aigroup-workflow 2.1.1 → 2.2.0

package/skills/python/fastapi-expert/references/pydantic-v2.md

@@ -0,0 +1,135 @@
+# Pydantic V2 Schemas
+
+## Schema Patterns
+
+```python
+from pydantic import BaseModel, EmailStr, Field, field_validator, model_validator
+from typing import Self
+
+class UserCreate(BaseModel):
+    email: EmailStr
+    password: str = Field(min_length=8)
+    username: str = Field(min_length=3, max_length=50)
+    age: int = Field(ge=18, le=120)
+
+    @field_validator('password')
+    @classmethod
+    def validate_password(cls, v: str) -> str:
+        if not any(c.isupper() for c in v):
+            raise ValueError('Password must contain uppercase')
+        if not any(c.isdigit() for c in v):
+            raise ValueError('Password must contain digit')
+        return v
+
+    @field_validator('username')
+    @classmethod
+    def validate_username(cls, v: str) -> str:
+        if not v.isalnum():
+            raise ValueError('Username must be alphanumeric')
+        return v.lower()
+
+class UserUpdate(BaseModel):
+    email: EmailStr | None = None
+    username: str | None = Field(None, min_length=3, max_length=50)
+```
+
+## ORM Mode (from_attributes)
+
+```python
+class UserResponse(BaseModel):
+    model_config = {"from_attributes": True}
+
+    id: int
+    email: EmailStr
+    username: str
+    is_active: bool = True
+    created_at: datetime
+
+# Usage with SQLAlchemy model
+user_response = UserResponse.model_validate(db_user)
+```
+
+## Model Validator
+
+```python
+class OrderCreate(BaseModel):
+    items: list[OrderItem]
+    discount_code: str | None = None
+    total: float
+
+    @model_validator(mode='after')
+    def validate_order(self) -> Self:
+        calculated = sum(item.price * item.quantity for item in self.items)
+        if abs(self.total - calculated) > 0.01:
+            raise ValueError('Total does not match items')
+        return self
+```
+
+## Nested Models
+
+```python
+class Address(BaseModel):
+    street: str
+    city: str
+    country: str = Field(default="US")
+
+class UserWithAddress(BaseModel):
+    name: str
+    addresses: list[Address] = Field(default_factory=list)
+```
+
+## Serialization Control
+
+```python
+class User(BaseModel):
+    model_config = {
+        "from_attributes": True,
+        "json_schema_extra": {
+            "example": {"email": "user@example.com", "username": "johndoe"}
+        }
+    }
+
+    id: int
+    email: EmailStr
+    password: str = Field(exclude=True)  # Never serialize
+    internal_id: str = Field(repr=False)  # Hide from repr
+
+# Serialize with aliases
+class ApiResponse(BaseModel):
+    model_config = {"populate_by_name": True}
+
+    user_id: int = Field(alias="userId", serialization_alias="user_id")
+```
+
+## Settings (Pydantic V2)
+
+```python
+from pydantic_settings import BaseSettings, SettingsConfigDict
+
+class Settings(BaseSettings):
+    model_config = SettingsConfigDict(
+        env_file=".env",
+        env_file_encoding="utf-8",
+        case_sensitive=True,
+    )
+
+    DATABASE_URL: str
+    SECRET_KEY: str
+    DEBUG: bool = False
+    CORS_ORIGINS: list[str] = ["http://localhost:3000"]
+    API_V1_PREFIX: str = "/api/v1"
+
+settings = Settings()
+```
+
+## Quick Reference
+
+| V1 Syntax | V2 Syntax |
+|-----------|-----------|
+| `@validator` | `@field_validator` |
+| `@root_validator` | `@model_validator` |
+| `class Config` | `model_config = {}` |
+| `orm_mode = True` | `from_attributes = True` |
+| `Optional[X]` | `X \| None` |
+| `.dict()` | `.model_dump()` |
+| `.parse_obj()` | `.model_validate()` |

package/skills/python/fastapi-expert/references/testing-async.md

