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。
Enables secure, multi-chain crypto operations for AI agents using threshold cryptography across 36+ blockchains.
Audits development branches to ensure adherence to project principles including DDD, TDD, DRY, and formal shipping workflows.
Standardizes code reviews by applying a dual-axis framework of severity ratings and confidence scores to identify high-impact issues.
Provides comprehensive guidance and implementation patterns for testing and debugging OBS Studio plugins in C/C++ and Rust.
Enforces Test-Driven Development principles and the Red-Green-Refactor cycle across multiple programming languages and frameworks.
Audits Home Assistant integrations against the official Integration Quality Scale (IQS) across all 52 technical and architectural rules.
Enforces scenario-driven end-to-end testing using real dependencies and live data to ensure features are truly validated before completion.
Normalizes security events to the Open Cybersecurity Schema Framework (OCSF) within Tenzir TQL pipelines.
Diagnoses and repairs AJV strict-mode JSON Schema compilation failures by identifying error classes and applying localized patches.
Implements production-ready security hooks, automated formatting, and CI/CD integrations for safer and more efficient Claude Code workflows.
Performs rigorous manual security code reviews by tracing untrusted data flows and validating against OWASP and CWE frameworks.
Automates the analysis, management, and remediation of security vulnerabilities across Checkmarx, SonarCloud, and GitHub Advanced Security.
Generates standardized pytest suites for Home Assistant integrations to ensure compliance with official Quality Scale standards.
Evaluates system designs for robust authentication, authorization, data protection, and cryptographic correctness.
Implements robust testing strategies using pytest, mocking, and advanced parameterization for Python applications.
Generates comprehensive security threat models and data flow diagrams following Bitwarden's formal engagement framework.
Automates the discovery and manual testing of MCP tool schemas to ensure plugin reliability and performance within Claude Code.
Audits software dependencies and manages security vulnerabilities across supply chains using Dependabot and Grype.
Identifies hardcoded credentials, audits for potential leaks, and provides guided remediation workflows to secure sensitive information in codebases.
Automates the creation of Abstract Syntax Tree (AST) based checks to evaluate the quality and compliance of AI-generated Python code.
Audits project dependencies for license compatibility, traces PII for data privacy, and evaluates AI ethical standards.
Conducts deep-dive research into malware, vulnerabilities, and threat intelligence to inform technical narratives and documentation.
Audits codebases for OWASP Top 10 vulnerabilities, AI-specific risks, and dependency security flaws.
Validates Claude extensions and plugins across hooks, manifest schemas, and runtime environments to ensure deployment readiness.
Generates comprehensive unit, integration, and end-to-end tests to ensure code reliability and meet coverage targets.
Orchestrates and routes complex AI evaluation workflows, including error analysis, trace reviews, and live evaluation setup.
Enforces a strict test-driven development workflow using the Red-Green-Refactor cycle across multiple programming languages.
Designs, deploys, and integrates automated quality evaluations and guardrails for AI model outputs using Truesight MCP.
Applies a structured root cause investigation protocol to resolve failing tests and persistent code defects without guesswork.
Streamlines testing and development for Electrobun desktop applications through automated integration suites and interactive playgrounds.
Scroll for more results...