Security & Testing Claude 技能

TDD Workflow

Implements a structured Red-Green-Refactor cycle for autonomous feature development and high-quality code implementation.

Codex Authentication Manager

Configures and manages OpenAI Codex CLI authentication, including OAuth login, API key orchestration, and secure multi-account switching.

Fear-of-Falling Preflight Guardrails

Enforces data integrity and R-script coding standards through strict, diff-aware guardrail checks.

Multi-AI Research & Analysis

Conducts deep, multi-perspective technical research and analysis using integrated Claude, Gemini, and Codex agents for verified, production-ready results.

Web Application Testing

Automates browser-based testing and UI verification for local web applications using Playwright.

Command Guard

Enforces security policies and safety guardrails by validating terminal commands against predefined rules before execution.

Agent Performance Evaluation

Builds comprehensive evaluation frameworks to measure, validate, and optimize AI agent performance and context engineering strategies.

Web Application Testing

Automates local web application testing and debugging using Playwright for comprehensive frontend verification and UI interaction.

Error Recoverer

Automates error detection, classification, and recovery to maintain continuous and resilient autonomous coding sessions.

Browser E2E Tester

Verifies feature implementation through automated browser-based end-to-end testing and acceptance criteria validation.

RSpec Matchers

Provides expert guidance on Ruby testing assertions, expectations, and the creation of custom RSpec matchers.

Jomonsho Release Preflight

Automates and standardizes the release verification process for Jomonsho projects through tiered linting, type-checking, and multi-level testing.

.NET Test Triage

Streamlines .NET test failure analysis by capturing errors and generating focused rerun filters.

Autonomous Error Recoverer

Automates the detection, classification, and resolution of errors encountered during AI-driven development sessions.

Testing Validator

Validates the functional integrity of Claude Code skills through automated example execution and systematic testing operations.

Command Guard

Enforces security policies and prevents destructive command execution by validating actions against local configuration files.

Quality Gates Manager

Enforces Definition of Done criteria by validating required checks and recording outcomes before task completion.

Self-Review Protocol

Ensures code quality and compliance through a standardized two-pass verification and quality assurance process.

MOVA Test Gate Runner

Executes and reports on validation, unit, and smoke test suites to ensure code quality before deployment.

Code Review Patterns & Security Audit

Performs rigorous security audits and code quality reviews using OWASP standards, Clean Code principles, and supply chain integrity checks.

Trust Layer TDD

Enforces test-driven development workflows by requiring failing tests before implementing behavioral code changes.

Jomonsho E2E Emulator

Automates end-to-end testing using Firebase Emulator Suite and Playwright with built-in flakiness detection.

Bedrock AgentCore Evaluations

Implements metric-based quality assurance and monitoring for Amazon Bedrock AI agents using built-in and custom evaluators.

Playwright Component Testing

Facilitates isolated UI component testing across major frontend frameworks using Playwright's experimental component features.

Safety Validation

Validates file modifications against .agentignore rules to prevent unauthorized changes to sensitive project zones.

Bedrock AI Safety & Guardrails

Implements comprehensive Amazon Bedrock Guardrails to secure generative AI applications with content filtering, PII protection, and hallucination detection.

Visual Testing Suite

Automates visual regression testing workflows using Chromatic, Lost Pixel, and Playwright to ensure UI consistency across deployments.

Mobile Testing & Emulation

Automates comprehensive mobile device emulation and responsive web testing using the Playwright framework.

Test Observability for Playwright

Integrates Playwright testing suites with OpenTelemetry and the Grafana stack to provide deep visibility into test failures across distributed systems.

Bug Fix Workflow

Implements a disciplined, TDD-driven approach to identifying, reproducing, and resolving software defects with guaranteed verification.