@@ -0,0 +1,159 @@
+# Async Testing
+
+## Test Setup
+
+```python
+import pytest
+from httpx import AsyncClient, ASGITransport
+from sqlalchemy.ext.asyncio import create_async_engine, AsyncSession, async_sessionmaker
+
+from app.main import app
+from app.core.deps import get_db
+from app.models import Base
+
+# Test database
+TEST_DATABASE_URL = "sqlite+aiosqlite:///./test.db"
+test_engine = create_async_engine(TEST_DATABASE_URL, echo=True)
+test_session = async_sessionmaker(test_engine, expire_on_commit=False)
+
+@pytest.fixture(scope="session")
+def anyio_backend():
+    return "asyncio"
+
+@pytest.fixture(scope="function")
+async def db():
+    async with test_engine.begin() as conn:
+        await conn.run_sync(Base.metadata.create_all)
+    async with test_session() as session:
+        yield session
+    async with test_engine.begin() as conn:
+        await conn.run_sync(Base.metadata.drop_all)
+
+@pytest.fixture
+async def client(db: AsyncSession):
+    def override_get_db():
+        return db
+
+    app.dependency_overrides[get_db] = override_get_db
+    async with AsyncClient(
+        transport=ASGITransport(app=app),
+        base_url="http://test"
+    ) as ac:
+        yield ac
+    app.dependency_overrides.clear()
+```
+
+## Endpoint Tests
+
+```python
+@pytest.mark.asyncio
+async def test_create_user(client: AsyncClient):
+    response = await client.post("/api/v1/users/", json={
+        "email": "test@example.com",
+        "username": "testuser",
+        "password": "Test1234"
+    })
+    assert response.status_code == 201
+    data = response.json()
+    assert data["email"] == "test@example.com"
+    assert "password" not in data
+
+@pytest.mark.asyncio
+async def test_get_user_not_found(client: AsyncClient):
+    response = await client.get("/api/v1/users/999")
+    assert response.status_code == 404
+
+@pytest.mark.asyncio
+async def test_list_users(client: AsyncClient, auth_headers: dict):
+    response = await client.get("/api/v1/users/", headers=auth_headers)
+    assert response.status_code == 200
+    assert isinstance(response.json(), list)
+```
+
+## Auth Helper Fixture
+
+```python
+@pytest.fixture
+async def test_user(db: AsyncSession) -> User:
+    user = User(
+        email="auth@test.com",
+        username="authuser",
+        hashed_password=hash_password("Test1234"),
+    )
+    db.add(user)
+    await db.commit()
+    await db.refresh(user)
+    return user
+
+@pytest.fixture
+async def auth_headers(test_user: User) -> dict:
+    token = create_access_token(sub=str(test_user.id))
+    return {"Authorization": f"Bearer {token}"}
+
+@pytest.mark.asyncio
+async def test_protected_endpoint(client: AsyncClient, auth_headers: dict):
+    response = await client.get("/api/v1/users/me", headers=auth_headers)
+    assert response.status_code == 200
+
+@pytest.mark.asyncio
+async def test_protected_endpoint_no_auth(client: AsyncClient):
+    response = await client.get("/api/v1/users/me")
+    assert response.status_code == 401
+```
+
+## Service Tests
+
+```python
+@pytest.mark.asyncio
+async def test_create_user_service(db: AsyncSession):
+    user_in = UserCreate(
+        email="service@test.com",
+        username="serviceuser",
+        password="Test1234"
+    )
+    user = await create_user_db(db, user_in)
+
+    assert user.id is not None
+    assert user.email == "service@test.com"
+
+@pytest.mark.asyncio
+async def test_get_user_not_found_service(db: AsyncSession):
+    user = await get_user_db(db, 999)
+    assert user is None
+
+@pytest.mark.asyncio
+async def test_duplicate_email(db: AsyncSession):
