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。
Automates the verification of documentation procedures by converting text-based guides into executable Doc Detective test specifications.
Conducts comprehensive security audits and regulatory compliance reviews for Kling AI video generation integrations.
Implements Eval-driven development to quantitatively measure code quality and track continuous improvements through standardized metrics.
Performs comprehensive security audits and vulnerability checks based on OWASP standards and industry best practices.
Automatically identifies and reports cross-site scripting (XSS) vulnerabilities in web applications through context-aware code analysis.
Executes a rigorous six-stage verification workflow to ensure code quality, security, and type safety within the Claude Code environment.
Configures enterprise-grade security for Replit including Single Sign-On (SSO) and robust role-based access control (RBAC).
Protects your applications by identifying vulnerabilities, enforcing OWASP standards, and implementing robust API security patterns.
Generates robust, production-grade test suites using industry-standard patterns and best practices across multiple languages and frameworks.
Secures Clay platform integrations by implementing API key protection, least privilege access, and robust audit logging.
Guides developers through designing production-quality LLM evaluation pipelines and scoring rubrics to ensure AI output reliability.
Reviews and optimizes code implementations against the mini_agent framework's constitutional principles and quality standards.
Simplifies Solidity-based MultiSig transaction preparation with safe, structured EIP-712 typed-data generation.
Secures Windsurf API integrations by implementing secret management, least privilege access, and audit logging best practices.
Configures enterprise-grade authentication including SAML 2.0 and OIDC for the Cursor code editor.
Enforces a rigorous 6-phase root cause analysis process to identify, reproduce, and fix software bugs with evidence-based verification.
Enforces an empirical evidence-first workflow by requiring command execution and output validation before any task is claimed as complete.
Audits test suites with SRE-level scrutiny to identify tautological tests, coverage gaming, and ineffective assertions.
Conducts comprehensive code security audits and provides remediation guidance based on the OWASP Cheat Sheet Series.
Enforces a strict Red-Green-Refactor workflow to ensure all production code is verified by failing tests first.
Scaffolds production-ready authentication and authorization systems using JWT, realm-based permissions, and session state machines.
Automates evidence-based debugging through systematic hypothesis generation, runtime instrumentation, and structured log analysis.
Diagnoses complex code errors and identifies root causes through a systematic, multi-step troubleshooting framework.
Enforces a rigorous, four-phase root cause analysis process to prevent guesswork and ensure permanent software fixes.
Reverse engineers network protocols using advanced packet analysis, traffic dissection, and technical documentation techniques.
Guides the creation of robust Gleam test suites using gleeunit and modern idiomatic assertion patterns.
Enforces rigorous verification and evidence collection before any task completion or status claim is made.
Configures Claude Code tool permissions and security rules to control access to files, commands, and web tools.
Enforces a strict Red-Green-Refactor workflow to ensure high-quality, verified code implementation for every feature and bugfix.
Optimizes Clay integrations through automated load testing, Kubernetes auto-scaling, and proactive capacity planning.
Scroll for more results...