Token导航 LogoToken导航

Agent Skill · 研究检索

posthog-survey-creator(Posthog 调查创建者)

posthog-survey-creator 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。

posthog-survey-creator 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,权限为调用外部服务;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 42,038。

总安装 1,115周安装 46GitHub Stars 31下载 364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:posthog-survey-creator(Posthog 调查创建者)
来源仓库:https://github.com/posthog/skills
仓库路径:skills/posthog-survey-creator
安装命令:
npx skills add https://github.com/posthog/skills --skill posthog-survey-creator
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/posthog/skills --skill posthog-survey-creator

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。

用于查找、检索和筛选相关信息。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。适合根据关键词或任务场景快速定位候选结果。可结合来源仓库和原始 README 核验具体用法。安装前建议确认权限范围和维护状态。

posthog-survey-creator 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/posthog-survey-creator

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/posthog/skills --skill posthog-survey-creator;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

    它需要调用外部服务,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

posthog-survey-creator 怎么安装?

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

posthog-survey-creator 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。

posthog-survey-creator 需要什么权限?

权限级别是调用外部服务。该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

posthog-survey-creator 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。

posthog-survey-creator 用的人多吗?

公开数据是累计安装 1,115 次,近一周安装 46 次,下载 364 次,GitHub 31 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。

posthog-survey-creator 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。

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。

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
posthog-survey-creator

Posthog 调查创建者 · 本页

1,11531调用外部服务未明确通过

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

PostHog Survey Creator

Guide users through creating effective surveys in PostHog via conversational flow. Target audience: Product Managers who need help with survey design, question wording, and targeting strategy.

Critical Rules

  1. One question per message. Wait for user response before proceeding.
  2. Use PostHog MCP first. When MCP is available, query PostHog for information instead of asking the user. Always present findings for validation.
  3. Only ask users when MCP unavailable. Fall back to questions only if MCP tools aren't accessible.
  4. Always create as draft. Never offer to launch immediately. Surveys are created as drafts so users can review in PostHog before launching.

PostHog MCP Detection

At the start of conversation or when needing PostHog data, attempt to use MCP tools:

  • posthog:event-definitions-list — Get available events
  • posthog:properties-list — Get event or person properties
  • posthog:surveys-get-all — Check existing surveys
  • posthog:feature-flag-get-all — Get feature flags for linking

If MCP works: Use data from PostHog and ask user to validate. If MCP fails/unavailable: Ask user directly about their PostHog setup.

Conversation Flow

Opening: Show the Journey

When user asks to create a survey:

"I'll help you create a survey in PostHog. Here's what we'll figure out together:

1. **Goal** – What do you want to learn?
2. **Questions** – What to ask and how
3. **Audience** – Who should see this?
4. **Timing** – When and how often?

Let's start with the goal. **What do you want to learn from this survey?**"

Wait for response.


Step 1: Understand the Goal

Ask: "What do you want to learn from this survey?"

Listen for keywords to match templates:

KeywordsTemplate
"recommend", "loyalty", "NPS"NPS
"satisfied", "satisfaction"CSAT
"easy", "effort", "friction"CES
"disappointed", "product-market fit"PMF
"why signed up", "jobs to be done"JTBD
"price", "expensive", "value"Pricing
"competitor", "alternatives"Competitive Intel
"not using", "adoption"Feature Adoption
"beta", "new feature"Beta Feedback
"trial", "upgrade"Trial Conversion
"new user", "intent"Welcome Survey
"onboarding", "getting started"Activation
"inactive", "churned", "win back"Dormant User
"cancel", "leaving"Churn/Exit
"support", "ticket"Support CSAT

After response: Present matching template OR explore custom, then proceed.


Step 2: Present Template or Explore Custom

If template matches:
"Based on what you're describing, a **Customer Effort Score (CES)** survey would work well. It measures how easy a task was—lower effort correlates with higher retention.

The standard approach is:
- Q1: Rating (1-7) – 'How easy was it to [task]?'
- Q2: Open text (for low scores) – 'What made this difficult?'

**Does this approach work for you, or would you like to customize it?**"
If no template matches:
"This sounds like a custom survey—I'll help you design one.

**What's the single most important thing you want to learn?**"

Step 3: Finalize Questions

If customizing, ask ONE question at a time until questions are defined.

Once set, confirm:

"Here's what we have:
[list questions]

**Does this look right?**"

Step 4: Define Audience (MCP-First Approach)

This is where PostHog MCP becomes critical. Do not ask the user about events or properties if MCP is available.

With PostHog MCP available:
  1. First, ask the high-level targeting question: "Now let's decide who sees this survey. **Who should see it?** For example: - All users - Users on a specific page - A specific segment (paid users, new users, etc.) - Users who completed a specific action"
  2. Based on their answer, query PostHog and present options: If they mention an action/event: ` [Use posthog:event-definitions-list to find matching events] "I found these events in your PostHog that might match: - report_viewed (1.2k times this month) - report_created (340 times this month) - report_exported (89 times this month) **Which event should trigger the survey?**" **If they mention a user segment:** [Use posthog:properties-list with type="person" to find properties] "I found these person properties you could filter by: - plan (values: free, pro, enterprise) - signed_up_at - company_size **Which property should we use, and what value?**" **If they mention a page:** "Got it—I'll target users on that page. What's the URL or URL pattern? (e.g., '/reports' or contains 'dashboard')"`
  3. If checking for existing similar surveys: [Use posthog:surveys-get-all to check for duplicates] "I noticed you already have an 'NPS Survey' running that targets the dashboard. **Should I create a new one, or would you like to modify the existing survey?**"
  4. If linking to feature flags: ` [Use posthog:feature-flag-get-all if user mentions beta/feature flags] "I found these feature flags that might be relevant: - new-reporting-feature (currently 30% rollout) - beta-dashboard-v2 (10% rollout) **Should the survey only show to users with one of these flags enabled?**" `
Without PostHog MCP (fallback):

If MCP tools fail or aren't available, ask the user directly:

"I don't have access to query your PostHog directly.

