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 rigorous, evidence-based verification before claiming any programming task or bug fix is complete.
Enforces Python code quality standards by automating linting, formatting, and static type checking before commits or pull requests.
Enforces a strict Red-Green-Refactor cycle to ensure all production code is verified by failing tests before implementation.
Automates end-to-end testing and UI debugging for local web applications using Playwright and server lifecycle management.
Automates the creation and editing of end-to-end (E2E) testing scenarios for the Probitas ecosystem using a specialized AI agent.
Provides expert guidance for writing resilient system-wide tests using user-facing locators, semantic helpers, and auto-retriable assertions.
Verifies that AI process documentation and specialized skills are effective and resistant to rationalization by applying a test-driven development cycle to their creation.
Transforms automated QA findings and screenshots into actionable developer tasks with clear acceptance criteria.
Eliminates flaky tests and race conditions by replacing arbitrary timeouts with intelligent state-based condition polling.
Accelerates debugging by dispatching multiple independent Claude agents to investigate and resolve concurrent system failures.
Applies the RED-GREEN-REFACTOR cycle to process documentation to ensure AI agents follow instructions under high-pressure scenarios.
Automates local web application testing and frontend verification using Playwright and managed server lifecycles.
Designs and executes controlled failure experiments to validate system resilience and recovery mechanisms.
Generates unit test fixtures and configurations for BigQuery SQL queries to validate transformation logic during development using synthetic data.
Implements a rigorous four-phase framework to identify root causes and resolve complex technical issues without introducing regressions.
Enforces a strict Red-Green-Refactor cycle by requiring a failing test before any production code is implemented.
Implements multi-layered data validation strategies across execution paths to make bugs structurally impossible.
Eliminates common testing mistakes by enforcing strict TDD principles and preventing mock-related technical debt.
Performs ultra-critical, multi-pass analysis of code changes to identify runtime failures, architectural flaws, and environment risks before merging.
Writes strategic, behavior-focused tests for core user flows and critical business paths to balance development velocity with reliable coverage.
Systematically identifies and resolves failing tests using smart error grouping and prioritized fixing strategies.
Implements a rigorous Red-Green-Refactor cycle to ensure high-quality, verified code across the software development lifecycle.
Systematically traces bugs through the call stack to identify original triggers and implement long-term fixes.
Conducts multi-source research across codebases and the web to provide deep architectural analysis and complex debugging solutions.
Implements multi-tiered data validation strategies to prevent deep execution failures and make software bugs structurally impossible.
Configures project-specific testing infrastructure, frameworks, and strategy documentation to establish a robust quality assurance foundation.
Facilitates end-to-end testing and interaction with local web applications using Playwright and automated server management.
Enforces robust input validation and sanitization standards to ensure data integrity and security across application logic and API endpoints.
Diagnoses and resolves task management issues in the STEEB application, including state synchronization errors, UI inconsistencies, and Firestore integration failures.
Prevents accidental credential leaks by configuring automated pre-commit hooks and scanning repositories for sensitive information.
Scroll for more results...