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。
Generates custom Semgrep rules to detect security vulnerabilities and logic bugs within source code.
Performs high-speed static analysis and security scanning to identify vulnerabilities and enforce custom code patterns.
Enforces maximal security isolation for Signal authentication using nested VM and container boundaries with colored operad constraints.
Verifies Strong Parallelism Invariance (SPI) and GF(3) conservation across deterministic data streams to ensure execution-order independence.
Automates browser-based regression testing using a modular Playwright framework and reusable test skills.
Verifies Strong Parallelism Invariance and GF(3) conservation to ensure deterministic execution across parallel 3-way color streams.
Ensures mathematical consistency and execution order invariance for deterministic color streams and tripartite data.
Performs rigorous security audits and bug detection on local code changes using a structured multi-phase review process.
Parses and analyzes Static Analysis Results Interchange Format (SARIF) files to streamline security vulnerability management and tool integration.
Validates infrastructure-as-code configurations using the native Terraform testing framework and .tftest.hcl patterns.
Tests Tizen application sandboxes for privilege escalation and escape vulnerabilities to ensure robust process isolation.
Executes untrusted code and system commands in secure, isolated microVMs to protect the host environment.
Automates higher-dimensional formal verification and version control using observational type theory and hierarchical agent structures.
Implements production-ready security patterns to protect web applications against common vulnerabilities like XSS, CSRF, and SQL injection.
Audits Python source code for PEP8 compliance, modern type hints, and architectural anti-patterns using industry-standard tooling.
Integrates GitHub Copilot's advanced coding capabilities into Claude for high-performance code analysis, debugging, and refactoring.
Streamlines smart contract validation using Hardhat and Foundry to ensure secure, gas-efficient, and production-ready blockchain code.
Verifies and synchronizes behavioral equivalence across AI agents using formal game-theoretic frameworks.
Enforces a strict Red-Green-Refactor cycle for software development tasks using automated gate hooks and evidence tracking.
Implements rigorous evaluation frameworks and testing patterns for AI agents based on Anthropic's engineering standards.
Performs deep-dive security audits and vulnerability assessments across diverse technology stacks to identify and remediate risks.
Generates formal Lean 4 proof chains using a GF(3)-balanced triad of agents for sound mathematical verification.
Validates the quality and architecture of written tests using the specialized BMAD TEA agent.
Designs comprehensive test scenarios and architecture ahead of development to ensure robust software quality and coverage.
Automates web browsers using deterministic seed-based state derivation to eliminate flaky tests and race conditions.
Validates software implementation against non-functional requirements to ensure architectural integrity and performance standards.
Automatically unlocks Bitwarden vaults and injects project-specific secrets directly into your development environment.
Generates comprehensive test automation frameworks and architectural setups for agile software development.
Initializes production-ready test framework architectures to ensure robust software quality and scalable validation structures.
Maps project requirements to test cases to ensure comprehensive coverage and informed quality gate decisions.
Scroll for more results...