腳本程式

Test Temporal workflows with pytest, time-skipping, and mocking strategies. Covers unit testing, integration testing, replay testing, and local development setup. Use when implementing Temporal workflow tests or debugging test failures.

Validates Claude skill files for correct structure, YAML frontmatter, Python imports, naming conventions, and compliance with official documentation

This skill should be used when improving existing Claude Code skills. Triggers include "improve this skill", "skill feels shallow", "upgrade skill", or when self-evaluating skill quality. Codifies the self-eval → research → rewrite → validate pattern.

This skill should be used when users want to create a new gallery project for the personal portfolio website. Trigger phrases include "create gallery project", "clone project", "add portfolio project", "new case study", "create new project", or when users want to add a project to the gallery section of the portfolio.

Reviews and improves code based on SOLID principles in object-oriented programming

Write minimal, evergreen code comments that explain complex logic without documenting obvious behavior or temporary changes. Use this skill when adding comments to PHP files, TypeScript/JavaScript files, or any code files, when documenting complex algorithms or business logic, when adding PHPDoc blocks or JSDoc comments, when writing self-documenting code with clear naming, or when reviewing existing comments for relevance and necessity. Focus on keeping code self-explanatory through clear structure and naming rather than relying heavily on comments.

Use when working with Ruby metaprogramming features including dynamic method definition, method_missing, class_eval, define_method, and reflection.

Implements JavaScript classes in C++ using JavaScriptCore. Use when creating new JS classes with C++ bindings, prototypes, or constructors.

Search and analyze code repositories on GitHub and Hugging Face (Models, Datasets, Spaces). This skill should be used when exploring open-source projects, finding implementation references, discovering ML models/datasets, or analyzing how others have solved similar problems.

Generate Zustand store files with TypeScript and middleware. Triggers on "create zustand store", "generate zustand state", "zustand slice", "state management".

Deployment procedures, health checks, and rollback strategies. Use this skill when deploying applications, performing health checks, managing releases, or handling deployment failures. Provides systematic deployment workflows, verification scripts, and troubleshooting guides. Complements the devops-automation agent.

This skill should be used when developing with the Hono web framework, including CLI tool usage, project scaffolding, routing, middleware configuration, testing, optimization, and deployment across multiple JavaScript runtimes (Cloudflare Workers, Deno, Bun, Vercel, AWS Lambda, Node.js)

Analyzes binary files for vulnerabilities and develops exploits. Use when working with ELF/PE executables, pwn challenges, buffer overflow, heap exploitation, ROP chains, format string bugs, or shellcode development.

Run Bandit security analysis to find common security issues and vulnerabilities in Python code. Use when the user mentions Bandit, security analysis, vulnerability scanning, security audit, software composition analysis (SCA), or wants to check for security issues in Python code.

Automate Chrome browser via DevTools Protocol. Use when user asks to scrape websites, take screenshots, generate PDFs, interact with web pages, extract content, fill forms, or automate browser tasks.

Initialize complete Python project with comprehensive documentation, development environment, and tooling. Use when creating a new Python project from scratch.

This skill should be used when users request research on a topic with the intent to save findings to a document. It provides a systematic workflow for conducting web research, synthesizing information from multiple sources, and creating well-structured documentation. Trigger words include "research and save", "look up and document", "find information about and write", or any request that combines information gathering with file creation.

Explains the standardized API organization pattern for this codebase. Use when creating new API endpoints, API clients, or modifying existing API structure. Covers the 5-file system (endpoint-types, endpoints, api-client, admin-api-client, protected-endpoints), role-based access patterns (admin vs regular users), and TypeScript type safety across the API layer. All API code lives in src/lib/api/ following this exact pattern.

Configures Claude Code permissions via natural language for CLI tools (git, gcloud, aws, kubectl, maven, gradle, npm, docker), project types (Rust, Java, TypeScript, Python), and file patterns. Use when asked to "configure permissions", "enable git", "allow docker", "setup project permissions", "apply permission profile", or "make files editable". Auto-detects project types and researches unknown tools.

Always search before starting any work across all coding agent session histories (Claude Code, Codex, Cursor, Gemini CLI, Aider, ChatGPT) to find whatever we've discussed before.