Vi Chan Terminal — Testing skill for Claude Code
♡ Vi-Chan Terminal: a kawaii, Claude-Code-style AI agent for your terminal.
How to install Vi Chan Terminal
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open JerenzeLevi/vi-chan-terminal and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Vi Chan Terminal does
♡ Vi-Chan Terminal: a kawaii, Claude-Code-style AI agent for your terminal. Bring any API key (OpenAI, Gemini, Claude, Ollama…) for file editing, shell commands, plan mode, MCP/Playwright, image generation, and Excel/Word/PowerPoint files.
Alternatives in Testing
- Pua — Use when the user invokes /pua or asks for PUA mode, try-harder/retry help, change-approach coaching, completi 19.5k ★
- Testing Strategy — This project is small, runs in a terminal, and is mostly deterministic 10.9k ★
- Debug — You are tasked with helping debug issues during manual testing or implementation 10k ★
README
Vi-Chan Terminal ♡
A kawaii, jolly, curious AI agent that lives in your terminal. Bring any AI's API key and Vi-Chan can read and edit your files, run commands, browse the web, make images and build Excel / Word / PowerPoint files, always asking before she changes anything.
/\_/\
( ˶•ᴗ•˶) Vi-Chan Terminal
> ♡ <
✨ ELI5: get her running in 3 steps
Think of Vi-Chan as a cute chat window that lets an AI help with your computer. She needs two things: **Python** (a free program that runs her) and an **API key** (a secret password that lets her talk to an AI).
**1. Install Python** (once): download it from [python.org/downloads](https://www.python.org/downloads/). On Windows, tick **"Add Python to PATH"** during install.
**2. Open a terminal and paste this** (Windows: search "Terminal" or "PowerShell"; Mac: search "Terminal"):
pip install git+https://github.com/JerenzeLevi/vi-chan-terminal.git
**3. Type `vichan` and press Enter.** She'll ask you to pick an AI, paste your API key, and choose a model. Then just talk to her! ♡
**What's an API key?** A long secret text you get from an AI company's website. It is *not* the same as a ChatGPT Plus or Claude Pro subscription; those don't include one. Get a key here (pay-as-you-go, cents for casual use):
- Google Gemini, has a free tier: aistudio.google.com/apikey
- OpenAI (ChatGPT models): platform.openai.com/api-keys
- Anthropic (Claude): console.anthropic.com
- OpenRouter (one key, many models): openrouter.ai/keys
- Ollama: no key at all, runs models on your own computer: ollama.com
Treat your key like a password. Never share it or post it online.
Stuck? Jump to [Troubleshooting](#-troubleshooting).
🛠 Technical install
**Requirements:** Python 3.9+, a terminal with UTF-8 /
Related Skills
AI Review Pipeline
AI code review pipeline — review, auto-fix, test generation & HTML report in one command. Zero dependencies, 6
Excalidraw Board
Free, editable Excalidraw diagrams from a JSON spec. Community icon libraries, no image model, no API key, no
Zames Pro
Terminal coding agent that drives chat.deepseek.com through Playwright — no API key required. Reads/edits file
Codex Skills
Five Codex CLI skills that give OpenAI Codex a Claude Code-style workflow (feature dev, PR review, browser tes
Static Ads Skill
I tried using it with some models that are considered as weak rn (gemini 3.8) against latest claude and openai
Pear Setup
Set up Pear by verifying your API key and testing the iCloud connection
Related Agents
ZeroClaw Android
Run AI agents 24/7 on your Android phone. Native Rust core, 25+ providers (OpenAI, Claude, Gemini, Groq, DeepS
AI ML
AI/ML 통합 전문가 + LLM API 최신 모델/SDK 코딩 가이드. RAG 시스템, 문서 분석, OpenAI/Anthropic/Gemini/Ollama 최신 API 보장. "AI integra
LLM Orchestrator
Use this agent for LLM integration work — prompt engineering, multi-provider abstraction (OpenRouter, Gemini,