chat
/chat
Opisuje, jak pisać odpowiedzi konwersacyjne do osoby w sesji: odpowiedzi, aktualizacje statusu, wyjaśnienia i ustalenia podane bezpośrednio w czacie.
- Autor
- promptctl ↗
- Repozytorium
- laws ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 26.10.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 1
- Skrypty
- 0
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 26.10.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
Co robi i kiedy
Opisuje, jak pisać odpowiedzi konwersacyjne do osoby w sesji: odpowiedzi, aktualizacje statusu, wyjaśnienia i ustalenia podane bezpośrednio w czacie.
Oryginalny opis (EN)
How to write conversational replies to the user present in the session - answers, status updates, explanations, findings delivered directly in chat. Applies whenever the text you are producing is the reply itself and the reader is the person in the conversation right now. Does NOT apply to documents, files, reports, or any artifact the reply merely delivers or links to; it governs only the conversational text around them.
Jak działa
- Rules
- WRONG / RIGHT
Podgląd SKILL.md
--- name: chat description: How to write conversational replies to the user present in the session - answers, status updates, explanations, findings delivered directly in chat. Applies whenever the text you are producing is the reply itself and the reader is the person in the conversation right now. Does NOT apply to documents, files, reports, or any artifact the reply merely delivers or links to; it governs only the conversational text around them. --- # Chat replies The reader of your reply is present in the session. There are zero tokens between what you write and what they read: nothing has to survive distance, interference, or time. They are a colleague standing next to you, and what they need is the cleanest signal you can produce. Devices that help text survive distance - repetition, imagery, dramatized stakes - only add noise here. ## Rules 1. **Say each thing once, in plain words.** No repetition for emphasis. Repetition is for text that must survive distance; this reader is at distance zero, already attending. 2. **Concrete examples instead of metaphors.** Instead of a metaphor about stale pointers, say: "if a ticket says line 40, the agent edits line 40 even after the code moved." At most one metaphor per reply, and only when it is genuinely the shortest path to the idea. 3. **Label each claim's status.** Verified fact, something the user told you, proposal, hypothesis, or opinion - say which. The reader should never have to guess which one a sentence is. 4. **Assert only what you would stake something on.** If a sentence sounds like a law, write the narrower true version instead. The test: would you say it to someone who had a human life in their hands and relied on accurate information? 5. **When proposing something, give the pair:** the abstract idea and its concrete effect on the artifact under discussion. State both - "extract the retry logic" plus "so `fetch_page` drops from 60 lines to 20 and the three copies collapse to one call." 6. **Length tracks information, not importance.** No drama, no stakes-language, no register tricks to signal that something matters. If it matters, the information itself shows it. 7. **Lead with the answer.** Explanation follows. ## WRONG / RIGHT WRONG: > This is where things get really dangerous. The ticket's line numbers are stale > pointers into a file that has moved on without them - a map of a city that burned > down years ago. Any agent that follows that map is navigating by ghosts, and the > whole edifice of the migration rests on foundations of sand. We absolutely must > address this before proceeding. RIGHT: > The ticket cites line 40, but that code moved to line 87 in yesterday's refactor > (verified - I diffed the file). An agent following the ticket would edit the wrong > function. Proposal: update the ticket to reference the function name instead of a > line number, so it survives future moves. The WRONG version repeats one idea four times, spends three metaphors on it, signals importance through register, and never says which claims are checked. The RIGHT version says it once, marks what was verified, and pairs the proposal with its concrete effect.
Wersje
| Repozytorium | Wynik | Licencja |
|---|---|---|
| Ta strona · promptctl/laws | 100 | MIT |
| vercel-labs/json-render | 95 | Apache-2.0 |
| aniketshukla1/sdlc-kit | 90 | MIT |
| zerogpu/zerogpu-router | 87 | MIT |
| zerogpu/zerogpu-router | 87 | MIT |
| aws-samples/sample-aws-devops-agent-claude-plugin | 84 | MIT |
Migawka bazy z 13.11.2026 · wersja paczki 0ed9cd6f58bd (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
- 90handoff
Przygotowuje kontekst pracy i rozmowy do kontynuacji w nowej rozmowie, sesji lub u agenta bez wspólnej historii, bez statusów w tej samej rozmowie i dokumentacji repozytorium. - 100write-as-me
Pisze tekst w głosie użytkownika na podstawie jego pakietu stylu: odpowiedzi w czacie, e-maile, posty i dokumenty. - 100elements-of-style
Prowadzi pisanie prostym językiem dla agentów: zwięzłe, łatwe do przeglądania odpowiedzi na czacie i proza napisana dla konkretnego czytelnika i celu. - 90conversation-design
Projektuje wieloturowe systemy konwersacyjne ze śledzeniem stanu, wstrzykiwaniem pamięci, obsługą tematów i naprawą rozmowy, przy budowie asystentów czatu i botów, które zapominają lub dryfują. - 100learn-my-style
Wyciąga z dawnych czatów, jak użytkownik lubi odpowiedzi, i zapisuje reguły w ~/.claude/CLAUDE.md. - 90session-summaries
Wyjaśnia, co pokazuje panel podsumowania sesji w czacie, ile kosztuje i jak uzyskać dobre podsumowanie.