+    user_in = UserCreate(email="dup@test.com", username="user1", password="Test1234")
+    await create_user_db(db, user_in)
+
+    with pytest.raises(IntegrityError):
+        user_in2 = UserCreate(email="dup@test.com", username="user2", password="Test1234")
+        await create_user_db(db, user_in2)
+```
+
+## Mocking Dependencies
+
+```python
+from unittest.mock import AsyncMock, patch
+
+@pytest.mark.asyncio
+async def test_with_mock_service(client: AsyncClient):
+    mock_user = User(id=1, email="mock@test.com", username="mock")
+
+    with patch("app.api.v1.users.get_user_db", new_callable=AsyncMock) as mock:
+        mock.return_value = mock_user
+        response = await client.get("/api/v1/users/1")
+        assert response.status_code == 200
+        assert response.json()["email"] == "mock@test.com"
+```
+
+## Quick Reference
+
+| Component | Purpose |
+|-----------|---------|
+| `@pytest.mark.asyncio` | Mark async test |
+| `AsyncClient` | HTTP client |
+| `ASGITransport(app=app)` | Test transport |
+| `app.dependency_overrides` | Override deps |
+| `AsyncMock` | Mock async functions |
+| `pytest.raises()` | Assert exception |

package/skills/python/pandas-pro/SKILL.md

@@ -0,0 +1,178 @@
+---
+name: pandas-pro
+description: Performs pandas DataFrame operations for data analysis, manipulation, and transformation. Use when working with pandas DataFrames, data cleaning, aggregation, merging, or time series analysis. Invoke for data manipulation tasks such as joining DataFrames on multiple keys, pivoting tables, resampling time series, handling NaN values with interpolation or forward-fill, groupby aggregations, type conversion, or performance optimization of large datasets.
+license: MIT
+metadata:
+  author: https://github.com/Jeffallan
+  version: "1.1.0"
+  domain: data-ml
+  triggers: pandas, DataFrame, data manipulation, data cleaning, aggregation, groupby, merge, join, time series, data wrangling, pivot table, data transformation
+  role: expert
+  scope: implementation
+  output-format: code
+  related-skills: python-pro
+---
+
+# Pandas Pro
+
+Expert pandas developer specializing in efficient data manipulation, analysis, and transformation workflows with production-grade performance patterns.
+
+## Core Workflow
+
+1. **Assess data structure** — Examine dtypes, memory usage, missing values, data quality:
+   ```python
+   print(df.dtypes)
+   print(df.memory_usage(deep=True).sum() / 1e6, "MB")
+   print(df.isna().sum())
+   print(df.describe(include="all"))
+   ```
+2. **Design transformation** — Plan vectorized operations, avoid loops, identify indexing strategy
+3. **Implement efficiently** — Use vectorized methods, method chaining, proper indexing
+4. **Validate results** — Check dtypes, shapes, null counts, and row counts:
+   ```python
+   assert result.shape[0] == expected_rows, f"Row count mismatch: {result.shape[0]}"
+   assert result.isna().sum().sum() == 0, "Unexpected nulls after transform"
+   assert set(result.columns) == expected_cols
+   ```
+5. **Optimize** — Profile memory, apply categorical types, use chunking if needed
+
+## Reference Guide
+
+Load detailed guidance based on context:
+
+| Topic | Reference | Load When |
+|-------|-----------|-----------|
+| DataFrame Operations | `references/dataframe-operations.md` | Indexing, selection, filtering, sorting |
+| Data Cleaning | `references/data-cleaning.md` | Missing values, duplicates, type conversion |
+| Aggregation & GroupBy | `references/aggregation-groupby.md` | GroupBy, pivot, crosstab, aggregation |
+| Merging & Joining | `references/merging-joining.md` | Merge, join, concat, combine strategies |
