decision-question
/decision-question
Pyta użytkownika o wybór tylko wtedy, gdy blokuje go decyzja należąca do niego, i podaje najmniejszy kompletny opis wyboru.
- Autor
- rjmurillo ↗
- Repozytorium
- ai-agents ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 12.11.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 3
- Skrypty
- 1
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 12.11.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
- 1 skrypt w paczce. Przejrzyj je przed instalacją, bo Claude może je uruchomić.
Skrypty: scripts/decision_question.py
Co robi i kiedy
Pyta użytkownika o wybór tylko wtedy, gdy blokuje go decyzja należąca do niego, i podaje najmniejszy kompletny opis wyboru.
Oryginalny opis (EN)
Ask the user to choose only when blocked on a decision they own, with the smallest complete decision brief. Use when you say `ask the user to choose`, `do I need a user decision here`, or `present a decision brief`. Do NOT use to review a decision already made (use decision-critic) or to surface project risks (use pre-mortem).
Jak działa
- Triggers
- Routing gate: when NOT to ask
- Process
- Scripts
- Decision brief contract
- Five or more options
- Harness bound
- Relationship to existing capabilities
- Anti-Patterns
- Verification
Podgląd SKILL.md
---
name: decision-question
version: 1.0.0
description: Ask the user to choose only when blocked on a decision they own, with the smallest complete decision brief. Use when you say `ask the user to choose`, `do I need a user decision here`, or `present a decision brief`. Do NOT use to review a decision already made (use decision-critic) or to surface project risks (use pre-mortem).
license: MIT
metadata:
capability:
kind: reusable-primitive
owns:
- user-decision-elicitation
status: active
routing:
role: conditional-adjunct
invoker: autoplan
trigger: autoplan's confusion protocol finds a material decision only the user can make
user-facing: false
---
# Decision Question
> Ask only when a real user decision is required. When asking, present the
> smallest complete decision brief that lets the user choose deliberately.
Questions spend user attention. Spend it only on decisions the user owns, and
make each question decision-complete. This skill owns how to ask. It does not
own whether a mutation is authorized or whether a task is finished.
`voice.md` routes here and does not carry the protocol. Load the reference and
script only when the routing gate says ask.
## Triggers
`ask the user to choose between these paths`, `do I need a user decision here`,
`present a decision brief`, `which option should the user pick`
## Routing gate: when NOT to ask
Multiple implementation choices do not make a user decision. Do not ask when any
of these holds:
- the user delegated the choice (`choose the best option and implement it`);
- repository or safety policy mandates one option;
- existing acceptance criteria already determine the choice;
- the distinction is an implementation detail within authorized scope, and
reversible;
- reading available evidence or tools resolves the uncertainty;
- the task is terminal under the task-completion contract and the question would only solicit optional
follow-up. The STOP TOKEN wins.
```text
no unresolved user decision -> act within existing authorization
material unresolved user decision -> build the brief below
```
## Process
Each command below is a locator that runs `decision_question.py`. Output is
one JSON object.
1. **Route.** Apply the gate. If no question is warranted, act and stop.
2. **Draft the brief** for the earliest load-bearing decision (fields below).
3. **Check and plan.** Write the brief as JSON and run:
```bash
( for d in "${CLAUDE_PLUGIN_ROOT}" "${COPILOT_PLUGIN_ROOT}" .claude; do if [ -n "$d" ] && [ -f "$d/lib/ptk_run.py" ]; then exec python3 "$d/lib/ptk_run.py" skills/decision-question/scripts/decision_question.py --brief <brief.json>; fi; done; echo "ptk_run: no plugin root holds lib/ptk_run.py" >&2; exit 2 )
```
Exit 2 with a `ptk_run:` line on stderr and no JSON is a launcher failure.
Read the line: it names the cause (no plugin root holds the resolver, a
missing target, or a launch error). Fix that, not the brief.
`status: incomplete` (exit 2, JSON on stdout) lists the missing fields. Enrich the brief and
rerun. `status: revise_recommendation` (exit 2) means an earlier answer
filtered out the recommended option: pick a remaining option or set
`no_recommendation`, then rerun. `status: ask` lists the prompt `pages` and
the `page` to present now.
4. **Ask, then prune.** Present the decision with the host's structured ask
tool (Claude Code: `AskUserQuestion`; Muse Code, and Codex in Plan mode only:
`request_user_input`, at most 3 questions; no such tool: a plain chat
question). Record the
answer under `answers` and rerun. When the user picks `_more`, add one to
that decision's count under `paging` and rerun; the same decision returns
its next page. Decisions that depend on an answer are pruned or filtered from
that answer, and unresolved IDs are never renumbered.
5. **Weak evidence on an irreversible choice.** `pre_ask_review` in the output
names `decision-critic` and `pre-mortem`. Run one before asking.
## Scripts
### decision_question.py
```bash
( for d in "${CLAUDE_PLUGIN_ROOT}" "${COPILOT_PLUGIN_ROOT}" .claude; do if [ -n "$d" ] && [ -f "$d/lib/ptk_run.py" ]; then exec python3 "$d/lib/ptk_run.py" skills/decision-question/scripts/decision_question.py --brief <brief.json> [--max-options N]; fi; done; echo "ptk_run: no plugin root holds lib/ptk_run.py" >&2; exit 2 )
```
Reads one decision, or `{context, decisions, answers, paging}`. Routes, then validates
and plans the next actionable decision. `--max-options` overrides the pinned
per-prompt bound for a harness that reports a different cap (minimum 3).
