From zh-en-relay
Relay complex Chinese user requests through English task prompts and translate final English-facing answers back into Chinese. Use when the user writes Chinese for coding, debugging, architecture, planning, long-form documentation, research, multi-step tasks, or requests involving files, paths, commands, code, logs, schemas, APIs, or tooling. Do not use for greetings, short confirmations, simple status checks, purely English requests, or when the user explicitly asks for the original language.
How this skill is triggered — by the user, by Claude, or both
Slash command
/zh-en-relay:zh-en-relayThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill to reduce ambiguity when a Chinese user request would benefit from an English task prompt, while still answering the user in Chinese.
Use this skill to reduce ambiguity when a Chinese user request would benefit from an English task prompt, while still answering the user in Chinese.
Use the relay for complex Chinese requests:
Skip the relay for greetings, simple confirmations, short status questions, tiny clarifications, purely English requests, or when the user asks to keep output in English or another original language.
The translation relay must not perform task planning, code edits, file reads, tool calls, validation, research, or implementation. It only conveys meaning between the user and the main agent.
The main agent owns all task execution, decisions, file changes, verification, and final accountability.
When the platform provides subagents and current tool policy permits them:
zh-to-en-prompt-relay to convert Chinese user requests into English prompts.en-to-zh-output-relay to translate final answers into Chinese.If subagents are unavailable or current tool instructions restrict their use, perform the same relay internally while keeping the translation and execution phases separate.
For Chinese to English:
For English to Chinese:
Provides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub kamisato520/zh-en-relay-skills --plugin zh-en-relay