Security & Testing Claude 技能

Breenix Code Quality Check

Enforces strict code quality standards and pre-commit verification for Breenix kernel development through compiler checks, linting, and log analysis.

Systematic Debugging

Facilitates document-driven kernel debugging through a structured four-phase pattern of problem analysis and evidence collection.

Breenix Integration Test Authoring

Streamlines the creation of kernel-level integration tests for Breenix using QEMU virtualization and serial signal monitoring.

Breenix CI Failure Analysis

Analyzes and diagnoses GitHub Actions CI/CD failures for Breenix kernel development, identifying root causes like kernel panics, page faults, and test timeouts.

Code Quality & Testing Framework

Enforces rigorous code quality standards and implements comprehensive multi-layer testing infrastructure to ensure production-grade software reliability.

AgentV Eval Builder

Generates and maintains structured YAML evaluation files for testing AI agent performance and response accuracy.

Testing Sync-Skills

Validates and tests synchronization functionality between .claude and .codex agent skill directories.

Solana Security Auditor

Audits Solana programs for security vulnerabilities using a systematic review framework for Anchor and native Rust.

Vue Test Architect

Writes robust, production-grade unit tests for Vue.js components using Vitest and Vue Testing Library.

WCAG Accessibility Audit Patterns

Performs comprehensive WCAG 2.2 accessibility audits and provides remediation strategies to ensure web content compliance.

Robot SF Branch Cleanup

Automates repository maintenance, linting, and parallel testing for Robot SF development branches.

Vitest Testing Suite

Implements professional Vitest testing patterns for high-quality JavaScript and TypeScript applications.

Testing Skills with Subagents

Applies a Test-Driven Development cycle to process documentation to ensure instructions resist rationalization and remain effective under high-pressure scenarios.

Smart Contract Auditor

Performs rigorous security audits on smart contracts with severity-rated findings and deployment recommendations.

Laravel Test Runner (No-Fork)

Executes Laravel test suites directly in the main session context to facilitate deep debugging and environment comparison.

Web App Testing & Debugging

Automates web application testing and UI debugging using Playwright to ensure seamless frontend functionality and visual consistency.

Visual Testing & UI Verification

Automates visual regression testing and UI verification through screenshots, responsive viewport analysis, and design-to-code comparisons.

Isolated Laravel Test Runner

Executes Laravel test suites in forked sub-agent contexts to prevent output pollution and enable parallel development.

Analyze Test Failures

Diagnoses and resolves failing tests within an isolated environment to maintain a clean workspace.

TypeScript Error Fixer

Eliminates TypeScript compilation errors and 'any' types through a systematic four-phase automated workflow.

Kernel Debug Loop

Enables rapid kernel development cycles through time-bounded execution and real-time log signal detection.

Deep Codebase Analysis

Performs comprehensive codebase audits and architectural exploration using isolated sub-agents to avoid session clutter.

Autonomous Code Reviewer

Conducts multi-dimensional code reviews focusing on quality, security, performance, and accessibility using parallel sub-agents and LSP integration.

Design Compliance & Architecture Audit

Performs comprehensive audits of code alignment with Architecture Decision Records (ADRs) and OpenSpec specifications to detect and resolve technical drift.

Data Encryption & Decryption

Secures sensitive information by providing seamless data encryption and decryption capabilities using AES, RSA, and other standard algorithms.

TDD Workflow for Claude Code

Enforces rigorous Test-Driven Development discipline through a structured Red-Green-Refactor cycle and automated session tracking.

Async API Testing Suite

Automates comprehensive API testing using pytest and httpx to ensure robust backend service reliability through asynchronous request handling.

LLM Agent Evaluation Builder

Designs and implements rigorous evaluation frameworks for LLM agents, multi-agent systems, and prompts using industry-standard metrics.

Unified Testing Patterns

Standardizes testing structures and best practices across multiple programming languages and frameworks within Claude Code.

TDD Workflow Manager

Enforces a strict test-driven development lifecycle to ensure high code quality and minimum 80% test coverage.