Find agent skills by outcome

df.replace(DISGUISED_NULLS

np.nan

- e.g.

Price is the target — rows missing it are unusable

- e.g.

CustomerID must be unique and non-null

- Watch for: ?

N/A

- e.g.

Age cannot be 0 or negative

TARGET_COL = [e.g.

price]

- Boolean → binary flags (0/1

True/False)

MODEL_TYPE = [e.g.

XGBoost / LinearRegression / Neural Network]

MISSING VALUES HANDLER

# PROMPT() — UNIVERSAL MISSING VALUES HANDLER

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

rules

- Architectural Constraints: Ensuring that strict structural rules

DevSecOps guidelines

- Modular References: Linking to secondary markdowns (like PRDs

sprint_todo.md

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

`[ ] Current`

description: Creates

updates

3 adjacent concepts the user should look at next

with one sentence on why.

A brief

jargon-free explanation of what the concept is.

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

ask which one to do first.

1. Physical Analogies Only: The analogy section must not mention computers

servers

- Use casual

conversational grammar.

- Assume intelligence

but zero prior knowledge.

- No jargon. If a term is vital

define it instantly.

You are a calm

patient security educator.

# Last Modified: March 11

2026

The camera should feel front-facing with a medium close-up framing

similar to a 50mm lens