Skip to content
Skills Library
Data & analytics · Planning

framing-ml-problems

/framing-ml-problems

Frames a data/ML problem before any modeling — the decision, the action, the cost of a wrong call, task type, target, and success metric. Use when picking a project direction, writing a research question, or mapping a problem onto an ML task type.

Licence
MIT
Last repository change
11.11.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 11.11.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Frames a data/ML problem before any modeling — the decision, the action, the cost of a wrong call, task type, target, and success metric. Use when picking a project direction, writing a research question, or mapping a problem onto an ML task type.

Original author description

Frames a data/ML problem before any modeling — the decision, the action, the cost of a wrong call, task type, target, and success metric. Use when picking a project direction, writing a research question, or mapping a problem onto an ML task type.

How it works

  1. The four questions (answer all four, in writing)
  2. Map it to a task type
  3. Write the one-paragraph frame
  4. How to verify
Original SKILL.md headings · 48 lines, 439 words
SKILL.md preview
---
name: framing-ml-problems
description: Frames a data/ML problem before any modeling — the decision, the action, the cost of a wrong call, task type, target, and success metric. Use when picking a project direction, writing a research question, or mapping a problem onto an ML task type.
---

# Framing ML problems

A model is never the goal. A better DECISION is the goal. Frame first, model later.

## The four questions (answer all four, in writing)

1. **What decision does this improve?** Not "predict X" — decisions. "Which page should an
   editor fix first?" is a decision. "Predict decline" is not, yet.
2. **Who acts on the output, and what do they do?** Name the person and the action. If nobody
   would act differently, the work has no customer.
3. **What does a wrong answer cost?** Wasted editor hours? A missed decline? The cost of errors
   decides how careful the method must be, and which errors matter more.
4. **Why does data or ML help at all?** Sometimes a plain rule (an if-statement) is the right
   answer. Sometimes a dashboard is. ML earns its place only when the pattern is real but too
   messy to write by hand — many signals, tangled, shifting over time.

## Map it to a task type

| If your question sounds like… | Task type | Target | Typical metric |
|---|---|---|---|
| "Which ones first?" | Ranking / scoring | a priority score | precision@K |
| "Will this one decline / recover?" | Classification | a yes/no label from an OBSERVED outcome | ROC-AUC, precision/recall vs base rate |
| "What kinds of items exist?" | Clustering | none (unsupervised) | silhouette + human sense-check |
| "Which signals travel together?" | Signal analysis | none | effect sizes, grouped comparisons |

Two rules that save whole projects:

- **The target must be observed, not defined.** A label that comes from someone's rule means your
  model learns the rule, not the world. Prefer outcomes measured in a later time window.
- **Name the metric before training.** "Good" defined after the fact always looks good.

## Write the one-paragraph frame

> For [who], deciding [what], we will build [output type] from [data], predicting/scoring
> [target] measured by [metric]. A wrong call costs [cost]. A plain rule isn't enough because
> [why]. We will claim only [observed / directional / decision-support] results.

If you can fill that paragraph honestly, you are framed. If a blank stays blank, that blank IS
your next task.

## How to verify

- Show your frame to someone (or your assistant) and ask: "what decision does this improve?"
  If their answer differs from yours, the frame isn't done.
- Check the target: is it observed in the data, or defined by a rule? If defined — reframe.
- Check the metric exists in your data. Can you compute it today, on a baseline? Do it.

Versions

The database has no other skills named framing-ml-problems.

Database snapshot: 13.11.2026 · package version 723c929e7667 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 90problem-framing
    Problem Framing. Turn a business brief, PRD, dataset description or stakeholder question into a one-page ANALYSIS_MANIFEST.md before any modeling. Use when someone asks what to predict, how to measure success, which metric or baseline to use, the cost of errors, or how to scope…
  • 90ml-problem-framing
    Frame ML problems around a decision, a measurable target, and honest error costs before touching models. Use when scoping an ML project or reviewing whether one should exist.
  • 100021-problem-framing
    Use when a problem or issue needs explicit framing before deeper analysis begins — establishing the Problem statement, Current state, Desired state, Stakeholders, and Success criteria. This should trigger when an issue's Problem Framing point of view needs evaluation, or when a…
  • 96problem-framing
    将模糊的设计挑战转化为清晰、可执行的问题陈述。使用结构化方法分析问题背景、约束条件、成功指标和解决方案假设。
  • 100question-framing
    Structure analytical questions with the Question Ladder (Goal, Decision, Metric, Hypothesis), then fill the 7-field Analysis Design Spec, before touching data. Trigger on "analyze", "investigate", "look into", "why did", "what's happening with", "what happened with", "figure…
  • 100question-framing
    Structure analytical questions with the Question Ladder (Goal, Decision, Metric, Hypothesis), then fill the 7-field Analysis Design Spec, before touching data. Trigger on "analyze", "investigate", "look into", "why did", "what's happening with", "what happened with", "figure…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.