VibeHarness: Skill for Claude Code

Python — AI, Data, Automation

Do not apply to Node.js web-only projects. Verify stack matches PROJECT_RULES.md. Record architecture decisions in docs/ai-dev/.

Stack by Project Type

Type	Stack	Install
AI/RAG/Chatbot	FastAPI + LangChain + ChromaDB	pip install fastapi uvicorn langchain openai chromadb
Data analysis	Streamlit + Pandas + Plotly	pip install streamlit pandas plotly
API server	FastAPI + SQLAlchemy	pip install fastapi uvicorn sqlalchemy
Automation	BeautifulSoup/Playwright	pip install beautifulsoup4 requests playwright

Initial Setup

python -m venv venv

# Mac/Linux:
source venv/bin/activate
# Windows:
venv\Scripts\activate

pip install -r requirements.txt

Always provide the correct activation command for the user's OS.

FastAPI Pattern

from fastapi import FastAPI
from fastapi.staticfiles import StaticFiles

app = FastAPI()
app.mount("/static", StaticFiles(directory="static"), name="static")

@app.get("/api/hello")
async def hello():
    return {"message": "Hello!"}

if __name__ == "__main__":
    import uvicorn
    uvicorn.run(app, host="0.0.0.0", port=8000)

Streamlit Pattern

import streamlit as st
import pandas as pd

st.title("Dashboard")
uploaded = st.file_uploader("Upload CSV", type="csv")
if uploaded:
    df = pd.read_csv(uploaded)
    st.dataframe(df)
    st.bar_chart(df)

SQLite + SQLAlchemy

from sqlalchemy import create_engine, Column, String, DateTime
from sqlalchemy.orm import declarative_base, sessionmaker

engine = create_engine("sqlite:///dev.db")
Base = declarative_base()
SessionLocal = sessionmaker(bind=engine)

Environment Variables

from dotenv import load_dotenv
import os
load_dotenv()
api_key = os.getenv("OPENAI_API_KEY")

Code Conventions

• snake_case (functions, variables), PascalCase (classes)
• Type hints required: def get_user(user_id: str) -> User:
• f-strings: f"Hello {name}"
• Pin versions in requirements.txt