Token导航 LogoToken导航

Agent Skill · 研究检索

ph-safe-messaging(ph 安全消息传递)

ph-safe-messaging 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

ph-safe-messaging 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 56,238。

总安装 461周安装 19GitHub Stars 10下载 150核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:ph-safe-messaging(ph 安全消息传递)
来源仓库:https://github.com/yoanbernabeu/producthunt-skills
仓库路径:skills/ph-safe-messaging
安装命令:
npx skills add https://github.com/yoanbernabeu/producthunt-skills --skill ph-safe-messaging
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/yoanbernabeu/producthunt-skills --skill ph-safe-messaging

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

用于在 Codex、Claude、Cursor、Gemini CLI 中查找、检索和筛选相关信息。适合根据关键词、任务场景或来源线索快速定位候选结果。通过 npx skills add 命令从 GitHub 仓库安装使用。安装前需确认权限范围、维护状态及是否触发联网或文件操作。

ph-safe-messaging 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/ph-safe-messaging

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/yoanbernabeu/producthunt-skills --skill ph-saf…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

ph-safe-messaging 怎么安装?

在终端执行 npx skills add https://github.com/yoanbernabeu/producthunt-skills --skill ph-safe-messagin…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

ph-safe-messaging 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

ph-safe-messaging 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

ph-safe-messaging 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

ph-safe-messaging 用的人多吗?

公开数据是累计安装 461 次,近一周安装 19 次,下载 150 次,GitHub 10 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

ph-safe-messaging 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
ph-safe-messaging

ph 安全消息传递 · 本页

46110只读未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Product Hunt Safe Messaging

This skill helps you write messages that effectively rally support while staying within Product Hunt's community guidelines.

When to Use This Skill

  • Writing launch day emails
  • Creating social media posts
  • Briefing supporters
  • Responding to "how can I help?" questions
  • Crafting any public launch messaging

The Core Principle

NEVER explicitly ask for upvotes.

Product Hunt guidelines are clear: asking or incentivizing people to upvote can trigger algorithm penalties or get your product unfeatured.

Language Conversion Guide

Forbidden → Allowed

❌ Don't Say✓ Say Instead
"Please upvote""Check it out"
"Vote for us""We'd love your support"
"Upvote if you like it""Let us know what you think"
"Every vote counts""Your feedback means a lot"
"Help us reach #1""Excited to share this with you"
"Click the upvote button""Take a look and share your thoughts"
"We need your upvotes""We need your feedback"
"Vote now""Check it out now"

Incentive Language

❌ Don't Say✓ Say Instead
"Upvote for 20% off""PH community gets 20% off"
"Voters get early access""Everyone from PH gets early access"
"First 100 upvoters win""First 100 signups from PH win"
"Vote to enter giveaway""Visit our PH page to enter giveaway"

Safe Message Templates

Email Templates

Template 1: Simple Announcement
Subject: [Product] is live on Product Hunt!

Hey [Name],

We just launched [Product] on Product Hunt!

[One sentence about what it does]

→ Check it out here: [Link]

If you find it useful, we'd really appreciate you
sharing your thoughts in the comments. Honest
feedback helps us improve!

Thanks for your support,
[Your Name]
Template 2: Personal Ask
Subject: Would love your support today

Hey [Name],

Today's a big day — [Product] just went live
on Product Hunt.

After [X months] of building, it's finally out there.
A bit nervous, honestly!

If you have a moment to take a look: [Link]

Any feedback — good or bad — would mean a lot.
And if you think it's cool, sharing it would
make my day.

No pressure either way. Just excited to
share this with you.

[Your Name]
Template 3: For Active Users
Subject: We're on Product Hunt — your experience matters

Hi [Name],

As someone who's been using [Product], I wanted
to let you know we just launched on Product Hunt.

→ [Link]

If you have a moment, I'd love for the PH community
to hear about your experience. Your perspective
as a real user is incredibly valuable.

Of course, only if you genuinely have good things
to say — authentic feedback is what we're after!

Thanks for being an early believer,
[Your Name]

Social Media Templates

Twitter/X

Simple Announcement:

🚀 Just launched [Product] on @ProductHunt!

[One line value prop]

Would love your feedback → [Link]

#ProductHunt

Story Version:

After [X months] of building, [Product] is
finally live on @ProductHunt.

