Security & Testing Agent Skills

LLM Safety Patterns

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

MSW API Mocking

Mocks network-level API requests using MSW 2.x to create deterministic and resilient frontend tests.

Input Validation & Sanitization

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

Assessment & Quality Auditor

Evaluates code, designs, and technical approaches using a structured 0-10 scoring system with detailed pros, cons, and improvement plans.

OrchestKit Health Diagnostics

Performs comprehensive health checks and troubleshooting for OrchestKit plugins, skills, and agent configurations within Claude Code.

Evidence Verification

Verifies task completion by collecting and documenting executable proof including test results, build outputs, and exit codes.

MCP Security Hardening

Implements defense-in-depth security patterns to protect Model Context Protocol (MCP) integrations against prompt injection and tool poisoning.

Property-Based Testing

Automates the discovery of edge cases and boundary conditions using Hypothesis to validate invariants across diverse input sets.

E2E Testing with Playwright

Automates and validates critical user journeys using Playwright 1.58+ with AI-assisted test generation and resilient semantic locators.

Automated Accessibility Testing

Implements automated accessibility audits and WCAG 2.2 compliance checks using axe-core, Playwright, and jest-axe.

Assess

Evaluates code, designs, and architectural approaches with structured 0-10 quality ratings and detailed pros/cons analysis.

OrchestKit Health Diagnostics

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

Evidence Verification

Verifies code changes through systematic collection of test results, build outputs, and quality metrics before task completion.

MCP Security Hardening

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

VCR HTTP Recording & Mocking

Automates the recording and replaying of HTTP interactions in Python tests using VCR.py to create deterministic, fast, and offline-capable test suites.

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.

Performance Testing

Automates the creation and execution of load, stress, and spike tests using industry-standard tools like k6 and Locust.

Performance Testing & Load Analysis

Validates system stability and scalability by simulating high-traffic scenarios using industry-standard tools like k6 and Locust.

Web Application Testing

Builds and debugs web application features through a structured, iterative testing process using Playwright.

Advanced Pytest Patterns

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

Golden Dataset Management

Protects and maintains high-quality test datasets for AI/ML systems through automated backup, restoration, and integrity validation.

LLM Safety Patterns

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

Multi-Scenario Orchestrator

Orchestrates a single skill across three parallel scenarios with synchronized execution and increasing levels of difficulty.

Skill Evaluator

Evaluates agent skills against Anthropic's official best practices to ensure optimal structure, naming, and content organization.

Traceability Matrix & Requirements Coverage

Verifies bidirectional traceability between requirements, source code, and test suites to ensure complete project coverage and compliance.

Test Coverage Analyst

Analyzes codebase test coverage, identifies critical gaps, and provides prioritized recommendations for improving software quality.

Test Suite Synchronization

Maintains alignment between test suites and source code by identifying orphaned tests, missing coverage, and implementation-coupled logic.

TDD Enforcement & Coverage Gates

Enforces test-driven development practices through automated pre-commit hooks and CI coverage gates.

Mutation Testing Expert

Validates test suite effectiveness by introducing intentional code defects to identify weak assertions and untested logic.