跳到主内容
智客 ZICQ

技能库 智客分类:Agent 工作流 review-management

审查管理

当用户想要分析,回应,或改善其应用评论和评分. 用户提及"审查","评分","负面评分","如何获得更多评分","评分回应",或"我的评分下降"时也使用. 关于更广泛的ASO审计,见aso-oudit. 关于造成审查不佳的留存问题,见留存-优化.

2969 安装量

官方网址:skills.sh

技能介绍

先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。

做什么

当用户想要分析,回应,或改善其应用评论和评分. 用户提及"审查","评分","负面评分","如何获得更多评分","评分回应",或"我的评分下降"时也使用. 关于更广泛的ASO审计,见aso-oudit. 关于造成审查不佳的留存问题,见留存-优化.

何时用

用户提到"审查","评分","负面评分","如何获得更多的评分","审查回应",或"我的评分下降". 关于更广泛的ASO审计,见aso-oudit. 关于造成审查不佳的留存问题,见留存-优化

代理如何加载

按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:Review Management、Initial Assessment、Review Analysis Framework、Sentiment Analysis、Review Metrics to Track、Rating Improvement Strategy。

文件分析

文件分析:这是一份仅含 SKILL.md 的指令型技能,代理激活后整份正文进入上下文。

官方 description(原文)

When the user wants to analyze, respond to, or improve their app reviews and ratings. Also use when the user mentions "reviews", "ratings", "negative reviews", "how to get more reviews", "review response", or "my rating is dropping". For broader ASO audit, see aso-audit. For retention issues causing bad reviews, see retention-optimization.

Review ManagementInitial AssessmentReview Analysis FrameworkSentiment AnalysisReview Metrics to TrackRating Improvement StrategyIn-App Rating Prompt OptimizationHandling Negative ReviewsTurning Detractors into AdvocatesReview Mining for Product InsightsCompetitor Review AnalysisYour Review Patterns

来源分类:skills.sh agent-skill

SKILL.md 与 Agent 调用

官方规范 ↗
name
review-management
description
When the user wants to analyze, respond to, or improve their app reviews and ratings. Also use when the user mentions "reviews", "ratings", "negative reviews", "how to get more reviews", "review response", or "my rating is dropping". For broader ASO audit, see aso-audit. For retention issues causing bad reviews, see retention-optimization.
  1. 发现技能客户端向 Agent 提供名称与描述目录。
  2. 匹配与调用用户指定或任务匹配后,载入 SKILL.md 指令。
  3. 按需加载按步骤读取参考文档、使用脚本与素材。

具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗

安装这个技能

Skills CLI ↗

先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。

交给 Agent 安装

复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。

把 Agent Skill「review-management」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-4e9ae9f6ebd0fc4c-%E5%AE%A1%E6%9F%A5%E7%AE%A1%E7%90%86.html
请存为 .cursor/skills/review-management/SKILL.md 或 .claude/skills/review-management/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。

GitHub 完整包 ↗

终端安装 · Skills CLI

需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。

npx skills add 'https://github.com/appeeky/aso-skills' --list

npx skills add 'https://github.com/appeeky/aso-skills' --skill 'review-management'

CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。

阅读排版

name: review-management description: When the user wants to analyze, respond to, or improve their app reviews and ratings. Also use when the user mentions "reviews", "ratings", "negative reviews", "how to get more reviews", "review response", or "my rating is dropping". For broader ASO audit, see aso-audit. For retention issues causing bad reviews, see retention-optimization. metadata: version: 1.0.0

Review Management

You are an expert in app review strategy and reputation management. Your goal is to help the user turn reviews into a growth lever — improving ratings, gaining insights, and building user trust.

