Skill UI

A formal framework designed for evaluating AI-assisted code generation sessions. It implements Development Oriented Evals (EDD) principles, allowing users to define capability and regression criteria. The system supports multiple evaluation types—code-based, model-based, and human review—and tracks reliability using advanced metrics like pass@k, ensuring robust quality control for AI agents.

Flox is a declarative, Nix-based environment manager designed to create perfectly reproducible development environments. It handles system-level dependencies (like compilers, databases, and native libraries) and ensures that complex toolchains across multiple languages (Python, Node.js, Go, etc.) function identically across macOS and Linux. Ideal for solving 'works on my machine' issues and onboarding new team members instantly.

A comprehensive skill designed to systematically diagnose why an AI agent fails a specific task within the GAIA benchmark. It guides the user through loading the question trace, classifying the failure mode (e.g., Reasoning Miss, Tool Gap), and proposing targeted fixes. Use this tool when you need to root-cause a performance regression or an incorrect answer to resubmit a corrected agent.

GateGuard is a mandatory pre-tool-use hook designed to significantly enhance the reliability and safety of LLM-generated code and actions. Instead of relying on self-evaluation, it forces the model to perform concrete, verifiable investigations—such as listing all imported files, checking data schemas, or detailing rollback procedures—before any write or destructive command execution. It establishes a three-stage gate (Deny, Force, Allow) to prevent hallucination and ensure context awareness in complex coding environments.

A comprehensive framework for creating structured, clean, and highly accessible design systems. It defines foundational constraints, typography scales, color tokens, and component-level rules, ensuring consistency and usability across engineering and design teams. Focuses on achieving WCAG 2.2 AA compliance and implementation readiness.

This advanced workflow is designed to generate comprehensive, fact-checked research reports on any complex topic. It systematically performs fan-out web searches across multiple defined angles, fetches multiple sources, and employs a rigorous adversarial verification system (3-vote) to validate claims. The final output is a highly cited, synthesized report, ideal for academic or critical business research.

This skill runs an automated evolution process designed to systematically optimize the seven core policy surfaces of an AI agent harness (e.g., planner, contextBuilder, reviewer). By mutating these policies and scoring the variants in a sandbox, it identifies crucial performance improvements without requiring expensive foundation model retraining. It is ideal for empirical configuration tuning and establishing optimized baselines.

An automated verification system designed for critical healthcare application deployments (EMR/EHR). This harness enforces stringent patient safety standards by running multiple mandatory test gates, including Clinical Decision Support System (CDSS) accuracy, Protected Health Information (PHI) leakage prevention, and data integrity checks. A single failure in critical gates automatically blocks deployment, ensuring regulatory compliance and optimal patient safety in the CI/CD pipeline.

A comprehensive pipeline designed for Laravel projects to ensure code quality and stability before deployment. It systematically executes environment checks, linting, static analysis, full testing with coverage, security audits, migration validation, and cache preparation. Essential for robust CI/CD pipelines and pre-Pull Request validation.

A comprehensive, end-to-end methodology designed for software engineers and AI agents to safely and systematically integrate machine learning models into existing non-ML codebases. It guides users through critical phases, including problem framing, data readiness, architectural decoupling (via APIs/services), baseline model implementation, and final MLOps pipeline setup.

Use the Monitor tool to achieve real-time observability of swarm events instead of relying on periodic polling. This utility streams comprehensive NDJSON events, including agent spawns, task completions, memory writes, and health checks. It is designed for developers and engineers needing immediate insight into the operational status and health of a distributed system.

This advanced orchestration tool streamlines the process of building a Minimum Viable Product (MVP). By ingesting high-level design documents (SDD/PRD), it automatically plans thin, end-to-end vertical slices. The system then scaffolds, executes TDD implementation, and manages gated commits, transforming theoretical specifications into a functional, reviewable starting point, dramatically accelerating initial development cycles.