`_should_skip_cell()` calls `self._graph.get_required_columns(column_name)` but the Files Modified table only adds `get_skip_config()` and `should_propagate_skip()` to ExecutionGraph - I don't think this method exists yet. `get_upstream_columns()` wouldn't work as a stand-in since after Step 2b it includes `skip.columns` edges too, and propagation should only consider template dependencies. Probably needs a `_required_columns` dict + accessor on the graph.

[andy9trider69-bit]

_should_skip_cell() calls self._graph.get_required_columns(column_name) but the Files Modified table only adds get_skip_config() and should_propagate_skip() to ExecutionGraph - I don't think this method exists yet. get_upstream_columns() wouldn't work as a stand-in since after Step 2b it includes skip.columns edges too, and propagation should only consider template dependencies. Probably needs a _required_columns dict + accessor on the graph.

Originally posted by @andreatgretel in NVIDIA-NeMo/DataDesigner#480 (comment)

[dinonuggies1]

Given the fact that this issue is incoherent, I'm closing it!