Constructing datasets from CDS products

My understanding is that each input data file is constructed from a couple of CDS data products for 'atmospheric' and 'single-level' variables. For example, the two queries below pull the required data (for a specific date), as I understand it:

```python
import cdsapi

c = cdsapi.Client()

c.retrieve(
'reanalysis-era5-pressure-levels',
{
'product_type': 'reanalysis',
'format': 'netcdf',
'variable': [
'geopotential', 'specific_humidity', 'temperature',
'u_component_of_wind', 'v_component_of_wind', 'vertical_velocity',
],
'year': '2023',
'month': '11',
'day': '01',
'time': [
'00:00', '06:00',
],
'pressure_level': [
'1', '2', '3',
'5', '7', '10',
'20', '30', '50',
'70', '100', '125',
'150', '175', '200',
'225', '250', '300',
'350', '400', '450',
'500', '550', '600',
'650', '700', '750',
'775', '800', '825',
'850', '875', '900',
'925', '950', '975',
'1000',
],
},
'atmospheric.nc')

c.retrieve(
'reanalysis-era5-single-levels',
{
'product_type': 'reanalysis',
'variable': [
'10m_u_component_of_wind', '10m_v_component_of_wind', '2m_temperature',
'geopotential', 'land_sea_mask', 'mean_sea_level_pressure',
'toa_incident_solar_radiation', 'total_precipitation',
],
'year': '2023',
'month': '11',
'day': '01',
'time': [
'00:00', '06:00',
],
'format': 'netcdf',
},
'single-level.nc')
```

Presumably, these files are then spliced together to form an input file. While I'm able to combine the files easily enough, there are subtleties that I'm clearly messing up, like constructing the `datetime` and `batch` coordinates, which seem to be mandatory (e.g., `ValueError: 'datetime' must be in data coordinates.`)

Do you plan to publish a script or instructions for constructing input files from these data products in the format expected by the model? It would be a fantastic help for applying the model!

Many thanks in advance,
Dan