发现security & testing类别的 Claude 技能。浏览 105 个技能,找到适合您 AI 工作流程的完美功能。
Enforces production-ready architecture patterns, secure environment management, and rigorous quality standards for TypeScript projects.
Implements an Eval-Driven Development (EDD) framework to measure and improve AI coding reliability through structured testing and metrics.
Implements professional Go testing patterns including table-driven tests, fuzzing, benchmarks, and TDD workflows.
Executes and reports on TypeScript unit and integration tests using a dedicated subagent for enhanced reliability and safety.
Validates API contracts using consumer-driven testing and OpenAPI specifications to ensure service compatibility and prevent breaking changes.
Generates and executes comprehensive unit and integration tests using pytest and Jest frameworks with built-in coverage reporting.
Measures and compares prompt efficacy through A/B testing, performance metrics, and detailed analytical reports.
Automates the iterative cycle of identifying coverage gaps, writing focused unit tests, and maintaining code quality through integrated reviews.
Provisions and manages isolated test environments to streamline automated testing and reporting workflows.
Enforces standardized unit testing patterns and implementation rules for robust Rust applications.
Empowers AI agents to self-review and correct code using 75 specialized techniques before final validation.
Automates the creation, execution, and analysis of comprehensive UI component tests using Vitest and React Testing Library.
Requests a second perspective from OpenAI's Codex models to identify gaps, risks, and architectural flaws in technical designs and implementations.
Implements multi-layered security architectures and ethical quality controls for AI agents and prompts.
Enforces a strict Red-Green-Refactor workflow to ensure high-quality, verified code implementation.
Conducts thorough security assessments of SMTP servers to identify vulnerabilities like open relays, user enumeration, and weak authentication.
Provides a comprehensive collection of over 18 optimized prompt templates and executable agents for specialized cognitive tasks.
Provides a comprehensive library of essential penetration testing commands for network scanning, exploitation, and vulnerability assessments.
Provides a comprehensive library of penetration testing commands and workflows for security professionals using industry-standard tools.
Analyzes network traffic using Wireshark to troubleshoot connectivity, optimize performance, and investigate security incidents.
Evaluates and benchmarks LLM agents using statistical testing, behavioral contracts, and reliability metrics to ensure production readiness.
Conducts comprehensive security audits to identify and remediate Insecure Direct Object Reference (IDOR) vulnerabilities in web applications.
Automates frontend testing and browser interactions for local web applications using Playwright scripts.
Analyzes and consolidates WebFetch domain permissions with automated security research and validation for Claude Code.
Enforces a strict Red-Green-Refactor workflow to ensure high-quality, verified code through test-first implementation.
Scans source code for security vulnerabilities and provides actionable remediation patterns based on industry standards.
Automates the assessment of pull requests to ensure code quality, security compliance, and architectural integrity before merging.
Detects universal security vulnerabilities and hardcoded secrets across all programming languages using standardized regex patterns.
Implements a structured, scientific approach to identify, isolate, and resolve software bugs efficiently.
Design and implement comprehensive test suites including unit, integration, and E2E tests across multiple programming languages.
Scroll for more results...