Security & Testing Claude 스킬

Smart Test Selection

Optimizes development cycles by intelligently selecting and running only the tests affected by your recent code changes.

Outside-In Agentic Testing

Generates behavior-driven tests that verify application interfaces across CLI, Web, TUI, and Electron using AI agents.

Smart Test Selection

Optimizes developer feedback loops by intelligently selecting and running only the tests affected by specific code changes.

Dynamic Debugger

Enables interactive, natural language debugging for multiple programming languages using the Debug Adapter Protocol (DAP).

Quality Audit Workflow

Conducts automated, end-to-end codebase quality audits with parallel agent orchestration, GitHub issue creation, and PR remediation.

Test Gap Analyzer

Identifies untested code paths and generates specific test suggestions to improve software reliability and coverage.

Quality Audit Workflow

Orchestrates comprehensive, parallel codebase audits with automated GitHub issue creation and PR-based remediation.

Smart Test Selection

Optimizes testing workflows by intelligently selecting affected tests based on code changes and reliability data.

Write Test

Automates behavior-driven test generation by identifying and filling coverage gaps in existing codebases.

Condition-Based Test Waiting

Eliminates flaky tests by replacing non-deterministic timeouts with robust, state-aware condition polling.

Code Implementation (Gate 0)

Enforces a rigorous Test-Driven Development (TDD) workflow by routing tasks to specialized language agents.

Skill Testing with Subagents

Validates AI skill reliability using a Red-Green-Refactor methodology and high-pressure compliance testing.

Evidence-First Verification Gate

Enforces a mandatory command-first workflow that requires fresh verification evidence before any success claims or code commits.

Systematic Debugging

Implements a rigorous four-phase debugging framework that ensures the root cause is fully understood before any code fixes are attempted.

TDD & Unit Testing Gate

Enforces rigorous unit test coverage and TDD methodology through mandatory quality gates for AI-driven development.

Testing Anti-Pattern Guard

Enforces high-quality testing standards by preventing mock-testing, production code pollution, and brittle dependency isolation.

Dev Review (Gate 4)

Orchestrates mandatory parallel code reviews using three specialized AI agents to enforce security, logic, and quality standards.

Root Cause Tracing

Systematically traces bugs from the point of failure back to the original trigger through call-chain analysis and instrumentation.

Automated Codebase Linting

Automates the identification and resolution of linting errors by dispatching parallel AI agents to clean your codebase.

Defense-in-Depth Validation

Enforces multi-layer validation patterns to make software bugs structurally impossible by verifying data at every architectural boundary.

Infrastructure Security Auditor

Conducts systematic infrastructure security audits, vulnerability assessments, and compliance validations through structured workflows.

Development Cycle Validation Gate

Enforces mandatory human approval and evidence-based validation of acceptance criteria before completing development tasks.

Advanced Testing & Quality Engineering

Implements sophisticated testing strategies including E2E, mutation, and property-based testing to ensure production-grade software reliability.

Security Best Practices

Implements robust security patterns and mitigates common vulnerabilities using industry-standard protocols and OWASP guidelines.

Shared Development Patterns

Provides a centralized library of architectural patterns for testing, security, and API design to ensure consistency across AI-driven development.

Testing & Quality Assurance

Implements comprehensive software testing strategies and architectural patterns to ensure code reliability and deployment confidence.

Backend API Testing Toolkit

Automates backend API verification using language-native test frameworks to ensure robust database and endpoint integrity.

Agent Testing with Subagents

Implements a strict Test-Driven Development (TDD) methodology for AI agents to ensure accurate, well-structured, and reliable outputs.

Security Infrastructure

Hardens application infrastructure through security headers, encryption standards, and regulatory compliance enforcement.

Test-Driven Development (TDD) Enforcer

Enforces the Red-Green-Refactor methodology with strict quality gates and mandatory code deletion for violations.