Security & Testing Claudeスキル

Deep Debug

Executes a multi-agent investigation to resolve complex software bugs through parallel evidence gathering and cross-referenced analysis.

Firebase Authentication

Automates the implementation of secure Firebase Authentication flows, including social sign-in, multi-factor auth, and session management.

Testing Patterns

Automates integration testing using declarative YAML specs and context-preserving sub-agents for MCP servers, APIs, and browsers.

AI Code Reviewer

Automates comprehensive code analysis to detect bugs, security vulnerabilities, and quality issues with actionable feedback.

Axiom iOS Testing Router

Orchestrates comprehensive testing workflows for Apple platforms, covering unit tests, UI automation, and advanced asynchronous debugging.

Quality Gates & Iteration Loops

Implements structured validation checkpoints, automated feedback loops, and multi-model consensus to ensure production-grade code quality.

Code Security & Quality Audit

Performs comprehensive security scans and code quality assessments to identify vulnerabilities, exposed secrets, and technical debt.

Test Coverage Analyzer

Performs on-demand test coverage analysis to identify untested code paths and improve software quality across multiple tech stacks.

Plugin Validation & Testing

Validates skill parsing logic and integration workflows for Claude Code plugin development.

Invalid Frontmatter Tester

Provides a deliberately malformed configuration to test error handling and validation logic in Claude Code plugin loaders.

Validation & Quality Orchestrator

Validates technical specifications, code implementations, and governance compliance using a multi-perspective agentic approach.

Intelligent Debugging Partner

Diagnoses and resolves complex software bugs using a scientific approach and agentic root cause analysis.

Automated Test & Ownership Enforcer

Executes, fixes, and verifies test suites while enforcing strict code ownership to ensure a 100% passing codebase.

Feature Next

Orchestrates a structured feature-driven development workflow using a TDD-enforced cycle to ensure code quality and implementation accuracy.

Risk Classification

Classifies task risk levels using a 4-tier model and automated verification gates to ensure safe AI agent execution.

Localization & i18n Testing

Automates internationalization and localization testing to ensure global products function correctly across different languages, regions, and cultural formats.

QE Contract Testing

Automates API contract verification, schema validation, and backward compatibility testing for REST, GraphQL, and event-driven systems.

Systematic Debugging

Enforces a rigorous, hypothesis-driven methodology to identify and resolve the root cause of software defects.

Proof of Work Validation

Generates verifiable proof artifacts and confidence scores to validate autonomous task completion and enable auto-approvals.

Testing Writing Guidelines

Enforces a minimalist testing strategy by focusing on critical user flows, clear naming conventions, and fast execution.

Universal Testing Strategies

Implements language-agnostic testing patterns and best practices across the entire testing pyramid to ensure robust code quality.

QE Code Intelligence

Streamlines codebase understanding through knowledge graph construction and semantic search while reducing AI token usage by 80%.

Verification & Quality Assurance for Claude Code

Ensures high-quality agent outputs through real-time truth scoring, automated code verification, and an intelligent rollback system.

Accessibility Audit & Fixer

Audits UI diffs for accessibility regressions and provides minimal code fixes with semantic testing recommendations.

.NET CRAP & Coverage Analysis

Analyzes code coverage and complexity metrics to identify high-risk code using the CRAP (Change Risk Anti-Patterns) score.

Slopwatch for .NET

Detects and prevents 'slop'—common LLM reward-hacking shortcuts like disabled tests and suppressed warnings—in .NET codebases.

.NET Aspire Integration Testing

Streamlines the creation of robust integration tests for distributed .NET applications using the Aspire testing framework and xUnit.

Clean Code Foundation

Enforces production-grade coding standards, security protocols, and architectural best practices to prevent AI hallucinations and technical debt.

Ralph Wiggum Surgical Debugger

Diagnoses and resolves deep-rooted code defects through autonomous forensic investigation and high-fidelity reflection loops.

Verification Mastery

Enforces a strict evidence-first workflow by requiring fresh command output and verification before any task is declared complete.