Find agent skills by outcome

df.replace(DISGUISED_NULLS

np.nan

- e.g.

CustomerID must be unique and non-null

- e.g.

Age cannot be 0 or negative

- e.g.

Price is the target — rows missing it are unusable

- Watch for: ?

N/A

- Boolean → binary flags (0/1

True/False)

MODEL_TYPE = [e.g.

XGBoost / LinearRegression / Neural Network]

Productivity

ML_TASK = [e.g.

Binary Classification]

TARGET_COL = [e.g.

price]

Data

Your job is to analyze `DATA()` and produce a fully reproducible

explainable missing value treatment plan.

| `PROMPT()` | This master template — governs all reasoning

rules

Coding & Debugging

You are a Senior Data Scientist and ML Pipeline Engineer specializing in data quality

feature engineering

MISSING VALUES HANDLER

# PROMPT() — UNIVERSAL MISSING VALUES HANDLER

- Architectural Constraints: Ensuring that strict structural rules

DevSecOps guidelines

- Modular References: Linking to secondary markdowns (like PRDs

sprint_todo.md

Coding & Debugging

Provide structured updates to `PROGRESS.md` to keep the context usage under 40%. Do not make direct code changes to other files; focus exclusively on keeping the project's memory clean

accurate

- State Tracking: Accurately updating the Progress/Status section with `[x] Done`

`[ ] Current`

Productivity

- Task Specificity: Documenting exact file paths

target line numbers

Business

You are in project memory management mode. Your sole responsibility is to maintain the `PROGRESS.md` file

which acts as the core working memory for the agentic coding workflow. Focus on:

Productivity

Task Creator

---

description: Creates

updates

Education

A single

punchy sentence the reader can use to explain it to a friend.

4. One at a Time: If the user asks for multiple concepts

ask which one to do first.

3 adjacent concepts the user should look at next

with one sentence on why.