📦

interview-me

Name: interview-me
Author: addyosmani

Ревизия содержимого r2 Безопасно ⚙️ Внешние команды

Clarify User Intent Before You Build

Underspecified requests cause teams to build the wrong outcome and discover misalignment late. This skill runs a focused, one-question interview that turns ambiguity into confirmed intent.

Поддерживает: Claude Codex Code(CC)

🥉 78 Бронза

Установить с помощью моего Агента

Скопируйте этот запрос в своего Агента. Он содержит каноническую страницу Skill и манифест.

Запрос агента

Review the Skillstore skill "interview-me" from https://skillstore.io/skills/addyosmani-interview-me.md and its manifest at https://skillstore.io/api/skills/addyosmani-interview-me/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Ваш Агент по-прежнему должен показать план и запросить все подтверждения, требуемые политикой безопасности.

Ресурсы для AI-агентов

Используйте эти ссылки, когда AI-агенту, crawler или script нужен чистый контекст вместо полной страницы.

Markdown-детали GET /skills/addyosmani-interview-me.md Подписанный manifest GET /api/skills/addyosmani-interview-me/manifest Подписанный lockfile GET /api/skills/addyosmani-interview-me/lockfile

Протестировать

Использование «interview-me». Build me a dashboard for our metrics.

Ожидаемый результат:

Hypothesis: You need a way to track experiment status and early signals. Confidence: about 30 percent because the audience, metrics, and success measure are unclear. Question: Who will use this dashboard?

Использование «interview-me». Make this process more scalable.

Ожидаемый результат:

Question: If you did not need to justify the decision, what result would you actually want? Guess: You may value faster completion more than broad future flexibility.

Использование «interview-me». I want a handoff document after the interview.

Ожидаемый результат:

Outcome: Track active experiments and their early signals.
User: The requester uses it during weekly reviews.
Why now: Information is spread across several documents.
Success: The requester can find every active experiment in one place.
Constraint: Keep the workflow lightweight.
Out of scope: Automated reporting and implementation planning.

Аудит безопасности

Безопасно

v2 • 19.09.2026 Открыть версионный отчет

All 24 static findings are false positives. The external-command matches are Markdown backticks, fenced examples, or prose, and the blocker matches describe interview guidance rather than system reconnaissance.

Просканировано файлов

226

Проанализировано строк

Пункты проверки

Ложные срабатывания проигнорированы

Факторы риска

Последний завершенный статический и семантический аудит не обнаружил подтвержденных проблем безопасности. Это не доказывает отсутствие побочных эффектов у навыка.

Аудитор:: codex Посмотреть историю аудитов →

Поделиться и цитировать этот отчет

Делитесь версионным отчетом об оценке, нейтральным значком, встраиваемой карточкой и цитатами. Skillstore публикует доказательства, не решая, безопасен ли этот Skill.

Открыть версионный отчет

Копировать ссылку на отчёт

https://skillstore.io/skills/addyosmani-interview-me/audits/2?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Значок Markdown

[![Skillstore security assessment](https://skillstore.io/badges/skills/addyosmani-interview-me/security.svg)](https://skillstore.io/skills/addyosmani-interview-me?utm_source=security_passport_badge)

Значок HTML

<a href="https://skillstore.io/skills/addyosmani-interview-me?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/addyosmani-interview-me/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Встраиваемая карточка

<iframe src="https://skillstore.io/embed/skills/addyosmani-interview-me.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Академические ссылки (APA · BibTeX · CFF)

Цитата APA

addyosmani. (2026). interview-me security audit report (audit version 2) [Author version unspecified]. Skillstore. https://skillstore.io/skills/addyosmani-interview-me/audits/2

Цитата BibTeX

@techreport{addyosmani-addyosmani-interview-me-2026,
  author = {addyosmani},
  title = {interview-me security audit report (audit version 2)},
  institution = {Skillstore},
  year = {2026},
  number = {2},
  url = {https://skillstore.io/skills/addyosmani-interview-me/audits/2},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "interview-me security audit report (audit version 2)"
version: "unspecified"
type: report
authors:
  - name: "addyosmani"
date-released: "2026-09-19"
url: "https://skillstore.io/skills/addyosmani-interview-me/audits/2"
identifiers:
  - type: other
    value: "skillstore:addyosmani-interview-me:audit:2"
    description: "Skillstore immutable audit report identifier"

Оценка Skillstore

Почему такая оценка Достоверность доказательств: Высокий

Архитектура

Сопровождаемость

Контент

Сообщество

Соответствие спецификации

Что вы можете построить

Shape a Product Request

Turn a broad product idea into a confirmed outcome, target user, success measure, and explicit scope boundary.

Clarify an Engineering Task

Expose hidden assumptions before planning or coding, especially when a familiar request could represent several different solutions.

Prepare a Stakeholder Handoff

Capture confirmed intent in the requester’s language so another collaborator can continue with fewer misunderstandings.

Попробуйте эти промпты

Start an Intent Interview

Interview me about this request one question at a time. State your hypothesis and confidence before the first question.

Challenge My Assumptions

Use interview-me to find assumptions in my request. Probe who benefits, why now, success criteria, constraints, and what is out of scope.

Test the Real Goal

Interview me about this proposed solution. Treat the solution as a hypothesis and identify the underlying problem before accepting the requested artifact.

Confirm and Handoff Intent

Run a one-question interview until you can predict my next three answers. Restate the confirmed intent with outcome, user, why now, success, constraint, and out of scope.

Лучшие практики

Start with a defensible hypothesis and state what remains unknown.
Ask one focused question at a time, with a reasoned guess attached.
Require explicit confirmation of the concrete restatement before handing off.

Избегать

Do not batch several discovery questions into one message.
Do not accept vague agreement or delegation as explicit confirmation.
Do not create a plan or specification before intent is confirmed.

Часто задаваемые вопросы

When should I use this skill?

Use it when a request is underspecified, conventional, or likely to hide competing priorities.

How many questions will it ask?

It asks only as many focused questions as needed to reach shared understanding.

Can it interview users in batch mode?

No. It requires a live, responsive interaction and asks one question at a time.

What does the final output contain?

The final output is a confirmed intent statement covering outcome, user, timing, success, constraints, and scope exclusions.

Does it write a project plan?

No. It clarifies intent first, then supports a handoff to planning or specification skills.

What happens when I say whatever you think?

The skill treats that response as delegation and asks concrete alternatives instead of treating it as a decision.

Сведения для разработчиков

Автор

addyosmani

Лицензия

MIT

Ревизия Skillstore

Примечание о версии

Автор не указал версию.

Репозиторий

https://github.com/addyosmani/agent-skills/tree/c004a74784a08295d52749b04cda634125b9a581/skills/interview-me

Ссылка

5d5054f8a23586f9b500fece1cb613a9dffc787b

Актуальность поддержки

19.09.2026

Использование

11 загрузок · 1 просмотров

Структура файлов

📄 SKILL.md