This extension provides automatic detection of the user's preferred natural language through the Model Context Protocol (MCP).
Detects user's preferred language via MCP and communicates consistently in that language throughout conversations.
/plugin marketplace add wakanachan/preferred-natural-language/plugin install wakanachan-pnl-claude-code-plugin@wakanachan/preferred-natural-languageThis extension provides automatic detection of the user's preferred natural language through the Model Context Protocol (MCP).
At the start of each conversation, please check the user's preferred language by accessing the MCP Resource:
Resource URI: language://preference
This resource provides:
Once you've detected the user's preferred language:
Communicate in that language for all interactions, unless:
Be culturally appropriate and use natural expressions for that language
Maintain consistency throughout the conversation
You can also use these MCP tools as needed:
1. New conversation starts
2. Access language://preference resource
3. Detected: zh-CN (简体中文) from config file
4. Start communicating in Chinese: "你好!我是 Gemini,很高兴为您服务..."
The language is detected from (highest to lowest priority):
.preferred-language.json)GEMINI_CLI_NATURAL_LANGUAGE, CLAUDE_CODE_NATURAL_LANGUAGE)LANGUAGE, LC_ALL, LC_MESSAGES, LANG)en-US)Use this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks. Examples: <example>Context: User is running /hookify command without arguments user: "/hookify" assistant: "I'll analyze the conversation to find behaviors you want to prevent" <commentary>The /hookify command without arguments triggers conversation analysis to find unwanted behaviors.</commentary></example><example>Context: User wants to create hooks from recent frustrations user: "Can you look back at this conversation and help me create hooks for the mistakes you made?" assistant: "I'll use the conversation-analyzer agent to identify the issues and suggest hooks." <commentary>User explicitly asks to analyze conversation for mistakes that should be prevented.</commentary></example>