すべてのClaudeスキルを閲覧

BusyBox for Windows

Equips Windows environments with standard UNIX command-line tools using a lightweight BusyBox binary.

SQL Injection Security Testing

Performs comprehensive SQL injection vulnerability assessments to identify, exploit, and remediate database security flaws in web applications.

Adaptive AI Behavioral Modes

Optimizes AI responses by switching between specialized operational modes tailored for brainstorming, implementation, debugging, and shipping.

Paid Ads Performance Marketer

Optimizes and manages performance marketing campaigns across Google Ads, Meta, LinkedIn, and other major advertising platforms.

Kaizen: Continuous Code Improvement

Enhances code quality and reliability through incremental improvements, error-proofing design patterns, and standardized development workflows.

Git Push Workflow

Automates the process of staging, committing with conventional messages, and pushing code to remote repositories.

AI Agent Engineering Advisor

Provides strategic guidance on building, evaluating, and iterating on AI agents using industry-standard frameworks.

Page Conversion Optimizer

Analyzes marketing pages to provide actionable recommendations for improving conversion rates and user engagement.

Red Team Tactics & Adversary Simulation

Implements structured adversary simulation principles and security audit workflows based on the MITRE ATT&CK framework.

Kaizen Code Quality & Improvement

Enhances software quality through continuous incremental improvements, error-proofing patterns, and standardized development workflows.

German Business Communication Toolkit

Drafts professional German project updates and stakeholder communications with a focus on conciseness and impact.

Shopify Development

Builds and manages Shopify apps, custom extensions, and Liquid themes using the latest GraphQL APIs and CLI tools.

Performance Profiling

Measures, analyzes, and optimizes web application performance using Core Web Vitals and advanced profiling techniques.

Langfuse Score Analytics

Analyzes LLM performance metrics and score trends directly within Claude Code using Langfuse observability data.

Compound Improvement Cycle

Implements a continuous learning framework that transforms daily tasks into reusable knowledge and system improvements.

Popup & Modal CRO Expert

Optimizes website popups, modals, and overlays to increase conversion rates while maintaining a high-quality user experience.

PDF Processing Toolkit

Simplifies complex PDF operations including text extraction, document merging, form filling, and programmatic document generation.

Canvas Art & Design Philosophy

Generates museum-quality visual art and professional design philosophies through meticulous spatial and chromatic orchestration.

SSH Penetration Testing

Conducts end-to-end SSH security audits, from initial service discovery and credential testing to advanced tunneling and post-exploitation analysis.

Codex Review

Automates professional code reviews and generates comprehensive changelogs using Codex AI integration.

Behavioral Modes

Optimizes AI performance by switching between specialized operational modes like brainstorming, implementing, debugging, and reviewing.

Web App Testing Toolkit

Automates and tests local web applications using Playwright to verify functionality, debug UI behavior, and capture browser logs.

Lint and Validate

Automates code quality control, static analysis, and type checking to ensure every modification meets production standards.

Launch Strategy & Go-To-Market

Provides comprehensive strategic planning and execution frameworks for SaaS product launches and feature announcements.

Systematic Debugging

Enforces a rigorous four-phase protocol to identify root causes and implement verified fixes for complex software bugs.

Red Team Tactics

Guides adversary simulation and security posture validation using the MITRE ATT&CK framework.

Network Services & Pen-Test Lab Setup

Configures and tests network services like HTTP, HTTPS, SNMP, and SMB for security research and penetration testing environments.

Langfuse Agent Evaluation Setup

Automates the end-to-end setup of evaluation pipelines for AI agents using Langfuse observability and datasets.

Doc Co-Authoring

Guides users through a structured, three-stage workflow to co-author high-quality technical documentation and proposals.

SSH Penetration Testing

Conducts comprehensive SSH security assessments including enumeration, credential attacks, and vulnerability exploitation for hardened network environments.