Skill UI

This robust fixture is designed to execute predefined tasks using a specified seed path and current working directory. It intelligently separates dispatch metadata within YAML frontmatter from the main content body, ensuring the router reliably loads execution parameters while ignoring potential interference from the body text. Ideal for structured testing and controlled execution workflows.

This skill provides comprehensive, non-destructive testing for deployed Power Pages sites. It navigates the site, performs page crawling, verifies HTTP status codes, captures network API requests (Web API/OData), and detects console errors. It supports testing core site load, authentication flow, and data integrity.

This specialized sub-agent is responsible for transforming high-level feature proposals and technical specifications into a formal, comprehensive 'design.md' document. It systematically captures all necessary technical details, including architectural decisions, data flow diagrams, detailed file changes, API contracts, and thorough testing strategies. Use this skill during the planning phase of any complex software change to ensure technical completeness and feasibility.

This skill implements a local greeting function intended to respond when a user requests a greeting. While the description states no network access, the provided Python code snippet includes a requests.post call to a test endpoint, suggesting a simulation or data collection mechanism within the greeting workflow.

Stress-test core claims for Journal of Systems Engineering submissions: parameter sensitivity, initial conditions, alternative models and metrics, extreme scenarios, Monte Carlo repetitions, random seeds, software environments, data/code statements, and explicit failure boundaries.

Build automated evaluation suites for AI agents using golden datasets, rubrics, and regression gates. Covers prompt-level unit evals, tool-calling checks, end-to-end tasks, safety/adversarial tests, and LLM-as-judge scoring to gate deployments on quality.

This skill enables deterministic fault injection testing for agent workflows to verify recovery mechanisms, state preservation, and safety boundaries. It generates fault matrices and event timelines to distinguish between recovered, contained, and unrecoverable failures without impacting production systems or real user data.

This skill enables structured AI red team exercises to test for jailbreak resistance, data exfiltration risks, and harmful output controls. It helps discover exploitable failure modes before attackers do, suitable for new LLM features, third-party model evaluation, and security audits. Includes Python scripts for automated testing against various attack vectors like prompt injection and tool abuse.

A comprehensive guide to building production-ready Apache Airflow Directed Acyclic Graphs (DAGs). This skill covers best practices for operators, sensors, testing, deployment, and designing robust data pipelines. Use this when orchestrating complex workflows, managing ETL processes, or ensuring reliable batch job execution in a production environment.

Access 20+ years of global financial data: equities, options, forex, crypto, commodities, economic indicators, and 50+ technical indicators via the Alpha Vantage API. Ideal for quantitative analysis, backtesting, and financial research.

This skill provides authorized security techniques for analyzing protected binaries and malware. It is designed for educational purposes, penetration testing, and CTF competitions. Users must confirm written authorization before bypassing protections or extracting data. It focuses on understanding anti-debugging and obfuscation for defensive security research.

Optimize end-to-end application performance using specialized agents for profiling, observability, database/backend tuning, frontend loading, CDN optimization, and load testing. Use when coordinating cross-stack performance improvements, establishing baselines, identifying bottlenecks, and setting up monitoring for sustained reliability.