Security & Testing Agent Skills

ast-grep

Performs AST-based code search, linting, and structural refactoring across multiple programming languages.

Autonomous Bug Diagnosis & Root Cause Analysis

Automates structured debugging workflows and root cause analysis using evidence-based protocols and comprehensive verification.

TUnit Test Runner

Executes and manages TUnit tests with Playwright integration to verify Blazor component functionality and accessibility.

Skill Reviewer

Performs systematic 14-phase audits of Claude Code skills to ensure technical accuracy, documentation standards, and production readiness.

GitHub Copilot MCP Integration

Enables advanced codebase analysis and specialized AI development tools by bridging Claude with the GitHub Copilot CLI.

Running Performance Benchmarks

Executes comprehensive performance audits, load tests, and regression analysis for API endpoints to ensure system stability and optimization efficiency.

Infrastructure Testing & Security

Validates infrastructure configurations and deployments through automated security scanning, cost analysis, and post-deployment verification.

Code Reviewer

Automates comprehensive code audits using research-backed security standards, performance pattern detection, and automated quality enforcement.

Fractary Artifact Validator

Automates the validation of Claude agents, skills, and commands against standardized architectural and formatting requirements.

Architecture Validator

Validates Claude Code project architectures against Fractary standards for Manager-as-Agent and Director-as-Skill patterns.

Workflow Validator

Validates Claude agentic workflows to ensure compliance with architectural patterns and the Manager-as-Agent principle.

Faber Evaluate

Automates the testing and quality review phase of the FABER workflow to ensure code meets specifications before release.

Spec Validator

Validates code implementations against technical specifications to ensure requirement coverage, test compliance, and documentation accuracy.

Regression Testing Orchestrator

Automates the evaluation and implementation of regression tests following bug fixes to ensure long-term code stability.

Solidity Security

Implements secure smart contract patterns and audits Solidity code to prevent common blockchain vulnerabilities and exploits.

Claude Permission Manager

Automates the configuration of granular Claude Code permissions to enable seamless Git and GitHub operations while blocking destructive commands.

Bats Shell Testing Patterns

Provides comprehensive guidance and implementation patterns for writing robust unit tests for shell scripts using the Bash Automated Testing System.

Auth Implementation Patterns

Implements secure authentication and authorization systems using modern patterns like JWT, OAuth2, and RBAC.

E2E Testing Patterns

Master end-to-end testing with Playwright and Cypress to build reliable, bug-free web applications and automated test suites.

Python Testing Patterns

Implements professional testing strategies for Python applications using pytest, advanced mocking, and test-driven development best practices.

Kubernetes Security Policies

Implements production-grade Kubernetes security configurations including NetworkPolicies, Pod Security Standards, and RBAC to harden cluster environments.

Web3 Smart Contract Testing

Develops and executes comprehensive test suites for Solidity smart contracts using Hardhat and Foundry frameworks.

Ark Chainsaw Testing

Executes and scaffolds end-to-end Ark resource tests using the Chainsaw framework and mock-LLM configurations.

Global Security

Guides AI-assisted coding to adhere to established global security standards and best practices.

Maven Build and Test Strategy

Orchestrates parallel Maven builds and intelligent test execution for complex Java and Scala projects.

Root Cause Tracing

Systematically traces software bugs backward through the call stack to identify and resolve original triggers at their source.

GDPR Auditor

Analyzes codebases and system documentation to identify GDPR compliance gaps, data protection risks, and privacy policy inconsistencies.

Scale Game Problem Solving

Validates architectural decisions by simulating extreme scaling scenarios to identify hidden bottlenecks and system failures.

Semgrep Rule Creator

Generates custom Semgrep rules to detect security vulnerabilities and logic bugs within source code.

Address Sanitizer

Detects memory safety vulnerabilities and errors in C and C++ programs using AddressSanitizer instrumentation.