problem-framing
/problem-framing
Zamienia brief biznesowy, PRD lub opis danych w jednostronicowy ANALYSIS_MANIFEST.md przed modelowaniem: cel, metryka, baseline i koszt błędów.
- Autor
- Harrypatria ↗
- Repozytorium
- data-mining-ml ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 31.10.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 3
- Skrypty
- 0
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 31.10.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
Co robi i kiedy
Zamienia brief biznesowy, PRD lub opis danych w jednostronicowy ANALYSIS_MANIFEST.md przed modelowaniem: cel, metryka, baseline i koszt błędów.
Oryginalny opis (EN)
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 a machine learning, data science, data mining, predictive modeling, forecasting, segmentation, churn, fraud, risk scoring or A/B testing project. CRISP-DM Business Understanding.
Jak działa
- Steps
- Questions that change the design
- Exit criteria
- Anti-patterns
Podgląd SKILL.md
--- name: problem-framing description: 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 a machine learning, data science, data mining, predictive modeling, forecasting, segmentation, churn, fraud, risk scoring or A/B testing project. CRISP-DM Business Understanding. --- # Problem Framing Goal: one page that makes every later choice defensible. No data is touched until the manifest exists. ## Steps 1. **Extract** from the brief, in the stakeholder's words: - Decision the output informs, who makes it, how often, and what happens today (the baseline process). - Unit of prediction (customer per month, transaction, store per week) and prediction time (when the score must exist). - Success metric tied to the decision, plus a guardrail metric. - Cost of each error type. Fill a cost matrix even if rough: cost of a false positive, cost of a false negative, value of a true positive. - Constraints: latency, interpretability, regulation, fairness, data residency, budget. - Stakeholders and the audience for explanations. - Data touchpoints: sources, grain, history length, label definition and label delay. - Expected prevalence of the target if known. 2. **Classify the archetype** (see `references/archetypes.md`): churn, demand forecasting, fraud or anomaly detection, A/B analysis, segmentation, recommender, NLP classification, risk scoring. The archetype sets default split strategy, headline metric and traps. 3. **Choose the baseline** that the model must beat: current rule, majority class, last value, seasonal naive, or a logistic or linear regression. 4. **Pick the headline metric by cost** (`model-evaluation/references/imbalance-and-metrics.md`). Never accuracy alone on imbalanced targets. 5. **Write `ANALYSIS_MANIFEST.md`** from `references/manifest-template.md`. Keep it to one page. Mark each assumption with `Assumption:`. 6. **Plan phases** with CRISP-ML(Q) rows: for each phase one risk, its assumption and a mitigation. ## Questions that change the design Ask the user only if the answer changes the architecture and cannot be assumed. Otherwise state the assumption in one line and continue. - Is the decision made per entity in batch, or per request in real time? - Is the label available at prediction time for past periods only (label delay)? - Will a person act on each prediction (review queue capacity sets precision at k)? - Are people affected by the decision (fairness analysis becomes mandatory)? ## Exit criteria - Decision, metric, cost matrix, baseline and prevalence written. - Leakage-relevant timing written: prediction time and feature availability. - Deliverables listed: notebooks, model bundle, API, web app, explainer, report. - RIGOR gates that will be hard to meet are named now, not at the end. ## Anti-patterns - Starting with "which algorithm" before "which decision". - A metric the business cannot act on (ROC-AUC for a review queue of 50 cases a day). - A target defined with information from after the prediction time. - Prevalence ignored, so the threshold defaults to 0.5.
Pliki w paczce (3)
- SKILL.md 3 KB
- references/archetypes.md 3 KB
- references/manifest-template.md 2 KB
Wersje
| Repozytorium | Wynik | Licencja |
|---|---|---|
| Ta strona · Harrypatria/data-mining-ml | 90 | MIT |
| veevia/design-agency | 100 | MIT |
| kaminoikari/product-playbook | 100 | MIT |
| wanghaisheng/openaiworkhorse-design-team | 96 | MIT |
| Avyayalaya/pm-skills-arsenal | 91 | MIT |
| SimonFoote-greensparx/CopilotForge | 90 | CC-BY-4.0 |
| jacob-balslev/skill-graph | 90 | Apache-2.0 |
Migawka bazy z 13.11.2026 · wersja paczki a4ee7f7c458e (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 100framing-ml-problems
Opisuje problem danych i ML przed modelowaniem: decyzję, koszt błędu, typ zadania, cel i miarę sukcesu. - 100data-mining-machine-learning
Prowadzi projekt ML zgodnie z CRISP-DM: od briefu biznesowego po notebook, model, usługę FastAPI i aplikację w React. - 100prd-business-problem
Opisuje problem biznesowy w PRD: kto cierpi, co dziś nie działa, ile kosztuje zwlekanie i dlaczego zmiana jest potrzebna teraz. - 100data-science
Obejmuje data science i analitykę: analizę statystyczną, potoki uczenia maszynowego, data governance, business intelligence, modelowanie predykcyjne i strategię analityczną. - 100question-framing
Układa pytanie analityczne w drabinę pytań: cel, decyzja, metryka i hipoteza, a dopiero potem sięga po dane. - 100data-scientist
Prowadzi analizę danych, modelowanie predykcyjne i statystyczne oraz wyciąga z danych wnioski biznesowe.