Skill UI

This discipline establishes a portable, framework-agnostic layer for ensuring type safety at the network edge of any React or React Native application. It mandates a single, typed API client to wrap all network fetching, guaranteeing that raw wire JSON is immediately parsed into trusted, domain-specific types or standardized error objects before entering the application state. This pattern drastically reduces runtime errors and enhances code robustness.

A robust protocol designed for multi-agent collaboration on long-running projects. It simulates a self-optimizing city where diverse AI agents (citizens) interact using decentralized markdown files (The Register, Contracts, Chronicle). This framework enables cross-vendor optimization, dynamic work routing, and constitutional evolution without requiring a centralized server or specific runtime environment.

This skill performs a comprehensive, read-only, multi-agent review of a git diff or file scope. It launches four specialized sub-agents—covering Regression, Security, Performance, and Contracts—in parallel. The main agent then aggregates, filters, and summarizes critical findings, ensuring the code change is robust, secure, and maintainable. Ideal for pre-commit or Pull Request review workflows.

This comprehensive guide outlines best practices for building reliable and robust AI agent harnesses. It covers optimizing action spaces, defining structured tools, managing observation formats, and implementing essential error recovery contracts. Use these principles to dramatically improve agent completion rates, manage context budgets effectively, and transition AI prototypes into stable, production-grade autonomous systems.

A comprehensive guide detailing security patterns and audit checklists for Automated Market Maker (AMM) smart contracts in DeFi. Covers critical vulnerabilities such as flash loans, slippage, reentrancy attacks, price manipulation, and integer overflow/underflow. Essential for reviewing major DeFi protocols like Uniswap.

This skill guides users through Phases 2 (Pseudocode Design) and 3 (Architecture Design) of the SPARC methodology. It translates high-level specifications into detailed technical blueprints, covering algorithm pseudocode, module boundaries, API contracts (using DDD patterns), and infrastructure planning, ensuring a robust plan before writing production code.

This skill prevents AI coding agents from generating generic interfaces by leveraging over 800,000 real web and iOS screens. It helps define design contracts, cover required states, and enforce quality gates during design, implementation, or review. Compatible with agents like Cursor, Copilot, and Claude Code, it ensures product-specific UIs grounded in actual user experience rather than hallucinated patterns.

This skill guides art historians on gathering, weighing, and citing non-visual, documentary, and material evidence for academic articles. It covers citing primary sources (archives, contracts), reconstructing provenance chains, interpreting technical reports, and ensuring that all scholarly claims are rigorously traceable to verifiable sources rather than mere assertion.

A comprehensive guide for revising empirical papers submitted to top-tier Software Engineering conferences (like FSE). This framework emphasizes structuring the paper around a clear SE contribution, treating research questions as contracts, backing every claim with proportional evidence, and rigorously arguing threats to validity, rather than merely listing them. It ensures the paper maintains maximum academic rigor and focus.

This guide provides rigorous guidelines for structuring and validating experimental results in computer architecture papers. It covers essential aspects like declaring simulation methodology contracts, ensuring result reproducibility through manifest files, selecting representative workloads, and performing detailed attribution and sensitivity analyses to distinguish true architectural gains from modeling artifacts.

A comprehensive guide for authors revising technical papers for top-tier conferences like ISSTA. It details the necessary structure, emphasizing strict scope definition, establishing clear evaluation contracts (subjects, baselines, metrics), pairing every claim with concrete evidence, and adhering to specialized review discipline.

This guide details how to assemble a comprehensive, reproducible replication package for academic manuscripts, especially in fields relying on complex institutional data (e.g., court records, contracts). It mandates creating a one-command master script, documenting the entire data pipeline from raw sources to final exhibits, and providing detailed protocols for hand-coded variables and data provenance. The goal is to ensure that any researcher can perfectly reproduce every finding.