security & testing Claude 스킬을 발견하세요. 105개의 스킬을 탐색하고 AI 워크플로우에 완벽한 기능을 찾아보세요.
Manages autonomous testing strategies and enforces quality gates to ensure high-standard software delivery.
Generates comprehensive, production-ready test suites for JavaScript, TypeScript, and Python using frameworks like Jest, Pytest, and Playwright.
Evaluates code implementations for build integrity, type safety, and architectural consistency within development loops.
Identifies, reports, and remediates security vulnerabilities in project dependencies across multiple programming languages.
Configures robust security HTTP headers and Content Security Policies to protect web applications from common vulnerabilities.
Refactors codebases using a TDD approach to improve internal quality, performance, and race safety without altering external behavior.
Orchestrates a multi-stage dual-AI workflow to plan, implement, and validate complex features with high-confidence code reviews.
Enforces a rigorous investigation-to-fix protocol that eliminates symptoms and solves underlying code issues using AI reasoning.
Orchestrates an advanced feedback loop between Claude, Codex, and Gemini to provide multi-perspective validation and high-integrity code generation.
Provides comprehensive guidelines and best practices for conducting high-quality code reviews and writing constructive feedback.
Validates authenticated API routes using automated cookie-based JWT token generation and mock authentication patterns.
Verifies multi-layer cryptographic identity proofs and orchestrates complex quest fulfillment within the Plurigrid ASI ecosystem.
Generates framework-compliant enterprise cybersecurity policies in multiple formats using industry-standard templates from SANS and CIS Controls.
Secures sensitive credentials using the hardware-backed macOS Keychain with mathematically balanced GF(3) lifecycles.
Implements comprehensive testing strategies for Rust including property-based testing, fuzzing, and performance benchmarking.
Validates codebase compliance with the Outfitter Stack by scanning for anti-patterns and generating actionable severity-ranked reports.
Simulates a multi-layered agent architecture to test thinking token capture and skill orchestration across complex workflows.
Implements comprehensive testing infrastructure and patterns for monorepos using Vitest, React Testing Library, and Storybook.
Automates static application security testing using Semgrep to identify vulnerabilities, security anti-patterns, and OWASP Top 10 issues.
Searches the NIST National Vulnerability Database to identify security vulnerabilities and assess risk scores for software components.
Validates Cynara privilege access control policies to ensure secure and compliant Tizen application environments.
Automates structured debugging workflows and root cause analysis using evidence-based protocols and comprehensive verification.
Executes and manages TUnit tests with Playwright integration to verify Blazor component functionality and accessibility.
Validates Tizen runtime privilege policies and coordinates system-wide access control decisions through the Cynara database.
Automates the creation of secure 1Password items including logins, API keys, and notes via the 1Password CLI.
Audits code and comments to ensure content appropriateness for youth audiences and educational environments.
Provides instant access to WCAG 2.1 AA criteria and WAI-ARIA implementation patterns with official W3C references.
Generates comprehensive unit, integration, and E2E test suites automatically while learning from your project's specific testing style.
Provides detailed web vulnerability intelligence, exploit payloads, and bounty payout estimates for security auditing.
Enforces mandatory human oversight for security-sensitive, complex, or high-volume code changes within the development lifecycle.
Scroll for more results...