Claude Skills

Master defensive Bash programming techniques for production-grade scripts. Use when writing robust shell scripts, CI/CD pipelines, or system utilities requiring fault tolerance and safety.

Spawn a Claude worker to address PR feedback, fix CI failures, or continue work on a pull request. Use when a PR needs updates based on review comments or failing checks.

Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production prompt templates.

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

Use when creating skills, writing SKILL.md files, editing skill definitions, or adding new reusable techniques to ai-coding-config

Master authentication and authorization patterns including JWT, OAuth2, session management, and RBAC to build secure, scalable access control systems. Use when implementing auth systems, securing APIs, or debugging security issues.

Manage NuGet packages in .NET projects/solutions. Use this skill when adding, removing, or updating NuGet package versions. It enforces using `dotnet` CLI for package management and provides strict procedures for direct file edits only when updating versions.

作業フローや手順を分析し、自動化可能な要素を特定する。ワークフロー分析時、自動化検討時、業務プロセス改善時、またはユーザーが作業フロー分析、自動化要素、業務手順、プロセス最適化に言及した際に使用する。

Trace a single concept's paper lineage in detail. Use when user says "trace [concept]", "where did [concept] come from", "[concept] paper history", "[concept] lineage", or wants deep genealogy of one specific concept.

複雑な作業を単一目的の小さなタスクに分解する。タスク分解時、作業細分化時、スキル設計時、またはユーザーがタスク分解、作業分割、細分化、単一目的、タスク粒度に言及した際に使用する。

Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.

Create commit messages following conventional commit conventions. Use when committing code changes, writing commit messages, or formatting git history. Follows conventional commits with issue references.

ReactUMG 常见组件陷阱/坑/问题提醒。在使用 ComboBoxString、EditableTextBox、SpinBox、ScrollBox、ProgressBar 等复杂组件时激活。涵盖动态选项不生效、ref 回调重复调用、深色主题配置等常见问题的解决方案。

Click framework examples and templates - decorators, nested commands, parameter validation. Use when building Python CLI with Click, implementing command groups, adding CLI options/arguments, validating CLI parameters, creating nested subcommands, or when user mentions Click framework, @click decorators, command-line interface.

ReactUMG 完整开发知识库。仅供 PlanReactUMG 和 DebugReactUMG Agent 显式调用，不应在日常开发中直接激活。包含所有开发规则、代码示例和最佳实践的详细参考文档。

ReactUMG 对齐/居中与可见性/显隐枚举值速查。在设置水平对齐、垂直对齐、HorizontalAlignment、VerticalAlignment、Visibility、隐藏/显示组件时激活。注意 Center=2（不是1）、Visible=0、Collapsed=1 等常见混淆点。

ユーザーに質問を投げかけるアシスタント。AskUserQuestionツールを使って選択肢付きの質問を提示します。