create-plugin
について
このスキルは、標準的なディレクトリ構造と必須ファイルを備えた新しいClaudeプラグインの基盤を作成します。ClaudeKitモノレポ内でbunを使用し、プラグインを一から始める開発者向けに設計されています。プロセスには、プラグインディレクトリの作成、コアファイルの生成、マーケットプレイスメタデータの更新が含まれます。
クイックインストール
Claude Code
推奨/plugin add https://github.com/majiayu000/claude-skill-registrygit clone https://github.com/majiayu000/claude-skill-registry.git ~/.claude/skills/create-pluginこのコマンドをClaude Codeにコピー&ペーストしてスキルをインストールします
ドキュメント
Create Claude Plugin
When to Use This Skill
Use this skill when:
- Creating a new Claude Code plugin from scratch
- Setting up the standard plugin directory structure
- Adding a new plugin to the ClaudeKit marketplace
Trigger phrases:
- "create a new plugin"
- "scaffold a plugin for X"
- "add a plugin called X"
Instruction
- Use the
Globtool to check if plugin is existing - Use Ask Question Tool to confirm overwriting if plugin already exists
- Create a new directory for the plugin
- Create a minimal plugin structure for plugin
- Update the plugin metadata file with basic information
- Update root README.md to include the new plugin
- Update
.claude-plugin/marketplace.jsonto include the new plugin - Update release please config to include the new plugin
Plugin Structure
|- .claude-plugin/
|- plugin.json
|- commands/ # Omit if no commands
|- example.md
|- agents/ # Omit if no agents
|- example-agent.md
|- skills/ # Omit if no skills
|- example-skill/
|- SKILL.md
|- hooks/ # Omit if no hooks
|- hooks.json
|- src/ # Omit if no hook script is needed
|- example.ts
|- dist/ # Auto-generated, omit
|- example.js
|- README.md
|- rolldown.config.js # Omit if no src
|- package.json # Omit if no src
|- tsconfig.json # Omit if no src
The minimal plugin.json is
{
"name": "plugin-name",
"version": "0.1.0",
"description": "A brief description of the plugin",
"author": {
"name": "Author Name"
}
}
Reference
For detailed information on creating Claude plugins, refer to following documentation:
GitHub リポジトリ
関連スキル
evaluating-llms-harness
テストThis Claude Skill runs the lm-evaluation-harness to benchmark LLMs across 60+ standardized academic tasks like MMLU and GSM8K. It's designed for developers to compare model quality, track training progress, or report academic results. The tool supports various backends including HuggingFace and vLLM models.
sglang
メタSGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.
langchain
メタLangChain is a framework for building LLM applications using agents, chains, and RAG pipelines. It supports multiple LLM providers, offers 500+ integrations, and includes features like tool calling and memory management. Use it for rapid prototyping and deploying production systems like chatbots, autonomous agents, and question-answering services.
cloudflare-turnstile
メタThis skill provides comprehensive guidance for implementing Cloudflare Turnstile as a CAPTCHA-alternative bot protection system. It covers integration for forms, login pages, API endpoints, and frameworks like React/Next.js/Hono, while handling invisible challenges that maintain user experience. Use it when migrating from reCAPTCHA, debugging error codes, or implementing token validation and E2E tests.
