Create AI Temp — AI skill for Claude Code
create-ai-temp generates that foundation in one command.
How to install Create AI Temp
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open ruoduan-hub/create-ai-temp and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Create AI Temp does
create-ai-temp generates that foundation in one command. Choose a ready-to-run Next.js preset or a stack-neutral clean architecture, and get a shared Chinese .agent knowledge base with dedicated entry points for Codex, Claude Code, Gemini CLI, GitHub Copilot, and Cursor.
Alternatives in AI
- Agent Rules Books — AGENTS.md rules / skills for AI coding agents: Codex, Cursor & Claude Code 2.6k ★
- RAG Skill — A Skill dedicated to local knowledge base retrieval 712 ★
- Model Config — /model-config — Choose the model you follow 705 ★
README
create-ai-temp
**Scaffold modern frontend projects with an AI-ready knowledge base built in.**
[](https://www.npmjs.com/package/create-ai-temp) [](https://www.npmjs.com/package/create-ai-temp) [](https://github.com/ruoduan-hub/create-ai-temp/actions/workflows/publish.yml) [](https://www.npmjs.com/package/create-ai-temp) [](https://github.com/ruoduan-hub/create-ai-temp/blob/master/LICENSE)
English · [简体中文](https://github.com/ruoduan-hub/create-ai-temp/blob/master/docs/README.zh-CN.md)
Why create-ai-temp?
Starting a project is more than installing a framework. Your team—and the AI tools working with it—also need shared architecture, conventions, workflows, and context.
`create-ai-temp` generates that foundation in one command. Choose a ready-to-run Next.js preset or a stack-neutral clean architecture, and get a shared Chinese `.agent` knowledge base with dedicated entry points for Codex, Claude Code, Gemini CLI, GitHub Copilot, and Cursor.
Features
- AI-ready by default — shared project context, coding rules, workflows, and reusable task templates.
- Works across AI tools — dedicated instruction files point every supported assistant to the same source of truth.
- Two project modes — start with a modern frontend preset or a technology-agnostic clean structure.
- Layered architecture — clear boundaries for domain, application, infrastructure, presentation, and shared code.
- Interactive and scriptable — use guided prompts locally or explicit flags in automation.
- Package-manager aware — supports pnpm,
Related Skills
Vibe Stack
29 .mdc architecture rules that prevent AI coding assistants from hallucinating insecure auth, deprecated impo
Web Fetch
LLM-neutral skill that fetches a URL to a temp file so agents can pipe the path through rg / jq / awk instead
Agentic Agent Prompt Builder
A free, single-file builder for well-structured AI agent prompts. Pick a starting preset, fill in the parts yo
Translate Academic Paper
Translate academic papers & monographs (PDF) into a single self-contained bilingual HTML — Chinese/original/si
Context Attachment Manager
Codex and Claude Code plugin (works in Claude Desktop): choose which past images go to the model with your nex
Dot Agents
A home for the dot-folders I use with AI tools (.claude, .codex, .cursor, ...): agents, rules, skills, and wor
Related Agents
Osf Clean Room
Reads a feature inside a temp folder, extracts its behavior and test coverage as a source-free specification,
Poros
The ask lane of this project's pipeline — Poros, the scout ahead. Launch it to re-rank the frontier after a mi
Boundary Auditor
Read-only reviewer of the architectural boundaries: module/slice/feature isolation, schema and data ownership,