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。
Validates code quality through a comprehensive 5-layer pyramid using independent LLM-as-judge evaluation for production readiness.
Validates bug resolutions by executing reproduction steps and automated test suites to ensure complete fixes and prevent regressions.
Automates AI agent quality testing and monitoring using built-in metrics and custom LLM-as-judge evaluation patterns.
Configures and tests common network services like HTTP, SNMP, and SMB to create controlled penetration testing lab environments.
Performs isolated UI component testing for React, Vue, and Svelte using Playwright's experimental component testing framework.
Implements a 5-layer verification pyramid to ensure production-grade code quality through automated checks and LLM-as-judge evaluation.
Executes an intensive code quality suite combining ESLint, TypeScript compilation, and unused code detection to maintain high development standards.
Validates Claude Code skill functionality and usability through comprehensive scenario-based testing operations.
Automates visual regression testing and UI consistency checks using Chromatic, Lost Pixel, and Playwright snapshots.
Emulates diverse mobile devices and responsive environments using Playwright to ensure seamless cross-platform web performance.
Enforces standardized testing protocols and best practices to ensure high-quality, maintainable test suites.
Enforces a strict test-driven development cycle using a multi-agent red-green-refactor orchestration.
Protects autonomous coding environments by enforcing command allowlists, filesystem permissions, and execution sandboxing.
Enforces a rigorous, root-cause-first framework for resolving bugs by eliminating guesswork and prioritizing evidence-based investigation.
Generates comprehensive unit tests for multiple programming languages by analyzing code structure and project requirements.
Ensures all code changes and task completions are backed by fresh, empirical evidence before making success claims.
Enforces strict code quality standards, architectural patterns, and TypeScript best practices for robust software development.
Automates the test-driven development lifecycle using Playwright to ensure robust web application functionality through iterative testing and implementation.
Automates browser testing and UI verification for local web applications using Playwright integration.
Streamlines bug triage and regression testing for OpenEvent workflows using deterministic reproduction traces and invariant validation.
Implements industry-standard smart contract security patterns and prevents common vulnerabilities in Ethereum-based applications.
Evaluates Agentic GraphRAG performance using automated benchmarking and LLM-as-judge scoring rubrics.
Facilitates comprehensive testing of Solidity smart contracts using Hardhat and Foundry to ensure security, reliability, and gas efficiency.
Implements GDPR-compliant data processing, consent management systems, and automated data subject request handlers.
Diagnoses and resolves complex bugs in .NET/ABP and React applications using systematic root cause analysis and performance optimization patterns.
Implements robust data validation and quality assurance using Great Expectations, dbt tests, and data contracts.
Automates .NET test failure analysis by capturing logs, generating markdown summaries, and creating focused rerun filters.
Builds systematic attack trees to visualize potential threat paths and identify critical security vulnerabilities.
Guides the execution of UI smoke tests and Playwright E2E suites to validate frontend changes and navigation flows.
Maps identified security threats to specific technical controls and mitigations to strengthen system architecture and defense-in-depth.
Scroll for more results...