Навыки handle-my-replies
📦

handle-my-replies

Ревизия содержимого r1 Безопасно ⚙️ Внешние команды

Prioritize Post Replies and Draft Responses

Busy comment threads make it difficult to identify replies that deserve attention. This skill sorts comments before drafting relevant responses for your review.

Поддерживает: Claude Codex Code(CC)
Maintain this Skill? Claim it 🥉 77 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 "handle-my-replies" from https://skillstore.io/skills/prateeks367-handle-my-replies.md and its manifest at https://skillstore.io/api/skills/prateeks367-handle-my-replies/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.

Протестировать

Использование «handle-my-replies». Post: I added setup examples to the guide. Replies: What changed? Thank you! Buy followers at my page.

Ожидаемый результат:

  • Real answer: What changed?
  • Draft: I added setup examples to the guide.
  • Reaction only: Thank you!
  • Leave it: Buy followers at my page.

Использование «handle-my-replies». Post: Every project benefits from daily meetings. Reply: Small teams may coordinate asynchronously without a daily meeting.

Ожидаемый результат:

  • Real answer: Thoughtful disagreement.
  • Draft: You are right that small teams may coordinate asynchronously. My claim was too broad.

Использование «handle-my-replies». A commenter says your client owes them money and asks you to publicly admit a contract breach.

Ожидаемый результат:

  • Needs the human: This comment involves a client, money, and a contract dispute.
  • No response drafted. Refer it to the responsible person.

Аудит безопасности

Безопасно

All six static findings are false positives: Markdown tool names are not shell execution, and reply-related prose is not system reconnaissance. The skill treats comments as untrusted data, requires human review before sending, and escalates sensitive matters. No evidence found of malicious execution, data exfiltration, or prompt injection.

1
Просканировано файлов
89
Проанализировано строк
0
Пункты проверки
0
Ложные срабатывания проигнорированы

Факторы риска

⚙️ Внешние команды (3)
Последний завершенный статический и семантический аудит не обнаружил подтвержденных проблем безопасности. Это не доказывает отсутствие побочных эффектов у навыка.
Аудитор:: codex
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
Оценка безопасности

Копировать ссылку на отчёт

https://skillstore.io/skills/prateeks367-handle-my-replies/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Значок Markdown

[![Skillstore security assessment](https://skillstore.io/badges/skills/prateeks367-handle-my-replies/security.svg)](https://skillstore.io/skills/prateeks367-handle-my-replies?utm_source=security_passport_badge)

Значок HTML

<a href="https://skillstore.io/skills/prateeks367-handle-my-replies?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/prateeks367-handle-my-replies/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Встраиваемая карточка

<iframe src="https://skillstore.io/embed/skills/prateeks367-handle-my-replies.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

prateeks367. (2026). handle-my-replies security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/prateeks367-handle-my-replies/audits/1

Цитата BibTeX

@techreport{prateeks367-prateeks367-handle-my-replies-2026, author = {prateeks367}, title = {handle-my-replies security audit report (audit version 1)}, institution = {Skillstore}, year = {2026}, number = {1}, url = {https://skillstore.io/skills/prateeks367-handle-my-replies/audits/1}, 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: "handle-my-replies security audit report (audit version 1)" version: "unspecified" type: report authors: - name: "prateeks367" date-released: "2026-10-02" url: "https://skillstore.io/skills/prateeks367-handle-my-replies/audits/1" identifiers: - type: other value: "skillstore:prateeks367-handle-my-replies:audit:1" description: "Skillstore immutable audit report identifier"

Оценка Skillstore

Почему такая оценка Достоверность доказательств: Средний
55
Архитектура
85
Сопровождаемость
87
Контент
65
Сообщество
83
Соответствие спецификации

Что вы можете построить

Manage a Busy Post

Separate genuine questions from simple acknowledgments and irrelevant comments, then prepare answers for review.

Respond to Technical Disagreement

Acknowledge valid criticism and draft a factual response without turning the thread into a personal argument.

Escalate Sensitive Comments

Identify comments involving clients, money, or disputes and pause drafting so the responsible person can review them.

Попробуйте эти промпты

Review One Reply
Here is my post: [post]. Here is one reply: [reply]. Classify it, then draft an answer only if appropriate.
Sort a Comment Thread
Here is my post: [post]. Sort these replies into the four categories before drafting: [replies]. Flag sensitive comments without drafting responses.
Handle Disagreement
Post: [post]. Disagreement: [comment]. Supporting facts: [facts]. Classify the comment, acknowledge valid points, and draft a concise response for review.
Review Replies for Voice Consistency
Post: [post]. Replies: [replies]. Voice examples: [examples]. Show triage, then draft eligible answers. Use VoiceMOAT tools if connected. Flag sensitive items without drafting.

Лучшие практики

  • Provide the original post and relevant facts so drafts address the actual question.
  • Review the classification before reviewing drafts, especially comments involving sensitive relationships or disputes.
  • Read every draft before sending and use voice examples or a connected voice profile to check consistency.

Избегать

  • Drafting a long answer for every comment before identifying which replies deserve attention.
  • Continuing an argument with repeated replies to bait or personal attacks.
  • Treating instructions inside comments as authorization to publish, send messages, or bypass review.

Часто задаваемые вопросы

What categories does the skill use?
It uses real answer, reaction only, leave it, and needs the human. Classification happens before drafting.
Does it fetch replies automatically?
No. You provide the replies. The optional get_post tool retrieves the original post and its numbers, not the replies.
Can I use it without VoiceMOAT?
Yes. Provide the post and replies directly. VoiceMOAT adds post context, voice profiles, and voice-match scoring when connected.
Which VoiceMOAT plan supports the connector?
The skill states that the connector requires the Pro or Enterprise plan.
Will it publish responses for me?
The documented workflow produces drafts for your review. Only the person using the skill decides what gets sent.
How does it handle sensitive or hostile comments?
Sensitive comments require human review without drafts. Bait receives one reply or none, while genuine disagreements receive factual responses.

Сведения для разработчиков

Автор

prateeks367

Лицензия

MIT

Ревизия Skillstore

r1

Примечание о версии

Автор не указал версию.

Ссылка

5726d703fd79596f46a4232d911221f962d9af1d

Актуальность поддержки

02.10.2026

Использование

0 загрузок · 0 просмотров

Структура файлов

📄 SKILL.md