Skill UI

This skill provides comprehensive web browser automation capabilities for agents. It utilizes AI-optimized snapshots, reducing context size by 93% by using element references instead of full DOM. Functions include navigation, interactive element extraction, form filling, data scraping, and state management across multiple isolated sessions. Ideal for complex web testing and data extraction workflows.

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.

This advanced pipeline orchestrates complex feature development based on Request for Comments (RFCs). It breaks down monolithic changes into small, independently verifiable work units, managing dependencies through a Directed Acyclic Graph (DAG). It includes multiple quality gates, dedicated unit testing, and a safe merge queue to ensure robust integration and controlled deployment.

A comprehensive guide for authors submitting to highly demanding journals like JFE. It teaches authors how to anticipate and pre-empt common methodological objections (endogeneity, multiple testing, fragility) before submission, and how to strategically plan responses during the review process. This ensures the manuscript is robust and maximizes acceptance chances.

This advanced methodology builds an evidence-linked causal chain from a localized fault to an actionable systemic root. It moves beyond simple proximate causes by requiring counterfactual testing, verifying multiple independent pathways, and prescribing countermeasures that eliminate enabling conditions, ensuring true recurrence prevention.

A rigorous methodology for debugging complex anomalies or incidents when multiple plausible causes exist. It guides the user to enumerate competing, falsifiable hypotheses and prioritizes running the cheapest, most discriminating observation first. By iteratively eliminating hypotheses and preferring the least-assumptive survivor, it systematically localizes the root cause efficiently.