interview
/interview
Przeprowadza wywiad o pomyśle lub projekcie, aż użytkownik i agent rozumieją go tak samo, rozstrzygając decyzje po kolei.
- Autor
- Ovich ↗
- Repozytorium
- charrette ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 27.10.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 3
- 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
Przeprowadza wywiad o pomyśle lub projekcie, aż użytkownik i agent rozumieją go tak samo, rozstrzygając decyzje po kolei.
Wyzwalacze z opisu
Oryginalny opis (EN)
Use when a person says "interview me" or asks to be interviewed about an idea or an existing design document (a board, a plan, a change) until it is understood the same way by them and the agent, or when another skill needs open decisions resolved one by one. Runs in chat and leaves the resolved decisions there, for the caller to write where they belong. Keeping the discussion as a document is brainstorm's, turning it into a plan is write-plan's.
Jak działa
SKILL.md bez nagłówków drugiego poziomu · 42 linii, 410 słów
Podgląd SKILL.md
--- name: interview description: Use when a person says "interview me" or asks to be interviewed about an idea or an existing design document (a board, a plan, a change) until it is understood the same way by them and the agent, or when another skill needs open decisions resolved one by one. Runs in chat and leaves the resolved decisions there, for the caller to write where they belong. Keeping the discussion as a document is brainstorm's, turning it into a plan is write-plan's. --- # Interview **The interview ends at shared understanding**: the person and the agent would describe the object the same way, and every decision is agreed or deferred. Until then, keep going. The object is a tree of decisions. Each is answered by what can be read or by the person. **Throw ideas in as you go.** An option the person did not list, a consequence they did not name, a neighbouring decision the conversation points at: one line, marked as yours, beside the question it belongs to. The interview draws the person out; it also gives them something to push against. **Research every decision that rests on a claim about the world**: a tool exists, it works with our versions, the industry does it this way. Read the official source, the specification, the package as published, its types and its changelog, and how reputable projects solve the same problem, from their sources. State the version read and the date. A search result or a blog is where reading starts, never where it stops. **One option, `experiments: yes | no`.** Ask it first, with your recommendation, when the subject makes it plausible, and later the moment reading cannot settle a claim or the person doubts a tool. On a yes, read `references/experiments.md`. The caller stores the answer with its decisions. **Before each question, read**: the code, the history, the existing documents. A question about a screen goes through the `point-at` skill first. **One decision per message, in tree order**, a branch once its parent is agreed. What reading settles is stated with its source, and the person confirms. Where a document says one thing and the code another, the person chooses which holds. What reading leaves open is asked: the decision with what it depends on, the question in one sentence, the recommended option first and marked, each option with the trade-off that decides it, and a closing line that takes a number or a rejection of the frame. A decision left unasked is one the implementation makes silently. **The short mode**, offered whenever the full interview would be skipped: three questions at most, on the decisions that change an output (kind `contract`) only, each with the recommendation first. Every decision it leaves unasked is closed as the agent's default, and named so. **Close in chat**, once understanding is shared: every decision with its status and source. The caller decides where that goes. **The caller writes decisions as rows**: read `references/decisions.md`.
Pliki w paczce (3)
- SKILL.md 3 KB
- references/decisions.md 1 KB
- references/experiments.md 1 KB
Wersje
| Repozytorium | Wynik | Licencja |
|---|---|---|
| Ta strona · Ovich/charrette | 81 | MIT |
| q00/ouroboros | 100 | MIT |
| vanducng/skills | 100 | MIT |
| boshu2/agentops | 100 | Apache-2.0 |
| mthines/agent-skills | 100 | MIT |
| r3dlex/oh-my-auggie | 100 | Apache-2.0 |
| YuDefine/nuxt-supabase-starter | 100 | MIT |
| biliboss/skills | 100 | MIT |
| Soe-Reh/soes-skills | 100 | MIT |
Migawka bazy z 13.11.2026 · wersja paczki bf0eda3acf27 (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
- 90write-plan
Pisze plan wdrożenia nietrywialnej funkcji lub przeróbki na podstawie wywiadu: projekt, decyzje, fazy i mandat dla orkiestratora. - 86brainstorm
Prowadzi z użytkownikiem rozmowę o pomyśle, zapisując decyzje, diagramy i ustalenia na tablicy w aiview. - 90interview-me
Przeprowadza wywiad o planie, pomyśle lub projekcie krótką serią pytań, a potem podsumowuje kierunek i następny krok. - 100spec
Przeprowadza wywiad o funkcji lub projekcie, a potem pisze specyfikację, którą można zbudować. - 100grill-me
Przeprowadza wywiad z użytkownikiem o planie lub pomyśle i zapisuje każdą odpowiedź w pliku burzy mózgów. - 100autopilot-interview
Przepytuje lub poddaje próbie wytrzymałości plan na prośbę użytkownika, rozstrzygając rutynowe wybory i wskazując istotne nierozstrzygnięte decyzje.