MCP HubMCP Hub
スキル一覧に戻る

cube-iml

majiayu000
更新日 2 days ago
18 閲覧
58
9
58
GitHubで表示
テストaitesting

について

このスキルは、Pythonのインポート解決が失敗した場合やフォルダが認識されない場合に、PyCharm/IntelliJのモジュール設定(.imlファイル)をチェックして修復します。`/cube-iml`コマンドを通じて、またはユーザーがIDE設定の問題を報告した際に起動できます。このツールはXML構造を検証し、開発ワークフローに適したソースフォルダ設定を保証します。

クイックインストール

Claude Code

推奨
プラグインコマンド推奨
/plugin add https://github.com/majiayu000/claude-skill-registry
Git クローン代替
git clone https://github.com/majiayu000/claude-skill-registry.git ~/.claude/skills/cube-iml

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

Cube IML Skill

Check and repair the PyCharm/IntelliJ module configuration file.

Trigger

Use when:

  • User runs /cube-iml or asks about PyCharm/IntelliJ configuration
  • User reports "module not configured" or import resolution issues
  • User says PyCharm doesn't recognize src or tests folders

Quick Check

Run this Python snippet to check the .iml file:

python -c "
from pathlib import Path
from xml.etree import ElementTree as ET

iml = Path('.idea/cube.iml')
if not iml.exists():
    print('MISSING: .idea/cube.iml does not exist')
    exit(1)

try:
    tree = ET.parse(iml)
    root = tree.getroot()
except ET.ParseError as e:
    print(f'CORRUPTED: XML parse error: {e}')
    exit(1)

# Check required elements
sources = tree.findall('.//sourceFolder')
has_src = any('src' in s.get('url', '') and s.get('isTestSource') == 'false' for s in sources)
has_tests = any('tests' in s.get('url', '') and s.get('isTestSource') == 'true' for s in sources)
has_sdk = tree.find('.//orderEntry[@type=\"jdk\"]') is not None

issues = []
if not has_src:
    issues.append('Missing src as source folder')
if not has_tests:
    issues.append('Missing tests as test source folder')
if not has_sdk:
    issues.append('Missing Python SDK configuration')

if issues:
    print('INCOMPLETE:')
    for i in issues:
        print(f'  - {i}')
    exit(1)

print('OK: cube.iml is valid and complete')
"

Actions Based on Result

If MISSING or CORRUPTED or INCOMPLETE

Ask the user:

The .idea/cube.iml file is [missing/corrupted/incomplete].

Would you like me to reconstruct it?
- Yes, reconstruct it
- No, I'll fix it manually

If user says yes, run:

python scripts/reconstruct_iml.py

If OK

Report: "PyCharm configuration looks good. If you're still having issues, try:

  1. File → Invalidate Caches and Restart
  2. Right-click src folder → Mark Directory as → Sources Root"

Manual Fix

If the script doesn't exist or fails, create the file manually:

<?xml version="1.0" encoding="UTF-8"?>
<module type="PYTHON_MODULE" version="4">
  <component name="NewModuleRootManager">
    <content url="file://$MODULE_DIR$">
      <sourceFolder url="file://$MODULE_DIR$/src" isTestSource="false" />
      <sourceFolder url="file://$MODULE_DIR$/tests" isTestSource="true" />
    </content>
    <orderEntry type="jdk" jdkName="Python 3.14 (cubesolve)" jdkType="Python SDK" />
    <orderEntry type="sourceFolder" forTests="false" />
  </component>
</module>

Adjust the jdkName to match the user's Python interpreter name.

GitHub リポジトリ

majiayu000/claude-skill-registry
パス: skills/cube-iml

関連スキル

content-collections

メタ

This skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.

スキルを見る

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.

スキルを見る

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.

スキルを見る

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.

スキルを見る