Security & Testing Agent Skills

Multi-Language Indexing Verifier

Verifies the multi-language indexing and search capabilities of the code-index-mcp server across various programming languages.

NetFlows Analyzer

Extracts and analyzes network flows from packet capture files with automated DNS hostname resolution.

Saleae Logic MSO Analyzer

Analyzes and decodes digital signals from Saleae Logic MSO binary export files for hardware reverse engineering and protocol analysis.

Overnight Development

Automates overnight software development by enforcing a test-driven development (TDD) workflow with Git hooks.

MassGen Self-Improvement Guide

Optimizes MassGen's multi-agent coordination and terminal interface through programmatic automation and visual UX evaluation.

Inline Repo Pre-Push Validator

Validates code across multiple stacks—including Server, Web, and Swift—to ensure correctness and project health before production releases.

Data Safety Auditor

Audits Vue 3 and Pinia applications for data loss risks, storage vulnerabilities, and synchronization issues with actionable remediation.

AI Truthfulness Enforcer

Enforces zero-tolerance verification protocols to prevent Claude Code from making unverified claims or fabricating progress reports.

QA Testing & Verification Protocol

Enforces rigorous testing protocols and mandatory user verification for web applications to eliminate false success claims and ensure production-grade reliability.

Crisis Debugging Advisor

Provides a systematic framework to regain control and verify reality when AI-assisted development leads to broken application states and false success claims.

Playwright Electron Debugger

Enables live debugging and UI inspection of Electron applications using Playwright and Chrome DevTools Protocol.

Authentication Patterns

Implements industry-standard authentication and authorization flows including JWT, OAuth2 with PKCE, and RBAC.

TDD Mastery

Implements a disciplined Test-Driven Development workflow using the Red-Green-Refactor cycle across multiple programming languages.

Security Hardening

Hardens application security by implementing best practices for input validation, authentication, and vulnerability prevention.

Testing Strategies & Best Practices

Implements advanced testing methodologies including contract, snapshot, and property-based testing to ensure robust software reliability.

Rust Anti-Pattern Reviewer

Identifies non-idiomatic Rust code and suggests high-performance refactoring patterns to improve safety and maintainability.

Unsafe Rust & FFI Checker

Audits unsafe Rust code for soundness, memory safety, and proper FFI implementation patterns.

Best Practices & Web Quality

Implements modern web development standards for security, browser compatibility, and code quality based on Lighthouse audits.

Testing Guidelines for Claude Code

Establishes standardized testing principles for building robust software through integration-focused strategies and mandatory regression coverage.

Code Anti-Pattern Guardrails

Enforces cross-language best practices and prevents common architectural errors in Python, Rust, and TypeScript.

ActivityPub WordPress Testing

Streamlines the creation and debugging of PHPUnit and Playwright tests for WordPress ActivityPub implementations.

UI Visual Validator

Performs rigorous visual validation and accessibility audits to ensure UI modifications meet design system standards and functional requirements.

Agent Skill Stress Tester

Applies a rigorous Red-Green-Refactor cycle to verify and bulletproof AI agent skills against rationalization and rule-breaking under pressure.

Local Change Code Reviewer

Performs a multi-agent, comprehensive audit of uncommitted local changes to identify bugs, security risks, and quality improvements before you commit.

Write Tests (TDD)

Automatically generates comprehensive test coverage for local code changes using specialized AI agents.

Judge Sub-Agent

Evaluates and scores AI-generated work using a specialized, context-isolated sub-agent to ensure high-quality results.

Prompt TDD & Subagent Testing

Applies the RED-GREEN-REFACTOR TDD cycle to prompt engineering using isolated subagents for reliable behavior verification.

Automated TDD Test Fixer

Systematically repairs failing unit and integration tests after code changes using intelligent agent orchestration.

Root Cause Tracing

Systematically identifies the original source of bugs and invalid data by tracing errors backward through the call stack.

TDD Red Phase Workflow

Generates comprehensive failing tests to define expected behavior and edge cases during the initial TDD red phase.