security & testing向けのClaudeスキルを発見してください。105個のスキルを閲覧し、AIワークフローに最適な機能を見つけましょう。
Audits Firebase projects for security vulnerabilities, architectural consistency, and adherence to production-ready best practices.
Enforces scenario-driven end-to-end testing using real dependencies and live data to ensure features are truly validated before completion.
Performs a systematic final sanity check after tests pass to catch security vulnerabilities, edge cases, and business logic errors before code is committed.
Standardizes Vue 3 component testing with best practices for mounting, asynchronous interactions, and state mocking.
Enforces a rigorous Red-Green-Refactor workflow by requiring mandatory failing tests and execution evidence before any production code is written.
Eliminates flaky tests by replacing arbitrary timeouts with intelligent condition polling and event-driven waiting patterns.
Implements a multi-layered validation strategy to eliminate data-driven failures and make bugs structurally impossible.
Analyzes websites to identify anti-bot vendors, challenge types, and the effectiveness of stealth vs. non-stealth browser modes.
Eliminates guesswork by enforcing a rigorous four-phase framework to identify root causes before implementing any code fixes.
Writes and organizes robust test suites for scientific Python packages using pytest and community best practices.
Encrypts and decrypts text messages using the classic ROT13 substitution cipher via bash scripts.
Exposes hidden architectural weaknesses and scalability bottlenecks by simulating system behavior at extreme scales.
Optimizes development and QA workflows by analyzing checklist effectiveness and identifying process gaps.
Scans Claude Code plugins and skills to detect malicious code, deceptive instructions, and unauthorized credential access.
Verifies AI agent reliability by running controlled failure simulations and scoring adherence to emergency procedures.
Resolves findings from QA code reviews by applying clean code refactoring and automated verification tests.
Performs comprehensive security audits of codebases, dependencies, and infrastructure using OWASP standards and architectural reviews.
Automates local web application testing and browser interaction using Playwright and lifecycle management scripts.
Conducts comprehensive pre-release audits with structured GO/NO-GO reports to ensure production quality.
Generates automated traceability matrices linking specifications to implementation and test coverage for IEEE 830 compliance.
Scans codebases for technical debt, dead code, and architectural violations to maintain long-term code hygiene.
Designs and implements rigorous evaluation frameworks for LLM agents, multi-agent systems, and prompts using industry-standard metrics.
Automatically analyzes codebase testing conventions and documents patterns to ensure consistent test implementation.
Automates post-implementation validation by running tests, linting, and build commands through a context-efficient sub-agent.
Implements a structured six-step debugging process to identify, isolate, and resolve software bugs while preventing future regressions.
Validates code integrity by performing automated linting and type checking to ensure high-quality, production-ready implementations.
Executes systematic security assessments on Linux systems to identify and exploit misconfigurations, vulnerable services, and privilege escalation vectors.
Ensures codebase integrity through automated type checking, linting, and formatting within the Claude Code environment.
Enforces a strict test-driven development lifecycle to ensure high code quality and minimum 80% test coverage.
Audits Python codebases for security vulnerabilities, performance bottlenecks, and architectural antipatterns to provide a comprehensive health score and remediation plan.
Scroll for more results...