**Do you know the event name for when users [complete the action]?**
(If not, we can target by page URL instead)"

Or for properties:

"**What's the property name for [plan/segment] in your PostHog?**
(e.g., 'plan', 'subscription_tier', etc.)"

Step 5: Configure Timing

Ask:

"**Should this survey show once per user, or repeat over time?**

- Once is good for most feedback surveys
- Recurring works for NPS (e.g., every 90 days)"

If recurring, follow up:

"**How often should it repeat?**"

Step 6: Confirm and Create

Summarize and ask for final confirmation:

"Here's the survey I'll create:

**Name:** [name]
**Questions:**
1. [Q1]
2. [Q2]

**Audience:** [targeting details]
**Schedule:** [once/recurring]

I'll create this as a draft so you can review and adjust the styling in PostHog before launching.

**Ready to create it?**"

Wait for confirmation, then use posthog:survey-create with start_date: null (draft).


Step 7: After Creation

"Done! Here's your survey: [link]

It's saved as a draft. From PostHog you can:
- Preview how it looks
- Adjust colors and styling
- Launch when you're ready

**Anything else you'd like help with?**"

MCP Query Patterns

Finding events for targeting

1. User says: "Users who created a report"
2. Query: posthog:event-definitions-list with q="report"
3. Present matches: "I found `report_created`, `report_viewed`, `report_shared`. Which one?"
4. User confirms

Finding person properties

1. User says: "Paid users only"
2. Query: posthog:properties-list with type="person"
3. Look for: plan, subscription, tier, pricing-related properties
4. Present: "I found a `plan` property with values free/pro/enterprise. Should we target `plan` is not `free`?"
5. User confirms

Checking existing surveys

1. Before creating, query: posthog:surveys-get-all
2. Check for similar names or targeting
3. If found: "You have an existing [survey name] with similar targeting. Create new or modify existing?"

Finding feature flags

1. User mentions beta/feature rollout
2. Query: posthog:feature-flag-get-all
3. Present relevant flags: "I found `beta-feature-x`. Link the survey to this flag?"

Example Conversation (With MCP)

User: "I want to create a survey"

Claude: "I'll help you create a survey in PostHog. Here's what we'll figure out together:

  1. Goal – What do you want to learn?
  2. Questions – What to ask and how
  3. Audience – Who should see this?
  4. Timing – When and how often?

Let's start. What do you want to learn from this survey?"


User: "I want to know if the new export feature is easy to use"

Claude: "Great! This is perfect for a Customer Effort Score (CES) survey.

Here's the standard approach:

  • Q1 (Rating 1-7): 'How easy was it to use the export feature?'
  • Q2 (Open text, for low scores): 'What would make it easier?'

Does this work, or would you like to customize it?"


User: "That works"

Claude: "Perfect. Now let's decide who should see this.

Who should see the survey? For example:

  • Everyone
  • Users who've used the export feature
  • A specific segment"

User: "People who have used the export feature"

Claude: [Queries posthog:event-definitions-list with q="export"]

"I found these export-related events in your PostHog:

  • export_completed (2.3k times this month)
  • export_started (2.8k times this month)
  • export_failed (145 times this month)

Which event should trigger the survey? I'd recommend export_completed so users have finished the action."


User: "Yes, export_completed"

Claude: "Got it—survey shows after export_completed.

Should this survey show once per user, or repeat over time?"


User: "Once"

Claude: "Here's the survey I'll create:

Name: Export Feature CES Questions:

  1. Rating (1-7): 'How easy was it to use the export feature?'
  2. Open text (low scores): 'What would make it easier?'

Audience: Users who trigger export_completed Schedule: Once per user

I'll create this as a draft so you can review it in PostHog before launching.

Ready to create it?"


User: "Yes"

Claude: [Creates survey via posthog:survey-create with start_date: null]

"Done! Here's your survey: [link]

It's saved as a draft. You can preview it, adjust the styling, and launch when ready.

Anything else you'd like help with?"


Example Conversation (Without MCP)

User: "People who have used the export feature"

Claude: [MCP query fails or unavailable]

"I can't query your PostHog directly. Do you know the event name for when someone completes an export?

If not, we can target by URL instead (e.g., show on the exports page)."


User: "I think it's called export_done"

Claude: "Got it—I'll use export_done as the trigger event.

Should this survey show once per user, or repeat?"


Question Design Reference

See references/question-examples.md for:

  • 22 survey templates with proven questions
  • Targeting recommendations per survey type
  • Branching logic examples

平台分布

Codex

35.94%
按下载量换算131

Claude

29.95%
按下载量换算109

Cursor

20.12%
按下载量换算73

Gemini CLI

9.07%
按下载量换算33

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

调用外部服务

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

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