Security & Testing Agent Skills

Systematic Debugging

Eliminates software bugs by identifying root causes through structured investigation and sequential reasoning.

Test Quality & Coverage Validator

Ensures high-quality codebases by validating test behavior, identifying edge case gaps, and enforcing strict coverage standards.

Code Review Multi-Agent

Performs deep, parallel code reviews for security, performance, and test coverage using specialized AI agents.

Reviewing Security (OWASP Top 10)

Conducts comprehensive security audits and code reviews based on OWASP Top 10 standards to identify and mitigate critical vulnerabilities.

Design Document Audit Scoring

Evaluates technical design documents and Statements of Work (SOW) using a rigorous 100-point scoring system to ensure high-quality implementation specs.

Readability Reviewer

Optimizes code clarity and reduces cognitive load by applying Readable Code principles and Miller's Law.

Hookify: Custom Behavior Hooks

Creates declarative rules and safety guardrails to prevent unwanted behaviors and enforce coding standards within Claude Code.

TDD Test Design & Implementation

Implements a comprehensive Test-Driven Development (TDD) workflow using RGRC cycles, Baby Steps, and systematic test design techniques.

Web E2E Testing (Playwright & Anvil)

Automates the creation, execution, and debugging of end-to-end Playwright tests for decentralized web applications.

Capability Flow Validator

Validates capability flow specifications against schema constraints to ensure structural completeness and pattern consistency.

Go Quality & Testing Suite

Validates Go code quality and executes unit tests to ensure project reliability and standards compliance.

HTTP API Testing

Automates the creation and execution of robust HTTP API tests for TypeScript and Python environments.

Code Anti-patterns Analysis

Identifies and resolves complex code smells, anti-patterns, and security vulnerabilities across multiple programming languages using structural pattern matching.

Rust Code Coverage (cargo-llvm-cov)

Generates precise Rust code coverage reports using LLVM-based instrumentation and integrates with CI/CD pipelines.

Mutation Testing Expert

Validates test suite effectiveness by introducing deliberate code mutations to identify weak assertions and untested logic paths.

Playwright Testing

Automates end-to-end web testing across multiple browsers using the Playwright framework for reliable UI and API verification.

Claude Security Settings

Configures granular security permissions, shell operator protections, and project-level access controls for Claude Code.

Binary Analysis & Reverse Engineering

Analyzes binary files and firmware to extract strings, identify file signatures, and explore raw data using industry-standard tools.

Debugging Methodology

Implements a systematic approach to diagnosing and resolving complex software bugs using advanced system tracing and memory analysis tools.

Python Dead Code Detection

Identifies and prunes unused Python functions, classes, and variables to maintain clean and efficient codebases.

Vitest Testing

Streamlines unit and integration testing for JavaScript and TypeScript projects using the high-performance Vitest runner.

Git Security Checks

Automates secret detection and security validation in Git workflows to prevent credential leaks before they are committed.

Property-Based Testing

Automates test case generation and edge-case discovery using fast-check for TypeScript and Hypothesis for Python.

Python Testing with pytest

Simplifies Python test suite creation and maintenance using pytest, mocking, and comprehensive coverage analysis.

Advanced Pytest Testing

Implements sophisticated Python testing patterns including scoped fixtures, parallel execution, and async support for robust application suites.

Code Review Checklist

Automates structured code reviews by evaluating security, performance, correctness, and maintainability against industry best practices.

Cargo Nextest Rust Test Runner

Optimizes Rust testing workflows with high-performance parallel execution, advanced filtering, and resilient CI integration.

Hypothesis Property-Based Testing

Automates edge case discovery and invariant validation using property-based testing with the Hypothesis framework.

Smart Test Tier Selection

Optimizes development workflows by automatically recommending the appropriate test tier based on the scope and impact of code changes.

Test Quality Analysis

Analyzes test suites to detect anti-patterns, improve coverage, and eliminate flaky tests for more reliable software delivery.