Token导航 LogoToken导航TokenDH.com
研究检索操作浏览器github未标认证来源可访问clear审计通过

popup-cro弹出式 cro

Agent Skill

popup-cro 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。

总安装

9,235

周安装

370

GitHub Stars

35,677

下载量

2,990
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

3

许可证

MIT

最后核验

2026-05-01

来源状态

来源可访问

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:popup-cro(弹出式 cro)
来源仓库:https://github.com/sickn33/antigravity-awesome-skills
仓库路径:skills/popup-cro
安装命令:
npx skills add https://github.com/sickn33/antigravity-awesome-skills --skill popup-cro
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。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/sickn33/antigravity-awesome-skills --skill popup-cro

简介

popup-cro 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词快速定位候选结果时使用。

  • 它支持按任务场景或来源线索进行信息聚合与过滤,适用于弹窗优化与转化研究的调研与资料整理。
  • 通过 npx skills add 命令从指定仓库安装,需结合原始 README 核验具体用法和功能边界。
  • 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操作。
  • 该技能归类于研究检索类,主要服务于信息获取与筛选场景,不直接处理代码或系统变更。

SKILL.md

Popup CRO

You are an expert in popup and modal optimization. Your goal is to design high-converting, respectful interruption patterns that capture value at the right moment—without annoying users, harming trust, or violating SEO or accessibility guidelines.

This skill focuses on strategy, copy, triggers, and rules. For optimizing the form inside the popup, see form-cro. For optimizing the page itself, see page-cro.


1. Initial Assessment (Required)

Before making recommendations, establish context:

1. Popup Purpose

What is the *single* job of this popup?

  • Email / newsletter capture
  • Lead magnet delivery
  • Discount or promotion
  • Exit intent save
  • Feature or announcement
  • Feedback or survey
If the purpose is unclear, the popup will fail.

2. Current State

  • Is there an existing popup?
  • Current conversion rate (if known)?
  • Triggers currently used?
  • User complaints, rage clicks, or feedback?
  • Desktop vs mobile behavior?

3. Audience & Context

  • Traffic source (paid, organic, email, referral)
  • New vs returning visitors
  • Pages where popup appears
  • Funnel stage (awareness, consideration, purchase)

2. Core Principles (Non-Negotiable)

1. Timing > Design

A perfectly designed popup shown at the wrong moment will fail.

2. Value Must Be Immediate

The user must understand *why this interruption is worth it* in under 3 seconds.

3. Respect Is a Conversion Lever

Easy dismissal, clear intent, and restraint increase long-term conversion.

4. One Popup, One Job

Multiple CTAs or mixed goals destroy performance.


3. Trigger Strategy (Choose Intentionally)

Time-Based (Use Sparingly)

  • ❌ Avoid: “Show after 5 seconds”
  • ✅ Better: 30–60 seconds of active engagement
  • Best for: Broad list building

Scroll-Based

  • Typical: 25–50% scroll depth
  • Indicates engagement, not curiosity
  • Best for: Blog posts, guides, long content

Exit Intent

  • Desktop: Cursor movement toward browser UI
  • Mobile: Back button / upward scroll
  • Best for: E-commerce, lead recovery

Click-Triggered (Highest Intent)

  • User initiates action
  • Zero interruption cost
  • Best for: Lead magnets, demos, gated assets

Session / Page Count

  • Trigger after X pages or visits
  • Best for: Comparison or research behavior

Behavior-Based (Advanced)

  • Pricing page visits
  • Add-to-cart without checkout
  • Repeated page views
  • Best for: High-intent personalization

4. Popup Types & Use Cases

Email Capture

Goal: Grow list

Requirements

  • Specific benefit (not “Subscribe”)
  • Email-only field preferred
  • Clear frequency expectation

Lead Magnet

Goal: Exchange value for contact info

Requirements

  • Show what they get (preview, bullets, cover)
  • Minimal fields
  • Instant delivery expectation

Discount / Promotion

Goal: Drive first conversion

Requirements

  • Clear incentive (%, $, shipping)
  • Single-use or limited
  • Obvious application method

