, checking PR eligibility (handling draft/merged status and follow-ups), and managing large or complex diffs. The skill synthesizes high-signal, actionable feedback by integrating parallel reviewers' findings with historical PR discussions, ensuring robust code quality before merging.

A comprehensive guide for submitting high-quality replication packages for academic journals like the American Economic Journal (AEJ: Micro). This package covers two essential components: self-contained, verifiable proofs for theoretical claims (the Proof Appendix), and a fully reproducible code and data deposit (the Code/Data Repository). It ensures that all numerical results, simulations, and empirical findings can be regenerated by the journal's editor, maintaining the highest standards of scientific transparency.

This guide provides comprehensive best practices for preparing supplementary materials for major academic conferences like AISTATS. It details the proper structure and handling of appendices, mathematical proofs, code archives, and additional data tables, ensuring that the main paper remains fully understandable even if the supplementary material is ignored by reviewers. Essential for publishing high-quality, robust research.

This skill automates the entire GitHub Pull Request (PR) review cycle, specifically targeting Copilot Code Review comments. It runs a robust loop: automatically triggering reviews, triaging open threads, dispatching parallel fixes that adhere to repo conventions, committing changes, and resolving comments. It continues iterating until the PR is deemed clean and ready for merge, minimizing manual effort and ensuring high code quality.

This guide details how to prepare high-quality, verifiable system artifacts (code, data, hardware) for academic conferences like EuroSys. It outlines the requirements for achieving multiple evaluation badges—Available, Functional, and Reproduced—by ensuring the artifact is self-contained, portable, and verifiable by an external evaluator without prior context.

A comprehensive, step-by-step preflight checklist designed for authors submitting manuscripts to top-tier scientific journals. It ensures thorough validation across all required components, including the mechanistic narrative, structural data integrity, statistical rigor (QSA), figure quality, and proper data/code deposition (DOIs). It serves as the ultimate gatekeeping mechanism before final submission.

This comprehensive preflight checklist is designed for authors preparing manuscripts for top academic journals. It guides users through crucial submission requirements, including double-blind anonymization, adherence to strict length norms (under 50 pages), structuring the contribution case, and ensuring compliance with modern transparency policies regarding data, code, and AI usage. Use it to maximize submission quality and minimize desk rejection risk.

Seaborn is a high-level Python visualization library designed for creating publication-quality statistical graphics. It facilitates dataset-oriented plotting, multivariate analysis, and complex statistical visualizations (like KDEs, distributions, and relationships) directly from Pandas DataFrames with minimal code. It builds upon Matplotlib to provide semantic mapping and statistical awareness.

Provides a comprehensive, quantitative auditing system for AI agents, skills, and commands. It evaluates these components against industry best practices using a multi-criteria weighted scoring model and assign a production readiness grade (A-F). Ideal for validating complex AI systems before deployment, identifying gaps, and ensuring robust, maintainable code.

This tool provides a comprehensive, multi-faceted audit of a codebase's health. It scores the project across critical areas like security vulnerabilities, exposed secrets, dependency risks, and structural integrity. Ideal for senior engineers performing pre-commit or pre-release quality assessments to identify weak spots and generate a prioritized remediation plan.

An autonomous system designed to continuously improve code quality by scanning codebase metrics. It functions as an agent, proposing mechanical code changes, executing them, and committing only if defined metrics improve. It supports multiple modes (Scan, Scaffold, Run) for systematic, data-driven codebase refactoring.

This tool provides a unified interface to run test suites for various programming stacks (Python, Node.js, Rust) within a CI/CD pipeline. It automatically detects the project's environment (by checking lock files or config) and executes the appropriate testing framework (e.g., pytest, vitest, cargo test), ensuring consistent code quality checks regardless of the underlying language. Ideal for pre-commit or CI/CD integration.