Przejdź do treści
Biblioteka skilli
Zarządzanie i produkt · Planowanie

grilling

/grilling

Przepytuje o niejasny plan lub decyzję i zapisuje odpowiedzi każdej rundy, a zapis decyzji zostawia innym skillom.

Licencja
Apache-2.0
Ostatnia zmiana repozytorium
13.11.2026

Ocena i bezpieczeństwo

90/ 100Klasa: dobry
Format25 / 25
Frontmatter z nazwą i opisem, poprawna nazwa, opis do 1024 znaków, nazwa zgodna z folderem.
Odkrywalność25 / 25
Opis mówi, kiedy użyć skilla, ma sensowną długość i jest w 3. osobie.
Treść25 / 35
Co najmniej 150 słów i do 500 linii, nagłówki, listy kroków, przykłady albo kod.
Higiena15 / 15
Bez zaślepek typu TODO, bez ścieżek Windows, z licencją.
Ryzykobrak sygnałów w skanie
Pliki w paczce
2
Skrypty
0
Komentarze HTML
0
Adresy URL w SKILL.md
0
Przestarzałość

Brak sygnałów. Repozytorium zmienione 13.11.2026, bez odwołań do wycofanych modeli i API.

Licencja

Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.

Co robi i kiedy

Przepytuje o niejasny plan lub decyzję i zapisuje odpowiedzi każdej rundy, a zapis decyzji zostawia innym skillom.

Oryginalny opis (EN)

Grill a plan, decision, or idea until it is clear: ask the questions that can be answered now, wait for the answers, and write each round into a testimony. It writes the testimony and nothing else: what the discussion settled is written by `adr` and `glossary`, run by `grill-and-records`. Use when a plan is still fuzzy, or when another skill reaches a decision it cannot settle alone.

Jak działa

  1. Before the first question
  2. The rounds
  3. What the discussion writes
  4. The output contract
  5. What this skill does not do
Sekcje z nagłówków SKILL.md, w oryginale · 46 linii, 560 słów
Podgląd SKILL.md
---
name: grilling
description: "Grill a plan, decision, or idea until it is clear: ask the questions that can be answered now, wait for the answers, and write each round into a testimony. It writes the testimony and nothing else: what the discussion settled is written by `adr` and `glossary`, run by `grill-and-records`. Use when a plan is still fuzzy, or when another skill reaches a decision it cannot settle alone."
family: method
invocation: model
---

# Grilling

A discussion that ends with a shared understanding and a written record. It asks the questions a person has not answered, waits for the answers, and moves outward as the answers settle. One testimony per run: this action writes it and does not decide how many discussions there are; the caller asked for this one.

Use it when a plan, decision, or idea is still fuzzy, or when `fog-explore`, `split`, `map-review`, or `task-review` reaches a decision it cannot settle alone.

## Before the first question

Name the subject in one sentence: what is being decided. Create the testimony with `waymark create --category testimony`, link it to the record the discussion serves, and keep its body to `res/testimony.md`.

Ask in the project's vocabulary: use the words `GLOSSARY.md` defines, and stay inside decisions `docs/adr/` already records. When the discussion needs a word the glossary does not have, or would overturn a recorded decision, say so in that round's testimony and leave the write to whoever asked for the discussion; this action adds no glossary entry and no ADR.

## The rounds

Think of the discussion as a tree of questions, where a child is a narrower part of its parent. Work it in rounds.

- **The frontier** is every question whose prerequisites are already settled: what can be asked now without guessing at answers not yet heard.
- **Ask the whole frontier in one round.** Number each question and give your recommended answer, worded so that "yes" accepts it.
- **Then wait** for the answers before the next round. A question whose answer depends on another question open in this round belongs to a later round.
- **Facts are your job, not the person's.** Look it up in the repository, the documents, or online; ask a person only for what only a person knows. A running lookup is an unsettled prerequisite, so only the questions downstream of it wait.

Done when the frontier is empty: every branch visited, nothing left silently assumed, and the person confirms the shared understanding.

## What the discussion writes

Everything this action writes goes into the testimony, as each round happens and not batched to the end:

- **The rounds**: the questions, the recommended answers, and what the person said.
- **The settled decisions**, with the alternative that lost, for the caller to write into the map or task the discussion serves.
- **The terms** the discussion fixed and will not change again, and the decisions that a recorded ADR no longer matches.
- **Work**: a question that becomes work is written as `work: <what>` for the caller, which opens the record.

This action writes the testimony and nothing else. The records these become are not its work: a term goes to `glossary` and a decision to `adr`, and `grill-and-records` runs those. A caller reaches `grill-and-records`, which runs this discussion first; the `what-is-the-mainline` skill says where that sits.

## The output contract

At the end, name the decisions and facts that are clear, the terms the testimony fixed, the work handed off, and anything that will need an ADR. A caller that asked a specific question gets the answer first.

The testimony exists, and `grill/res/testimony.md` says what it holds.

## What this skill does not do

- Decide; the person does.
- Write a glossary entry or an ADR; `grill-and-records` runs the actions that do.
Pliki w paczce (2)
  • SKILL.md 4 KB
  • res/testimony.md 1 KB

Wersje

RepozytoriumWynikLicencja
Ta strona · QiYueran-source/weave-your-work90Apache-2.0
nikospavlopoulos/devops-mutant-powers100MIT
RIJUDEVx/agent-skills100MIT
yuan88964/RelayStudio100MIT
SimplySylvia/Claude-Quorum100MIT
FrancoStino/opencode-skills-collection100MIT
cravingmaker/skills100MIT
helmholtzai-consultants-munich/helmholtz-agent-skills100Apache-2.0
bendrucker/claude100MIT

Migawka bazy z 13.11.2026 · wersja paczki 76579d0de055 (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

  • 90grill-and-records
    Przeprowadza rozmowę o planie i zapisuje ustalone terminy w słowniku oraz decyzje w ADR.
  • 100plan-grilling
    Przepytuje plan, projekt lub pomysł w kolejnych rundach pytań, aż wszystkie decyzje zostaną rozstrzygnięte przed budową.
  • 100grill-docs
    Przepytuje użytkownika o plan i zapisuje przebieg: transkrypt pytań i odpowiedzi w katalogu grills oraz każdą decyzję w dokumencie decyzji repozytorium.
  • 100grilling-sleek
    Dokładnie przepytuje użytkownika o plan, decyzję lub pomysł, gdy chce on sprawdzić swoje myślenie.
  • 100kit-grill
    Zadaje trudne pytania o pomysł, plan lub decyzję, po jednym na raz, z zalecaną odpowiedzią na początku.
  • 95grill-with-docs
    Przeprowadza surowy wywiad nad planem lub projektem i zapisuje przy tym decyzje architektoniczne oraz słownik pojęć.

Uwagi i zgłoszenia

Wiadomość trafi do Bartosza Sokolińskiego. Adres e-mail jest potrzebny tylko do odpowiedzi. Szczegóły w polityce prywatności.