**Exit codes**:
- `0`: routing resolved. No question warranted (`skip`), a complete bounded
brief (`ask`), every open decision held (`held`), or nothing left (`resolved`).
- `1`: unreadable or malformed brief JSON, an answer that is not one of the
decision's options, a duplicate decision ID, an out-of-range `paging` count, or a cap below 3.
- `2`: a question is warranted but the brief is not decision-complete
(`incomplete`, with the missing fields listed), or an earlier answer removed
the recommended option (`revise_recommendation`).
## Decision brief contract
Each decision carries a stable ID (`D1`, `D2`), a one-sentence statement of what
must be decided now, why it matters now, at least two materially distinct options
(presented 2 to 4 per page; overflow becomes a split chain) with their consequences, a recommendation with its load-bearing reason (or an
explicit statement that evidence supports none), and `Hold` only when deferring
is legitimate and a reopen condition exists. Render with the host's structured
ask tool (Claude Code: `AskUserQuestion`, which `voice.md` defines); do not
invent a new UI contract.
Field rules, option construction, split chains, Hold, and the completeness
check: [decision-brief-protocol.md](references/decision-brief-protocol.md).
## Five or more options
Never drop an option. Pick one shape:
- **Batch** coherent alternatives into groups of at most 4.
- **Split** into one call per option, each answered Include, Defer, Cut, or
Hold. This is the default when unsure. A Hold answer stops the chain at once.
Check dependencies before you fire the chain.
More than 6 options: first ask a meta-question (proceed, narrow, or batch).
Write non-ASCII text (CJK, accents) as literal UTF-8. Never `\u`-escape it.
## Harness bound
`decision_question.py` pins what the Claude Code `AskUserQuestion` schema accepts:
1 to 4 questions per call, 2 to 4 options per question, and a free-text `Other`
the tool adds itself. `Hold` and the continuation entry each take a presented
slot. Options beyond the bound split into ordered pages. Another harness with a
different cap: pass the observed value as `--max-options`.
## Relationship to existing capabilities
- `decision-rigor` (a `review` reference) stays a PR review axis. This skill
reuses its concepts (assumptions, distinct alternatives, reversibility,
failure modes) and none of its verdict schema, `CONTEXT_MODE`, or JSON output.
- `decision-critic` and `pre-mortem` are optional steps for high-impact
decisions, not steps for every question.
## Anti-Patterns
| Avoid | Why | Instead |
|-------|-----|---------|
| Asking when the user delegated the choice | Spends attention the user already gave away | Act within authorization |
| More options than the harness shows | The user cannot see or pick the overflow | Split into a deterministic chain |
| Asking D2 before D1 is answered | D1's answer may make D2 moot | Ask D1, then prune D2 |
| `Hold` with no reopen condition | The decision silently disappears | State the event that reopens it |
| Omitting a recommendation the evidence supports | Pushes the cost back to the user | Recommend and give the reason |
| Fabricating a recommendation | Invents confidence the evidence lacks | Say evidence supports no preference |
## Verification
- [ ] The routing gate ran. A delegated, policy-mandated, criteria-determined,
detail-level, evidence-resolvable, or terminal case emitted no question
(`status: skip`, exit 0).
- [ ] The presented decision is complete (`status: ask`, exit 0).
- [ ] No page exceeds the bound; over-bound briefs report `split: true`.
- [ ] Dependent decisions were pruned or filtered from the recorded answers.
- [ ] A held decision keeps its ID and states its reopen condition.
Pliki w paczce (3)
- SKILL.md 8 KB
- references/decision-brief-protocol.md 7 KB
- scripts/decision_question.py 18 KB
Wersje
| Repozytorium | Wynik | Licencja |
|---|---|---|
| Ta strona · rjmurillo/ai-agents | 100 | MIT |
| rjmurillo/ai-agents | 100 | MIT |
Migawka bazy z 13.11.2026 · wersja paczki 0fabf3ff09eb (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
- 100decision-critic
Stress-testuje rozumowanie przed decyzją: wyciąga ukryte założenia, sprawdza twierdzenia i generuje perspektywy przeciwne. - 100pre-mortem
Prowadzi analizę pre-mortem: zespół wyobraża sobie porażkę projektu i cofa się, by znaleźć jej przyczyny i ryzyka. - 100pre-mortem
Analizuje, jak produkt lub plan może się nie udać, przed decyzją go/no-go, i wskazuje ryzyka do wzięcia pod uwagę. - 90decision-architect
Porządkuje trudną decyzję: opcje, kryteria, ważone punktacje, odwracalność i pre-mortem, a potem rekomenduje wybór. - 90decision
Prowadzi decyzję przez jedno lub dwa pytania wielokrotnego wyboru naraz, z kompromisami i rekomendacją przy każdym pytaniu. - 86brief
Informuje właściciela, co zrobił zespół AI w repozytorium, co jest zablokowane i jakie decyzje czekają na niego.