Skill UI

This pattern defines a robust, continuous loop structure for autonomous agents. It integrates crucial components like quality gates, evaluation harnesses, and explicit recovery controls. It guides complex workflows by defining decision paths (e.g., PR control, RFC decomposition) and includes strategies to mitigate common failure modes such as infinite loop churn or cost drift, ensuring measurable progress in autonomous systems.

This skill provides a granular, session-by-session view of total accumulated costs. It lists metrics such as start time, message count, top model, and total cost for every recorded conversation. This is ideal for identifying which specific sessions consumed the most resources, which is crucial for project retrospectives and evaluating the sustainability of current session patterns.

This skill analyzes Git diffs to assess risk levels, recommend reviewers, and classify changes. It helps developers prepare Pull Requests, review large or cross-module changes, and evaluate security risks before merging. Use it with specific branches or PR references to get comprehensive statistics and file-level risk assessments.

Codified expertise for electricity and gas procurement, tariff optimization, demand charge management, renewable PPA evaluation, and multi-facility energy cost management. Use for running RFPs, analyzing tariffs, mitigating demand charges, assessing PPAs, building budgets, and responding to market volatility.

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.

A comprehensive, library-agnostic checklist covering best practices for Flutter and Dart applications. It guides developers on architectural principles, state management patterns (BLoC, Riverpod, etc.), Dart idioms, performance optimization, and clean code principles, making it invaluable for code reviews.

This skill provides a detailed, side-by-side comparison of advanced LLM agent evaluation frameworks, such as ruflo and HAL. It helps researchers and developers identify capability gaps—including real code execution, full web browsing, and structured file parsing—and prioritize architectural improvements for robust agent benchmarking and performance tracking.

Guides users through the entire end-to-end process of running the GAIA benchmark. It covers environment validation, cost estimation, model execution, and generating a signed, HAL-compatible submission package for leaderboards. This ensures high integrity and reproducibility for model performance evaluation.

A sophisticated multi-agent development harness inspired by GANs. It separates product planning, code generation, and rigorous evaluation into three distinct agents (Planner, Generator, Evaluator). This creates an adversarial feedback loop, allowing projects to iteratively reach professional, production-grade quality far beyond what a single-agent workflow can achieve. Ideal for complex, full-stack applications.

A utility for scaffolding and verifying fixed evaluation corpora (bench suites). It generates deterministic test suites from existing repositories, decoupling the evaluation process from the repo's natural test suite. This ensures consistent fitness scoring when running evolution pipelines across different commits or forks.

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.

This skill facilitates the crucial process of sharing learned intelligent patterns across isolated projects or machines using the InterPlanetary File System (IPFS). It allows users to publish a project's accumulated knowledge base to a decentralized network and later fetch, apply, and merge these patterns into new or existing projects. This is invaluable for bootstrapping new applications with prior knowledge or consolidating learnings across a large monorepo.