Security & Testing Claude 技能

Code Review Expert

Performs comprehensive code audits focusing on security vulnerabilities, performance bottlenecks, and maintainability standards.

Find Bugs & Security Auditor

Audits local branch changes to identify security vulnerabilities, logical bugs, and critical code quality issues using a rigorous multi-phase verification process.

Web3 Smart Contract Testing

Tests and validates Ethereum smart contracts using Hardhat and Foundry with advanced patterns like mainnet forking and fuzzing.

PCI Compliance & Secure Payments

Implements PCI DSS standards and secure payment processing patterns to protect sensitive cardholder data.

Web Application Testing

Automates browser-based testing and debugging for local web applications using Playwright automation.

Prowler Compliance Framework Manager

Automates the creation, management, and mapping of cloud security compliance frameworks like CIS, NIST, and SOC2.

Prowler Compliance Review

Automates the validation and review process for cloud security compliance frameworks within Prowler.

Hookify Rule Automation

Configures custom guardrails and automation rules to intercept and guide Claude's behavior during CLI sessions.

Senior CAPA Officer

Manages Corrective and Preventive Actions (CAPA) within Quality Management Systems using systematic root cause analysis and compliance-driven workflows.

G2 Visualization Testing

Standardizes the creation of unit and integration tests for the G2 visualization library using Jest and specific implementation patterns.

V3 Security Overhaul

Hardens claude-flow v3 architectures by remediating critical vulnerabilities and implementing secure-by-default development patterns.

Verification & Quality Assurance

Ensures codebase reliability and agent output quality through real-time truth scoring, automated verification checks, and instant rollback capabilities.

GitHub Code Review

Orchestrates multi-agent code reviews on GitHub to provide deep security, performance, and architectural analysis within pull requests.

Systematic Debugging

Identifies the root cause of bugs and test failures through a rigorous four-phase investigation process before proposing or implementing any fixes.

Test-Driven Development

Enforces a strict Red-Green-Refactor workflow to ensure high code quality and reliability through test-first implementation.

Verification Before Completion

Enforces a mandatory evidence-based protocol for validating work through fresh command execution and output analysis before making any success claims.

Requesting Code Review

Streamlines the process of dispatching specialized subagents to verify code quality and requirement fulfillment before merging changes.

Testing Skills With Subagents

Validates and bulletproofs AI process documentation by applying Test-Driven Development cycles to verify compliance under realistic pressure scenarios.

Sentry SDK E2E Tester

Automates the end-to-end testing workflow for Sentry JavaScript SDK applications and packages.

Audit Support & SOX Compliance

Streamlines SOX 404 compliance workflows through standardized control testing, sample selection, and audit documentation guidance.

Web Application Testing

Facilitates end-to-end testing and browser automation for local web applications using Python and Playwright.

Route Tester

Tests and validates authenticated API routes using cookie-based JWT authentication and mock authorization patterns.

Agent Evaluation & Quality Assurance

Builds robust evaluation frameworks and multi-dimensional rubrics to measure, optimize, and validate AI agent performance and context efficiency.

Test Fixture Manager

Streamlines the creation and management of standardized test fixtures and sample data for automated testing.

Test Fixture Path Manager

Configures and manages custom directory paths for test fixtures to streamline automated testing workflows.

Python Playground

Executes and tests Python snippets in an isolated environment to verify logic, investigate CPython behavior, or experiment with the Monty interpreter.

Agent Performance Evaluation

Measures and optimizes AI agent performance through multi-dimensional rubrics, LLM-as-judge methodologies, and robust testing frameworks.

Web E2E Testing

Develops, executes, and debugs Playwright end-to-end tests for the Uniswap web application using custom fixtures and automated blockchain environments.

Skill Quality Tester

Validates, tests, and scores Claude Code skills to ensure they meet professional engineering standards and tier requirements.

Dependency Auditor

Audits and manages software dependencies across multiple languages to ensure security, license compliance, and optimal performance.