[Why you built it]

Take a look and let me know what you think → [Link]

Progress Update:

Wow! [X] hours into our @ProductHunt launch:

• [X] people have checked it out
• [X] amazing comments and feedback
• Learning so much from this community

Thanks for the support! 🙏 → [Link]
LinkedIn

Professional Announcement:

Excited to share that [Product] launched on
Product Hunt today.

After [context], we built [solution] to help
[target audience] [achieve outcome].

If this sounds relevant to your work, I'd
genuinely appreciate you taking a look and
sharing your professional feedback.

[Link in comments]

#ProductHunt #[Relevant tags]

Supporter Briefing

What to Tell Supporters:

Hey! Just a quick note on how to support our
Product Hunt launch:

PLEASE DO:
✓ Check out the product page
✓ Leave a genuine comment about your thoughts
✓ Share with anyone who might find it useful
✓ Answer any questions others have

PLEASE DON'T:
✗ Just write "Great product!" (low value)
✗ All comment at the exact same time
✗ Create new accounts just to support
✗ Copy/paste the same comment

The most valuable thing? Authentic engagement.
Tell us what you actually think!

Link: [Link]

Responding to "How Can I Help?"

When Someone Asks:

❌ Don't say: "Please go upvote!"

✓ Do say:

Thanks so much for asking!

Here's what would be most helpful:
1. Check out our page: [Link]
2. If you genuinely like it, leave a comment
   with your thoughts
3. Share with anyone you think would find it useful

Your honest feedback is what we're really after.
If you see things we should improve, I want to
hear that too!

Handling Comment Requests

When Preparing Comment Examples:

❌ Don't say: "Please post this exact comment: [script]"

✓ Do say:

Some ideas for what to comment about:
• What problem this solves for you
• A feature you find interesting
• A question about how something works
• Honest feedback on what could be better

Make it your own — authentic voices are way
more valuable than scripted comments!

Platform-Specific Guidelines

In Product Hunt Comments

Allowed:

  • Thanking people genuinely
  • Answering questions
  • Sharing relevant information
  • Acknowledging feedback

Not Allowed:

  • Asking commenters to upvote
  • Self-promotion on other products
  • Spammy responses
  • Begging for support

In Direct Messages

Allowed:

  • Following up on comments
  • Answering specific questions
  • Building genuine relationships

Not Allowed:

  • Mass messaging users
  • Asking strangers to upvote
  • Spamming launch links

In External Communications

Allowed:

  • Announcing your launch
  • Sharing the link
  • Asking for feedback
  • Offering genuine value

Not Allowed:

  • Explicit vote requests
  • Vote-for-reward schemes
  • Misleading urgency
  • Fake scarcity

Safe Messaging Checklist

Before Sending Any Message

  • No explicit vote request
  • No vote-for-reward language
  • Focus on feedback, not voting
  • Genuine, not manipulative
  • Would you be embarrassed if PH saw this?

Message Quality Check

  • Personalized (not mass copy-paste)
  • Clear what you're asking for
  • Respectful of recipient's time
  • Value offered (not just asking)
  • Appropriate for the relationship

Red Flag Phrases

Avoid These Completely

"Upvote" (verb)
"Vote for"
"Click upvote"
"Every vote counts"
"Help us win"
"We need votes"
"Vote to support"
"Upvote if you"
"First to upvote"
"Vote now"

These Are Fine

"Check it out"
"Take a look"
"Share your thoughts"
"Give us feedback"
"Let us know what you think"
"Support our launch"
"We'd appreciate your feedback"
"Leave a comment"
"Tell us what you think"

Output Format

MESSAGE REVIEW FOR: [Product Name]

ORIGINAL MESSAGE:
"[Original text]"

ISSUES FOUND:
- [Issue 1]: [Location in text]
- [Issue 2]: [Location in text]

REVISED MESSAGE:
"[Compliant version]"

COMPLIANCE CHECK:
✓ No explicit vote requests
✓ No vote incentives
✓ Focus on feedback/support
✓ Genuine tone
✓ Appropriate for platform

STATUS: [Compliant / Needs revision]

平台分布

Codex

36.35%
按下载量换算55

Claude

30.26%
按下载量换算45

Cursor

15.74%
按下载量换算24

Gemini CLI

8.23%
按下载量换算12

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills