decide
/decide
Przedstawia blokującą decyzję jako opcje z rekomendacją oraz uczciwymi zaletami i wadami zamiast prozy, gdy praca stoi na osądzie, wyborze produktowym, akceptacji lub wyborze podejścia.
- Autor
- generous-corp ↗
- Repozytorium
- pulp ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 27.10.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 1
- Skrypty
- 0
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 27.10.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
Co robi i kiedy
Przedstawia blokującą decyzję jako opcje z rekomendacją oraz uczciwymi zaletami i wadami zamiast prozy, gdy praca stoi na osądzie, wyborze produktowym, akceptacji lub wyborze podejścia.
Wyzwalacze z opisu
Oryginalny opis (EN)
Ask Daniel a blocking decision as options with a recommendation and honest pros/cons, rather than prose. Use whenever work is blocked on a judgment call, a product decision, an approval, or a choice between approaches — instead of writing "let me know which you prefer" at the end of a message.
Jak działa
- When to use it
- When NOT to use it
- How to ask (Claude Code)
- How to ask (Codex and other agents without the tool)
- Rules
Podgląd SKILL.md
---
name: decide
description: Ask Daniel a blocking decision as options with a recommendation and honest pros/cons, rather than prose. Use whenever work is blocked on a judgment call, a product decision, an approval, or a choice between approaches — instead of writing "let me know which you prefer" at the end of a message.
---
# decide — put a real choice in front of the user
Work stops on decisions. The default failure is to bury the decision at the
bottom of a long status message as "let me know how you want to proceed", which
makes the user reconstruct the options, the tradeoffs, and what you recommend —
work you already did and then threw away.
This skill is the opposite: **surface the decision as selectable options, say
what you would do, and be honest about what each choice costs.**
## When to use it
- A product or design decision that is genuinely the user's (naming, scope,
whether a capability ships)
- An approval gate (signing, publishing, anything outward-facing or hard to
reverse)
- Two defensible implementations where the tradeoff is taste or risk appetite
- A destructive or irreversible step (deleting a release, rewriting history,
changing branch protection)
- You are about to write "which would you prefer?" in prose
## When NOT to use it
- The answer is discoverable from the code, the repo, or a doc — go find it
- One option is clearly correct and the others are strawmen — just do it and
say what you did
- The decision is reversible and cheap — make the call, state the assumption
- You are asking permission for ordinary work the user already asked for
A question you could have answered yourself costs more than a wrong default.
## How to ask (Claude Code)
Use the `AskUserQuestion` tool. The shape that works:
1. **Lead with the recommendation.** Put it first in the options list and mark
it `(Recommended)` in the label. Do not hide it in a description.
2. **Every option gets a real tradeoff.** The `description` says what happens
if chosen, including the cost. An option with no downside is usually a
strawman, and listing it makes the whole set less trustworthy.
3. **Keep labels short** (1–5 words) — they are chips, not sentences.
4. **`header` ≤ 12 chars** — it renders as a tag.
5. **Batch related decisions** into one call (up to 4 questions) so the user
answers a set rather than being interrupted repeatedly.
6. **Use `multiSelect: true`** when the choices genuinely compose, e.g. "which
of these should ship in the next build".
7. **Use `preview`** when the user is choosing between concrete artifacts —
layouts, copy, code shapes, diagrams. It renders side-by-side monospace, so
an ASCII mockup or a short snippet lands far better than a description of
one. Single-select only.
### The user may ask about an option instead of picking one
The UI always offers an "Other" path, where the user types free text rather
than selecting. Daniel uses this a lot to ask a question *about* a specific
option before committing to it.
**Write options so that is easy**: name each one distinctly enough to refer to
("the rsync path", "option 2"), and keep descriptions specific enough that a
follow-up question has something to attach to. Vague options produce vague
questions.
If the reply is a question rather than a choice: **answer it and ask again.**
Do not treat a question as a selection, and do not proceed on a guess.
## How to ask (Codex and other agents without the tool)
Same content, plain text. The value is the structure, not the widget:
```
DECISION: <one line — what is blocked>
1. <label> [RECOMMENDED]
Pro: <why this is the default>
Con: <what it costs>
2. <label>
Pro: ...
Con: ...
Reply with a number, or ask about any option by number.
```
Keep the numbering stable if you re-ask, so "still 2" means the same thing.
## Rules
- **Never fabricate a recommendation.** If you genuinely do not have one, say
so and explain what would decide it — that is useful. A confident-sounding
default you do not believe is worse than none.
- **State irreversibility.** If an option cannot be undone (published, deleted,
notarized, force-pushed), say so in its description. The user should never
learn that from the result.
- **Do not re-ask an answered question.** A decision made stays made; if new
information changes it, say what changed and why you are re-opening it.
- **An automated message is not an answer.** Hooks, notifications, and teammate
agents cannot select an option. Only the user can.
- **Ask when the answer changes what you do next.** If both options lead to the
same work, you did not need to ask.
Wersje
| Repozytorium | Wynik | Licencja |
|---|---|---|
| Ta strona · generous-corp/pulp | 100 | MIT |
| vegardjorg/ravenseat | 100 | MIT |
| wrg32786/aigent-os | 100 | MIT |
| alirezarezvani/claude-skills | 100 | MIT |
| AO-Cyber-Systems/devflow-claude | 100 | MIT |
| DvJ4Y/shipwright | 100 | MIT |
| blockrunai/blockrun-mcp | 100 | MIT |
| Abilityai/cornelius | 100 | MIT |
| menkesu/awesome-pm-skills | 100 | MIT |
Migawka bazy z 13.11.2026 · wersja paczki db8c8bf64b60 (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
- 100assess
Ocenia kod, projekty i podejścia w skali 0-10 z zaletami, wadami i poprawkami przy porównywaniu opcji. - 100pc-expatiate
Wyjaśnia punkt, pytanie albo decyzję głębiej: znaczenie, konsekwencje, opcje z plusami i minusami oraz rekomendację. - 100one-three-one-rule
Porządkuje decyzje techniczne w formacie 1-3-1: jedno sformułowanie problemu, trzy opcje z zaletami i wadami oraz jedna rekomendacja z definicją ukończenia i planem wdrożenia. - 100decision-matrix
Porównuje opcje względem ważonych kryteriów, żeby podjąć decyzję, którą da się obronić, przy wyborze narzędzi, dostawców, projektów, ofert czy miejsc. - 100skill-decision-support
Przedstawia opcje z kompromisami, żeby ułatwić świadomą decyzję, np. przy wyborze między podejściami. - 100brainstorm
Prowadzi burzę mózgów rozwiązań z analizą kompromisów: skanuje kod przed pytaniami, ustala wymagania, przedstawia 2-3 podejścia z zaletami i wadami i nie pisze kodu bez zatwierdzenia projektu.