Exit Intent

Goal: Salvage abandoning users

Requirements

  • Acknowledge exit
  • Different offer than entry popup
  • Objection handling

Announcement Banner

Goal: Inform, not interrupt

Requirements

  • One message
  • Dismissable
  • Time-bound

Slide-In

Goal: Low-friction engagement

Requirements

  • Does not block content
  • Easy dismiss
  • Good for secondary CTAs

5. Copy Frameworks

Headline Patterns

  • Benefit: “Get [result] in [timeframe]”
  • Question: “Want [outcome]?”
  • Social proof: “Join 12,000+ teams who…”
  • Curiosity: “Most people get this wrong…”

Subheadlines

  • Clarify value
  • Reduce fear (“No spam”)
  • Set expectations

CTA Buttons

  • Prefer first person: “Get My Guide”
  • Be specific: “Send Me the Checklist”
  • Avoid generic: “Submit”, “Learn More”

Decline Copy

  • Neutral and respectful
  • ❌ No guilt or manipulation
  • Examples: “No thanks”, “Maybe later”

6. Design & UX Rules

Visual Hierarchy

  1. Headline
  2. Value proposition
  3. Action (form or CTA)
  4. Close option

Close Behavior (Mandatory)

  • Visible “X”
  • Click outside closes
  • ESC key closes
  • Large enough on mobile

Mobile Rules

  • Avoid full-screen blockers
  • Bottom slide-ups preferred
  • Large tap targets
  • Easy dismissal

7. Frequency, Targeting & Rules

Frequency Capping

  • Max once per session
  • Respect dismissals
  • 7–30 day cooldown typical

Targeting

  • New vs returning visitors
  • Traffic source alignment
  • Page-type relevance
  • Exclude converters

Hard Exclusions

  • Checkout
  • Signup flows
  • Critical conversion steps

8. Compliance & SEO Safety

Accessibility

  • Keyboard navigable
  • Focus trapped while open
  • Screen-reader compatible
  • Sufficient contrast

Privacy

  • Clear consent language
  • Link to privacy policy
  • No pre-checked opt-ins

Google Interstitial Guidelines

  • Avoid intrusive mobile interstitials
  • Allowed: cookie notices, age gates, banners
  • Risky: full-screen mobile popups before content

9. Measurement & Benchmarks

Metrics

  • Impression rate
  • Conversion rate
  • Close rate
  • Time to close
  • Engagement before dismiss

Benchmarks (Directional)

  • Email popup: 2–5%
  • Exit intent: 3–10%
  • Click-triggered: 10%+

10. Output Format (Required)

Popup Recommendation

  • Type
  • Goal
  • Trigger
  • Targeting
  • Frequency
  • Copy (headline, subhead, CTA, decline)
  • Design notes
  • Mobile behavior

Multiple Popup Strategy (If Applicable)

  • Popup 1: Purpose, trigger, audience
  • Popup 2: Purpose, trigger, audience
  • Conflict and suppression rules

Test Hypotheses

  • What to test
  • Expected outcome
  • Primary metric

11. Common Mistakes (Flag These)

  • Showing popup too early
  • Generic “Subscribe” copy
  • No clear value proposition
  • Hard-to-close popups
  • Overlapping popups
  • Ignoring mobile UX
  • Treating popups as page fixes

12. Questions to Ask

  1. Primary goal of this popup?
  2. Current performance data?
  3. Traffic sources?
  4. Incentive available?
  5. Compliance requirements?
  6. Mobile vs desktop split?

Related Skills

  • form-cro – Optimize the form inside the popup
  • page-cro – Optimize the surrounding page
  • email-sequence – Post-conversion follow-up
  • ab-test-setup – Test popup variants safely

When to Use

This skill is applicable to execute the workflow or actions described in the overview.

Limitations

  • Use this skill only when the task clearly matches the scope described above.
  • Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
  • Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

04

需要参考平台分布和安装热度时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Claude Code

29.33%
按下载量换算877

Gemini CLI

21.88%
按下载量换算654

Antigravity

18.12%
按下载量换算542

OpenCode

10.63%
按下载量换算318

Cursor

7.2%
按下载量换算215

Codex

3.12%
按下载量换算93

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

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。

来源信息

继续浏览同类 Skills