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。
Resolves complex technical issues using a rigorous four-phase methodology focused on root-cause identification rather than quick fixes.
Manages Fail2Ban intrusion prevention within SWAG reverse proxy containers to secure homelab infrastructure and web services.
Configures automated contract testing, Arazzo workflows, and integration tests for Speakeasy-generated SDKs.
Validates Claude Code plugin integrity and applies safe automatic fixes for structure, agents, and skill configurations.
Automates security audits for Claude Code plugins using vulnerability patterns, secret scanning, and OWASP-aligned checklists.
Validates PopKit plugins against official Claude Code patterns and Anthropic engineering standards through automated script-based checks.
Implements robust testing for scientific Python packages using pytest best practices and community-standard guidelines.
Validates software implementations against structured specifications using six mandatory quality gates and automated proof verification.
Enforces a strict Red-Green-Refactor workflow to ensure high-quality, bug-free production code through test-first development.
Routes users to specialized security architecture skills including threat modeling, compliance mapping, and secure design patterns.
Provides secure, ephemeral E2B sandboxes for isolated code execution and multi-agent swarm orchestration within Claude Code.
Performs expert-level security audits, vulnerability assessments, and compliance mapping using industry standards like OWASP and CVSS v3.1.
Verifies the functionality of the OpenCode Skills Plugin API through script execution, file reading, and skill discovery.
Performs objective, isolated verification of static analysis rule changes against specifications to ensure compliance and stability.
Generates and refines standardized static analysis rule specifications for the Inspequte JVM analysis tool.
Integrates the Codex CLI with Claude Code to automate testing, debugging, and complex code analysis using gpt-5-codex.
Provides a malformed skill configuration to test naming convention validation and linting logic within Claude Code.
Provides a standardized skill template used for validating and testing Claude Code plugin integrations.
Evaluates architectural quality, catalogs technical debt, and generates risk-based improvement roadmaps for legacy and complex codebases.
Evaluates and improves security patches with senior-level expertise in vulnerability remediation, secure coding patterns, and regression prevention.
Empowers developers to design, validate, and implement tailored security linting rules using Semgrep and Bandit syntax.
Audits and optimizes Neovim configurations by detecting deprecated APIs, validating best practices, and performing health checks.
Enforces integration testing against real local services like databases, caches, and queues to catch bugs that mocks miss.
Enforces strict compliance standards by blocking pull request creation until all code review requirements and security checks are satisfied.
Conducts mandatory OWASP-aligned security audits for sensitive code changes involving authentication, APIs, and databases.
Implements property-based testing to validate complex business logic invariants across all possible input ranges.
Diagnoses and resolves complex Claude Agent SDK errors, TypedDict contract mismatches, and MCP server serialization failures.
Enforces a strict Red-Green-Refactor workflow to ensure high-quality code through mandatory failing tests before implementation.
Streamlines Elixir testing by automating ExUnit test generation and execution with structured JSON reporting.
Enforces rigorous evidence-based reporting by requiring fresh verification command output before any task is marked as finished.
Scroll for more results...