Security & Testing Claude 技能

Unit Testing Patterns

Implements high-performance, isolated unit testing patterns using the AAA methodology across TypeScript and Python environments.

Advanced LLM Guardrails & Safety

Implements comprehensive safety layers for LLM applications using NeMo, Guardrails AI, and red-teaming validation patterns.

AI Defense-in-Depth Security

Implements an 8-layer security architecture to harden AI pipelines and LLM integrations against vulnerabilities and data leaks.

OrchestKit Health Diagnostics

Diagnoses and validates the health of OrchestKit installations to ensure skills, agents, and hooks are correctly configured.

E2E Testing with Playwright

Automates end-to-end browser testing using Playwright 1.58+ with AI-assisted test generation and self-healing capabilities.

PII Masking & Privacy Patterns

Protects sensitive user data by implementing automated PII detection and redaction across LLM observability pipelines and logs.

Testing Standards Enforcer

Enforces rigorous testing standards and best practices by automatically validating test structure, naming, and coverage during the development process.

PII Masking Patterns

Protects sensitive user data in LLM observability pipelines by detecting and masking PII using regex, Microsoft Presidio, and LLM Guard.

Defense-in-Depth Security

Implements a robust 8-layer security architecture to harden AI pipelines and protect LLM integrations from end-to-end vulnerabilities.

Comprehensive Code Verification

Verifies code implementations using parallel specialized agents and nuanced grading to ensure production readiness and security.

Web Application Testing with Playwright

Automates the end-to-end testing lifecycle using AI agents to plan, generate, and self-heal Playwright test suites.

Advanced LLM Guardrails & Safety

Implements production-grade LLM safety layers using NeMo Guardrails, Guardrails AI, and adversarial red-teaming to prevent hallucinations, toxicity, and prompt injections.

Security Scanning & Vulnerability Audit

Automates comprehensive security audits and vulnerability scanning across dependencies, source code, secrets, and container images.

LLM Application Testing

Implements deterministic testing patterns for AI applications using DeepEval, RAGAS, and advanced mocking strategies.

Advanced Pytest Patterns

Optimizes Python testing suites using custom markers, parallel execution with xdist, and advanced hook implementations for scalable infrastructure.

Multi-Scenario Orchestrator

Orchestrates a single skill across three parallel scenarios with synchronized state and progressive difficulty to validate performance and scalability.

Comprehensive Test Execution & Analysis

Executes full-stack test suites with parallel failure analysis and integrated coverage reporting.

Test Standards Enforcer

Enforces rigorous testing best practices and quality standards across your codebase by blocking non-compliant test implementations.

Input Validation & Sanitization

Secures applications by implementing robust server-side input validation and sanitization patterns using Zod and Pydantic.

MCP Security Hardening

Implements robust security patterns for Model Context Protocol integrations to prevent prompt injection and tool poisoning.

Advanced Integration Testing

Generate production-ready integration tests for APIs, databases, and frontend components to ensure seamless system interaction.

MSW 2.0 API Mocking

Mocks network-level API requests for frontend testing using Mock Service Worker 2.x standards.

LLM Testing & Validation

Implements deterministic testing patterns and quality metrics for LLM-based applications using DeepEval and RAGAS.

Input Validation & Sanitization

Validates and sanitizes untrusted user input using industry-standard Zod and Pydantic patterns to prevent security vulnerabilities.

Advanced Pytest Patterns

Implements sophisticated Python testing workflows using custom markers, parallel execution with xdist, and advanced fixture architecture.

Test Data Management

Streamlines the creation and management of test data using factories, fixtures, and automated database seeding patterns.

API Contract Testing

Implements consumer-driven contract testing using Pact to ensure API compatibility and prevent breaking changes in microservice architectures.

Issue Resolution & RCA

Resolves GitHub issues through a systematic 11-phase workflow featuring parallel multi-agent root cause analysis.

LLM Safety Patterns

Implements robust security patterns for LLM integrations to prevent prompt injection, hallucinations, and sensitive data leakage.

OWASP Top 10 Security

Audits and secures web applications against the most critical security vulnerabilities identified by OWASP.