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。
Conducts deep security audits to identify vulnerabilities, hardcoded secrets, and OWASP compliance issues within your codebase.
Captures and analyzes browser console output, exceptions, and framework-specific warnings to streamline web debugging and performance auditing.
Measures and compares prompt efficacy through A/B testing, performance metrics, and detailed analytical reports.
Automates the verification of code against project-specific guidelines, CLAUDE.md rules, and architectural standards.
Automates defensive security workflows and coordinates multi-agent response playbooks to optimize incident response efficiency.
Identifies critical logical errors, null references, and race conditions through multi-pass deep-dive code analysis.
Assesses implementation readiness through a multi-factor 90% confidence threshold to prevent architectural drift and redundant code.
Audits code for vulnerabilities and enforces industry-standard security best practices across authentication, data handling, and infrastructure.
Implements multi-layered security architectures and ethical quality controls for AI agents and prompts.
Configures granular security policies and tool access patterns to streamline developer workflows while maintaining system safety.
Implements a structured methodology for identifying, isolating, and resolving complex software bugs using hypothesis-driven investigation.
Automates comprehensive dark mode audits by emulating color schemes and validating WCAG 2.1 contrast ratios.
Enforces standardized unit testing patterns and implementation rules for robust Rust applications.
Provides a comprehensive collection of over 18 optimized prompt templates and executable agents for specialized cognitive tasks.
Executes multi-layered automated tests, security scans, and performance audits to ensure code meets production quality gates.
Generates comprehensive test strategies and technical specifications from architecture documents to establish robust quality gates before development begins.
Performs comprehensive security reviews and vulnerability assessments to provide deployment clearance for software systems.
Analyzes and audits access control configurations to identify vulnerabilities and misconfigurations in IAM policies and network ACLs.
Secures infrastructure as code by implementing robust secrets management, automated compliance scanning, and policy enforcement.
Empowers AI agents to self-review and correct code using 75 specialized techniques before final validation.
Analyzes your Python project's existing tests and configurations to provide evidence-based recommendations for better coverage, structure, and performance.
Evaluates and benchmarks LLM agents using statistical testing, behavioral contracts, and reliability metrics to ensure production readiness.
Automates comprehensive security vulnerability scans and penetration testing for web applications and APIs.
Provides a comprehensive library of penetration testing commands and workflows for security professionals using industry-standard tools.
Conducts comprehensive security audits to identify and remediate Insecure Direct Object Reference (IDOR) vulnerabilities in web applications.
Provides a comprehensive library of essential penetration testing commands for network scanning, exploitation, and vulnerability assessments.
Automates the detection, execution, and reporting of unit and integration tests across multiple programming languages and frameworks.
Conducts thorough security assessments of SMTP servers to identify vulnerabilities like open relays, user enumeration, and weak authentication.
Performs automated keyboard navigation audits and WCAG compliance checks using Playwright and axe-core.
Conducts automated code reviews using Codex CLI to identify bugs, security vulnerabilities, and UI changes before project milestones.
Scroll for more results...