+| Performance Optimization | `references/performance-optimization.md` | Memory usage, vectorization, chunking |
+
+## Code Patterns
+
+### Vectorized Operations (before/after)
+
+```python
+# ❌ AVOID: row-by-row iteration
+for i, row in df.iterrows():
+    df.at[i, 'tax'] = row['price'] * 0.2
+
+# ✅ USE: vectorized assignment
+df['tax'] = df['price'] * 0.2
+```
+
+### Safe Subsetting with `.copy()`
+
+```python
+# ❌ AVOID: chained indexing triggers SettingWithCopyWarning
+df['A']['B'] = 1
+
+# ✅ USE: .loc[] with explicit copy when mutating a subset
+subset = df.loc[df['status'] == 'active', :].copy()
+subset['score'] = subset['score'].fillna(0)
+```
+
+### GroupBy Aggregation
+
+```python
+summary = (
+    df.groupby(['region', 'category'], observed=True)
+    .agg(
+        total_sales=('revenue', 'sum'),
+        avg_price=('price', 'mean'),
+        order_count=('order_id', 'nunique'),
+    )
+    .reset_index()
+)
+```
+
+### Merge with Validation
+
+```python
+merged = pd.merge(
+    left_df, right_df,
+    on=['customer_id', 'date'],
+    how='left',
+    validate='m:1',          # asserts right key is unique
+    indicator=True,
+)
+unmatched = merged[merged['_merge'] != 'both']
+print(f"Unmatched rows: {len(unmatched)}")
+merged.drop(columns=['_merge'], inplace=True)
+```
+
+### Missing Value Handling
+
+```python
+# Forward-fill then interpolate numeric gaps
+df['price'] = df['price'].ffill().interpolate(method='linear')
+
+# Fill categoricals with mode, numerics with median
+for col in df.select_dtypes(include='object'):
+    df[col] = df[col].fillna(df[col].mode()[0])
+for col in df.select_dtypes(include='number'):
+    df[col] = df[col].fillna(df[col].median())
+```
+
+### Time Series Resampling
+
+```python
+daily = (
+    df.set_index('timestamp')
+    .resample('D')
+    .agg({'revenue': 'sum', 'sessions': 'count'})
+    .fillna(0)
+)
+```
+
+### Pivot Table
+
+```python
+pivot = df.pivot_table(
+    values='revenue',
+    index='region',
+    columns='product_line',
+    aggfunc='sum',
+    fill_value=0,
+    margins=True,
+)
+```
+
+### Memory Optimization
+
+```python
+# Downcast numerics and convert low-cardinality strings to categorical
+df['category'] = df['category'].astype('category')
+df['count'] = pd.to_numeric(df['count'], downcast='integer')
+df['score'] = pd.to_numeric(df['score'], downcast='float')
+print(df.memory_usage(deep=True).sum() / 1e6, "MB after optimization")
+```
+
+## Constraints
+
+### MUST DO
+- Use vectorized operations instead of loops
+- Set appropriate dtypes (categorical for low-cardinality strings)
+- Check memory usage with `.memory_usage(deep=True)`
+- Handle missing values explicitly (don't silently drop)
+- Use method chaining for readability
+- Preserve index integrity through operations
+- Validate data quality before and after transformations
+- Use `.copy()` when modifying subsets to avoid SettingWithCopyWarning
+
+### MUST NOT DO
+- Iterate over DataFrame rows with `.iterrows()` unless absolutely necessary
+- Use chained indexing (`df['A']['B']`) — use `.loc[]` or `.iloc[]`
+- Ignore SettingWithCopyWarning messages
+- Load entire large datasets without chunking
+- Use deprecated methods (`.ix`, `.append()` — use `pd.concat()`)
+- Convert to Python lists for operations possible in pandas
+- Assume data is clean without validation
+
+## Output Templates
+
+When implementing pandas solutions, provide:
+1. Code with vectorized operations and proper indexing
+2. Comments explaining complex transformations
+3. Memory/performance considerations if dataset is large
+4. Data validation checks (dtypes, nulls, shapes)