Security & Testing Agent Skills

Ultrathink Detective

Conducts comprehensive, multi-dimensional codebase audits using advanced AST analysis to identify architecture, risks, and technical debt.

Skill Test-Driven Development

Ensures AI agents follow specific process guidelines by applying TDD principles to skill documentation through pressure testing and loophole refactoring.

Circom ZK Development

Develops and tests zero-knowledge proof arithmetic circuits using the Circom language for zkSNARK applications.

Frontend Bugfix Pro

Debugs and resolves frontend test failures and React/TypeScript bugs using a structured TDD workflow and confidence-based scoring.

JavaScript Testing Standards

Enforces rigorous standards for JavaScript and TypeScript testing using Bun Test, fake timers, and mutation testing quality gates.

Security Testing & Verification

Verifies web application security through automated and manual testing of CSRF protection, rate limiting, input validation, and security headers.

.NET TDD Workflow

Guides the Red-Green-Refactor development cycle for .NET applications to ensure robust, testable, and maintainable code.

Requesting Code Review

Standardizes the code review process by dispatching specialized subagents to verify requirements and identify technical issues early in the development lifecycle.

Business Logic Vulnerability Detection

Identifies and remediates subtle security flaws in AI-generated code, such as race conditions, integer overflows, and calculation errors that bypass standard functional tests.

Security Architecture Overview

Provides a comprehensive guide to the 5-layer defense-in-depth security architecture of Secure Vibe Coding OS to ensure enterprise-grade protection.

Standardized Bugfix Workflow

Implements a structured, TDD-driven bugfix process with automated confidence scoring and quality gate validation.

Code Quality Checker

Automates comprehensive code quality checks including linting, formatting, type validation, and security scanning across multiple languages.

Systematic Debugging Workflow

Automates a multi-phase debugging protocol to identify root causes and verify hypotheses before applying code changes.

AI Manipulation Defense System (AIMDS)

Protects AI agents from adversarial attacks and manipulation using temporal analysis, vector intelligence, and formal verification.

CLI Testing Patterns

Systematizes exploratory testing for command-line tools by validating help text, option flags, error handling, and output accuracy.

API Testing Patterns

Systematizes autonomous API testing through automated endpoint discovery, security validation, and comprehensive schema checks.

Systematic Debugging

Enforces a rigorous four-phase framework to identify root causes and implement stable fixes for any technical issue.

Final Check Automation

Automates the end-to-end testing, security auditing, and pre-deployment validation workflow for Claude Code.

Secure Error Handling

Implements environment-aware error handling to prevent sensitive information leakage while providing standardized API responses.

Feature Flag Implementation

Implements, manages, and automates feature flag lifecycles using type-safe patterns and best practices.

Testing Strategies & TDD

Implements comprehensive testing patterns including unit, integration, and E2E tests following the testing pyramid and TDD principles.

Software Testing Strategy Expert

Provides expert, language-agnostic guidance on software testing strategies, methodologies, and quality assurance best practices.

Secure Coding Practices

Implements OWASP-aligned security patterns and robust authentication frameworks to protect applications from common vulnerabilities.

Prism QA Task Creator

Generates comprehensive test specifications and validation requirements to bridge the gap between issue discovery and QA implementation.

TDD Failing Test Creator

Generates comprehensive failing test specifications and reproduction steps to drive Test-Driven Development and bug resolution.

PRISM QA Gate

Automates the creation and management of quality gate decision files to enforce software standards and track review findings.

Risk Profile Assessment

Conducts comprehensive risk analysis for software features to identify, score, and mitigate technical and business hazards.

PRISM TDD Workflow Loop

Automates the end-to-end TDD development cycle by orchestrating AI agents through planning, testing, and implementation phases.

PRISM Story Review & Quality Gate

Performs comprehensive test architecture reviews and quality gate assessments to ensure software resilience and maintainability.

Root Cause Analysis Expert

Identifies the underlying causes of software bugs through systematic code analysis, log tracing, and impact assessment.