Erlemar

---
name: draft-critic-mm
description: Review drafted DSWoK vault notes (dswok.com) against .claude/writing_style_guide.md and vault conventions. Use before publishing to catch style violations, AI writing tells, factual errors in citations, missing cross-links, and frontmatter convention violations.
tools: Read, Grep, Glob
---

You are a style and convention critic for the DSWoK reference vault (dswok.com). Your job is to review a drafted vault note against `.claude/writing_style_guide.md`, vault frontmatter conventions, and cross-link requirements — and produce a concrete, actionable critique before publication. This agent is for vault notes only (not blog posts, not book reviews).

## How to review

Erlemar

Fill one broken-link stub in the DSWoK vault: research the topic, draft the note in DSWoK voice, run `draft-critic-mm`, save to the right folder, and refresh `missing_notes.md`.

Use the path `ROOT = '/Documents/DSWoK'`.

## Inputs

- `$ARGUMENTS` (optional). If provided, treat as the stub title to fill (e.g. "AUC", "Negative sampling", "T5"). If omitted, pick the highest-impact stub from `missing_notes.md` (most references first; ties broken by alphabetical order).

## Workflow

Erlemar

import pandas as pd
import altair as alt
import numpy as np
alt.data_transformers.disable_max_rows()

from IPython.display import display, HTML
display(HTML("<style>.container { width:100% !important; }</style>"))

import matplotlib_inline.backend_inline
matplotlib_inline.backend_inline.set_matplotlib_formats('retina')

Erlemar

res_layers = list(range(1, 66))
upper_shale = [1, 2, 3, 4]
middle_shale =[29, 30, 31, 32, 33, 34]
lower_shale = [62, 63, 64, 65]
shale_layers = upper_shale + middle_shale + lower_shale
sand_layers = [x for x in res_layers if x not in shale_layers]



# create figure

Erlemar

import plotly.graph_objects as go
import numpy as np
import pandas as pd
df = pd.read_csv('/Users/andreylukyanenko/Downloads/df_numpy_3d_B4_pred.csv')
# Create figure
fig = go.Figure()

# Add traces, one for each slider step
for step in range(1, 126):

Erlemar

import plotly.graph_objects as go
import numpy as np
import pandas as pd
df = pd.read_csv('/Users/andreylukyanenko/Downloads/df_numpy_3d_B4_pred.csv')
# Create figure
fig = go.Figure()

# Add traces, one for each slider step
for step in range(1, 66):
    df_small = df.loc[df['k'] == step]

Erlemar

import itertools
import random
from typing import List, Tuple

import numpy as np

from interfaces.TaggingOperation import TaggingOperation
from tasks.TaskTypes import TaskType

Erlemar

Erlemar

from fastai import *

Erlemar

import os

import hydra
import pytorch_lightning as pl
from omegaconf import DictConfig
from pytorch_lightning.loggers import CometLogger, TensorBoardLogger

from src.lightning_classes.lightning_nbeats import LitM5NBeats
from src.utils.utils import set_seed