decision-matrix
/decision-matrix
Uzasadnia wybór między bliskimi koncepcjami przez punktację opcji wobec ważonych kryteriów, gdy wybór kierują upodobania zamiast dowodów.
- Autor
- veevia ↗
- Repozytorium
- design-agency ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 02.11.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 1
- Skrypty
- 0
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 02.11.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
Co robi i kiedy
Uzasadnia wybór między bliskimi koncepcjami przez punktację opcji wobec ważonych kryteriów, gdy wybór kierują upodobania zamiast dowodów.
Oryginalny opis (EN)
Make a comparative choice transparent and defensible by scoring each option against weighted criteria — especially when options are close in quality. Use when you're stuck between 2–3 concepts, when preference (not evidence) is driving selection, or when a decider needs to justify a choice to senior stakeholders with explicit reasoning.
Jak działa
- When to use
- The matrix structure
- Steps
- Agent guide
- Watch-outs
- Connects to
Podgląd SKILL.md
---
name: decision-matrix
title: Score options against weighted criteria
description: Make a comparative choice transparent and defensible by scoring each option against weighted criteria — especially when options are close in quality. Use when you're stuck between 2–3 concepts, when preference (not evidence) is driving selection, or when a decider needs to justify a choice to senior stakeholders with explicit reasoning.
status: stable
contract-exempt: "design-method knowledge skill — a reusable thinking tool, not an executable contract"
when_to_load:
- Stuck between 2–3 genuinely competitive options and you need a structured comparison
- Personal preference is driving selection rather than the criteria that matter
- A decider must communicate a choice to senior stakeholders with a defensible rationale
- Trade-off analysis where some criteria matter far more than others (weighting)
applies-to: concept comparison, structured decision making, trade-off analysis, stakeholder communication
done_when:
- Each option is scored against every weighted criterion
- Weighted totals are computed and the winner + its weak criterion noted
- Combinable elements from losing options are identified
metadata:
duration: 20–30 min
team-size: solo, or full team; decider approves weights + final selection
sprint-phase: 4 Decide
---
# Decision Matrix
**TL;DR:** Score each option against the criteria that matter, weight the criteria by importance, and total. Makes the *reasoning* explicit — which option best satisfies what matters most — and is most valuable when two options are close and you need to surface what's actually different and why. Analytical input to a human decision, not a replacement for it.
## When to use
- When 2–3 options are genuinely competitive and need a structured comparison.
- When the decider must communicate a choice to senior stakeholders with a rationale.
- When personal preference is driving selection rather than the criteria.
## The matrix structure
Rows = criteria · Columns = options · Cells = score (1 = doesn't meet, 2 = partially, 3 = fully) · Weight = importance per criterion (1–3) · Weighted score = weight × cell.
```
Option A Option B Option C
Criterion 1 (weight 3) 3 2 1
Criterion 2 (weight 3) 2 3 2
Criterion 3 (weight 2) 3 2 3
Criterion 4 (weight 1) 1 2 3
─────────────────────────────────────────────────────
Weighted total 24 22 18
```
## Steps
1. **Post the criteria + weights (2 min):** list the criteria; the decider confirms weights (1–3).
2. **Score each option per criterion (10–15 min):** score silently and simultaneously, then read the average/mode — avoids scoring-as-advocacy.
3. **Apply weights and total (5 min):** multiply, sum per option.
4. **Find the winner — and the gaps (5 min):** highest total wins, but note which criterion each option won; losing options often have strong elements worth incorporating.
5. **Hand to the decider (3 min):** the matrix informs the decision; the decider may override for strategic value the criteria didn't capture (and states why, in one sentence, logged as an ADR note).
## Agent guide
When generating a Decision Matrix:
1. List the criteria with weights.
2. Score each option against each criterion using evidence, not intuition; flag any score that is `assumed` rather than `observed` (load `evidence-tagging`).
3. Calculate weighted totals; note the winner and the criterion it lost on.
4. Identify combinable elements — which part of a losing option should be folded into the winner.
## Watch-outs
- **Equal weights for everything** — then it's just a sum of scores; the weighting is the most important step.
- **Scoring as advocacy** — favourites get inflated; score silently and average.
- **Matrix replacing the decision** — it's analytical input; the human still chooses.
- **Forgetting constraints** — an option that violates a known constraint should score 1 on a constraint-compliance criterion, which (weighted) drops it out of contention.
## Connects to
- `rubric-authoring` — the weighted criteria ARE a rubric; author them there for repeatable scoring.
- `traffic-light-decisions` — the matrix surfaces the trade-off; the decision still closes with one light.
- `evidence-tagging` — each score carries its provenance (observed vs assumed).
- `design-sprint-tookit` (Decide phase) — `speed-critique`, `straw-poll`, and `supervote` surround the matrix in a full sprint.
Wersje
| Repozytorium | Wynik | Licencja |
|---|---|---|
| Ta strona · veevia/design-agency | 100 | MIT |
| joeysim/joeysim-skills | 100 | MIT |
| iflytek/skillhub | 100 | Apache-2.0 |
| The-Utopia-Studio/skills | 100 | Apache-2.0 |
| microclaw/microclaw | 100 | MIT |
| qa-aman/claude-skills | 100 | MIT |
| JayRHa/AgentSkills | 100 | MIT |
| omexit/claude-skills-pack | 100 | MIT |
| fzfclee/consulting-skills | 100 | Apache-2.0 |
Migawka bazy z 13.11.2026 · wersja paczki 8d29d4065159 (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 2 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 100decision-matrix-mcda
Szereguje opcje względem ważonych kryteriów macierzą decyzyjną i analizą wielokryterialną (macierz Heuera i Phersona, porównania AHP Saaty'ego z testem spójności) oraz sprawdza odporność zwycięzcy na zmiany wag i ocen. - 100decision-analysis
Ocenia kompromisy przy wyborze między alternatywami, takimi jak build czy buy, przepisanie czy łatanie, wybór technologii i alokacja zasobów, metodą kryteriów ważonych z konsekwencjami drugiego rzędu. - 100weighted-scorer
Buduje macierze decyzyjne z ważonymi kryteriami do wyboru technologii, oceny dostawców i porównań opcji, z walidacją analizą wrażliwości, na przykład build vs. buy. - 90decision-architect
Porządkuje trudną decyzję: opcje, kryteria, ważone punktacje, odwracalność i pre-mortem, a potem rekomenduje wybór. - 100tradeoff-analysis
Ocenia opcje według ważonych kryteriów, sprawdza wrażliwość wyniku i odwracalność, gdy trzeba wybrać między konkretnymi wariantami. - 90tradeoff-analysis
Porównuje opcje według jawnych ważonych kryteriów, z testami czułości i uwzględnieniem odwracalności, przy ważnym wyborze bez oczywistego zwycięzcy.