security & testing Claude 스킬을 발견하세요. 105개의 스킬을 탐색하고 AI 워크플로우에 완벽한 기능을 찾아보세요.
Audits Codex home directories to detect configuration drift, security risks, and cleanup opportunities.
Analyzes and validates visual diffs from Storybook, Playwright, and Argos to distinguish intentional UI changes from accidental regressions.
Analyzes git history to map code ownership risks, identify low bus factors in sensitive components, and detect security maintenance gaps.
Generates repository-specific security threat models by identifying assets, trust boundaries, and potential abuse paths based on source code evidence.
Manages IT outages and security incidents using structured workflows for triage, containment, and blameless post-mortem analysis.
Reviews code and architecture against language-specific security standards and the OWASP Top 10:2025 framework.
Guides technical teams through IT outages and security incidents using structured SRE and SecOps workflows.
Diagnoses production bugs and regressions using evidence-based analysis and reproducible fix plans before implementing code changes.
Implements and migrates secure Better Auth integrations for TypeScript and JavaScript applications with OWASP-aligned defaults.
Enforces best practices for Rust unsafe code to minimize risk, manage raw pointers, and ensure FFI interoperability while preventing undefined behavior.
Enforces rigorous data protection controls and privacy-by-design principles across application layers to ensure regulatory compliance.
Automates the validation of backend services including REST APIs, AWS Lambdas, gRPC endpoints, and GraphQL interfaces.
Decompiles freeform SKILL.md files into machine-auditable structures to perform automated security audits and risk scoring.
Protects AI agents from deceptive content, prompt injection, and harmful information across social media platforms.
Audits and reports on specific user actions across cloud resources to ensure security, accountability, and compliance.
Validates project health through rapid pre-QA sanity checks including server availability, file existence, and browser console errors.
Audits Claude Code configurations and MCP servers for security vulnerabilities, misconfigurations, and injection risks using AgentShield.
Conducts comprehensive WCAG 2.2 Level AA accessibility audits for React and TypeScript applications with specialized MUI framework awareness.
Audits Claude Code plugins and skills for malicious code and harmful natural language instructions using AI semantic analysis.
Streamlines testing of time-dependent .NET logic by implementing and manipulating TimeProvider and FakeTimeProvider abstractions.
Performs comprehensive audits of code quality, security vulnerabilities, and technical debt using modern engineering standards and actionable remediation plans.
Protects AI agents from induced content, spam, and prompt injection while interacting with social platforms like Moltbook.
Audits Claude Code session logs to refine and optimize bash command permission decisions for increased workflow efficiency.
Conducts automated end-to-end QA sweeps to catch console errors, layout bugs, RBAC violations, and API schema drift.
Implements mandatory adversarial defense rules and security guardrails to protect mortgage refinance workflows from manipulation.
Performs comprehensive accessibility audits using axe-core to ensure WCAG 2.1 AA compliance and inclusive user experiences.
Automates consumer-driven contract testing and schema validation for REST, GraphQL, and event-driven APIs to prevent breaking changes.
Audits and refactors React codebases into enterprise-grade, feature-based architectures following Bulletproof React patterns.
Automates the Playwright end-to-end testing lifecycle with LLM-powered visual analysis and actionable fix recommendations.
Provides a constructive adversarial perspective to stress-test ideas, designs, and decisions through rigorous examination.
Scroll for more results...