Skill UI

Performs comprehensive, two-layer validation on generated plans. Layer 1 executes instant structural checks (format, dependencies, compliance) while Layer 2 triggers specialist agents (e.g., security, DB, performance) based on plan content. The system forces resolution of all identified issues before allowing execution, supporting auto-fixes and guided human input.

This skill provides a comprehensive, 4-phase workflow for managing and reviewing a pull request backlog. It automatically audits open PRs, classifying them by size, staleness, overlap, and CI status. Users can then initiate deep code reviews, generate comment drafts, and set up local worktrees for systematic maintenance and quality assurance.

A comprehensive, multi-step framework for conducting systematic QA testing on web applications. This guide covers scope detection (diff-aware), tiered testing depth (Quick, Standard, Exhaustive), detailed issue taxonomy (Functional, Visual, UX, etc.), structured bug documentation, and the critical fix-and-verify loop, ensuring high code quality throughout the development cycle.

This skill guides a thorough, adversarial review of development plans across four key dimensions: Architecture, Code Quality, Testing, and Performance. It forces explicit consideration of trade-offs, risks, and user approval before any code is written, ensuring robust and well-engineered solutions for complex systems.

A sophisticated, multi-agent system designed to perform deep, comprehensive code reviews on pull requests. It covers core elements like code quality, functionality, security vulnerabilities, and testing coverage. Advanced features include detecting scope drift, enforcing SOLID principles, identifying DRY violations, and providing anti-hallucination safeguards for maintain high software integrity.

This command inspects the native code execution sandbox environment. It reports on platform compatibility (e.g., bubblewrap, Seatbelt), active security configurations (auto-allow status, filesystem policies, network allowlists), and details recent security violations. Use it to audit the execution environment before running autonomous workflows.

This protocol provides a systematic, multi-step diagnostic approach to determine if a command failure (e.g., permission denied, network issues) is genuinely due to sandbox restrictions or is caused by environmental or measurement errors. It includes eight critical checks—such as verifying shell scope and reading real exit codes—to eliminate false positives before filing a blocker report.

This technique segments unstructured clinical documents (such as HPI, PMH, and A&P sections) into contextually rich, canonical chunks. This is crucial for improving the precision of downstream NLP tasks like Named Entity Recognition (NER) and de-identification. By identifying and normalizing headers and mapping them to LOINC codes, the system ensures that the source context (e.g., historical vs. active) is maintained, leading to significantly more accurate results.

This skill converts free-text radiology narratives (CT, MRI, X-ray, etc.) into structured, machine-readable data. It automatically identifies and segments key report sections (Technique, Findings, Impression) and extracts critical clinical details such as anatomy, measurements, laterality, BI-RADS/Lung-RADS scores, and follow-up recommendations. It is crucial for building structured medical records and decision support systems.

This skill manages the complex, multi-step workflow for updating the company's threat intelligence database. It delegates the core research and content updates to the dedicated AgentSec system. The process involves reading AgentSec's source material, executing rigorous testing in an isolated workspace, synchronizing the validated security feed, and finally ensuring data integrity by validating the updates across the guide and landing mirrors.

This utility is essential for developers needing to ensure that recent code modifications function as intended. By running the application within a verification environment, users can quickly validate that the changes meet all expected behaviors, maintaining system stability and quality assurance before deployment or merging.

A comprehensive guide detailing advanced, authorized techniques for Active Directory security testing and red teaming. It covers critical attack vectors such as Kerberos exploitation, BloodHound path analysis, NTLM relay, and domain privilege escalation. Designed for security professionals to systematically map and exploit domain weaknesses.