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。
Guides developers through designing production-quality LLM evaluation pipelines and scoring rubrics to ensure AI output reliability.
Automates end-to-end browser testing and web interactions using the modern Playwright framework for reliable web application validation.
Automates end-to-end browser testing and web automation across Chromium, Firefox, and WebKit with native WSL2 support.
Enforces a rigorous 6-phase root cause analysis process to identify, reproduce, and fix software bugs with evidence-based verification.
Master systematic troubleshooting techniques and root cause analysis to efficiently resolve complex bugs and performance bottlenecks across any technology stack.
Enforces absolute code quality by automatically fixing all linting, typing, and security issues across your entire project.
Performs ruthless, multi-agent code reviews with weighted scoring and an elite 95% passing threshold.
Implements comprehensive testing strategies for multi-agent systems, including contract validation, integration plans, and end-to-end user journeys.
Implements secure storage, rotation, and management of sensitive credentials across major cloud providers and CI/CD platforms.
Implements secure credential handling and automated secret rotation for CI/CD pipelines and cloud environments.
Enforces an empirical evidence-first workflow by requiring command execution and output validation before any task is claimed as complete.
Automates shell script verification using the Bash Automated Testing System (Bats) framework for robust and portable scripts.
Facilitates major version upgrades of software dependencies through compatibility analysis, staged rollouts, and rigorous testing.
Implements reliable end-to-end testing suites using Playwright and Cypress to capture regressions and ensure application stability.
Applies methodical debugging frameworks and root cause analysis to resolve complex software issues across diverse technology stacks.
Executes tSQLt database unit tests against SQL Server to verify schema changes and stored procedures.
Streamlines the creation and management of Ruby on Rails tests using the default Minitest framework.
Implements industry-leading Python testing patterns and TDD workflows using pytest and advanced mocking strategies.
Implements rigorous Python testing standards using pytest, TDD workflows, and refactor-safe mocking patterns.
Eliminates technical debt by identifying and fixing the root causes of Python errors instead of implementing complex workarounds.
Implements robust unit testing for shell scripts using the Bash Automated Testing System (Bats) framework.
Automates the self-dogfooding property-based testing workflow for the Aletheia MoonBit repository.
Analyzes repository structures to generate secure, stack-specific permission settings and allow lists for Claude Code.
Provides expert guidance on isolating Ruby tests using test doubles, stubbing, spies, and verifying doubles within the RSpec framework.
Optimizes RSpec test suites by providing expert techniques for profiling, database efficiency, and parallel execution.
Scans code and skills for sensitive credentials, API keys, and personal data to prevent accidental exposure.
Automates the remediation of critical vulnerabilities and implements secure-by-default patterns for claude-flow v3 architectures.
Automates code quality verification, truth scoring, and intelligent rollbacks to ensure high-reliability agent outputs.
Guides developers through the 2025 Rust ecosystem with expert patterns for testing, security auditing, and performance profiling.
Analyzes Rust code to implement idiomatic error handling using Result types, context propagation, and custom error enums.
Scroll for more results...