Initial Assessment

  1. Check for app-marketing-context.md — read it for context
  2. Ask for the App ID (to fetch current reviews)
  3. Ask for target country (default: US)
  4. Ask about their current rating and trend (improving or declining?)
  5. Ask if they currently respond to reviews

Review Analysis Framework

Sentiment Analysis

Categorize reviews into:

| Category | Description | Action | |----------|-------------|--------| | Bugs & Crashes | Technical issues | Fix and respond with timeline | | Feature Requests | Users want something new | Track frequency, consider for roadmap | | UX Complaints | Confusing or frustrating flows | Prioritize UX improvements | | Pricing Complaints | Too expensive, paywall issues | Review monetization strategy | | Love & Praise | Positive feedback | Thank and ask for sharing | | Competitor Mentions | Users comparing to alternatives | Understand competitive gaps |

Review Metrics to Track

| Metric | Target | Why | |--------|--------|-----| | Average rating | 4.5+ stars | Below 4.0 significantly hurts conversion | | Rating trend | Stable or improving | Declining trend signals problems | | Review velocity | Consistent | Sudden drops may indicate prompt issues | | Response rate | 100% of negative | Shows you care, can change ratings | | Response time | < 24 hours | Fast responses build trust |

Rating Improvement Strategy

In-App Rating Prompt Optimization

When to show the prompt:

  • After a positive experience (completed a task, achieved a goal)
  • After the user has used the app 3+ times
  • After at least 7 days of usage
  • Never after a crash, error, or frustrating moment
  • Never during onboarding or first session

Apple's SKStoreReviewController rules:

  • Can only be called 3 times per 365-day period per device
  • Apple controls when the dialog actually appears
  • You cannot customize the dialog
  • You can control WHEN you call it (timing is everything)

Smart trigger patterns:

  1. Achievement trigger — User completes a milestone
  2. Streak trigger — User returns for N consecutive days
  3. Value trigger — User saves money, time, or achieves a result
  4. Delight trigger — After a moment of surprise or delight

Handling Negative Reviews

Response framework (HEAR):

  1. Hear — Acknowledge the specific issue they mentioned
  2. Empathize — Show you understand their frustration
  3. Act — Explain what you're doing about it (or have done)
  4. Resolve — Invite them to contact support for direct help

Response templates:

Bug report:

Thank you for reporting this, [name]. We identified the issue and it's fixed in version [X.X] releasing [date]. We appreciate your patience — please update when available and let us know if it resolves the issue.

Feature request:

Great suggestion! We've added this to our roadmap. We're always looking to improve based on user feedback. Stay tuned for upcoming updates.

Vague negative ("This app sucks"):

We're sorry to hear about your experience. We'd love to understand what went wrong so we can improve. Could you reach out to [support email] with details? We're here to help.

What NOT to do:

  • Don't be defensive or argumentative
  • Don't copy-paste the same response to every review
  • Don't ignore negative reviews
  • Don't ask users to change their rating (against guidelines)
  • Don't offer incentives for reviews

Turning Detractors into Advocates

  1. Fix the issue they reported
  2. Respond acknowledging the fix
  3. Follow up via support if they contacted you
  4. Many users will update their review after a positive resolution

Review Mining for Product Insights

Competitor Review Analysis

Read competitor reviews to find:

  • Unmet needs — What do users wish the competitor had?
  • Common complaints — What frustrates users? (your opportunity)
  • Switching triggers — Why do users leave competitors?
  • Feature expectations — What's table stakes in the category?

Your Review Patterns

Analyze your reviews for:

  • Most mentioned features (positive and negative)
  • Common user segments (who uses your app?)
  • Emotional language (what feelings does your app evoke?)
  • Comparison mentions (which competitors do users mention?)

Output Format

Review Health Report

Rating:           [X.X] ★ ([trend: ↑/↓/→])
Total Reviews:    [N]
Last 30 Days:     [N] reviews, [X.X] avg rating
Response Rate:    [X]%

Top Issues:
1. [issue] — mentioned [N] times
2. [issue] — mentioned [N] times
3. [issue] — mentioned [N] times

Top Praise:
1. [praise] — mentioned [N] times
2. [praise] — mentioned [N] times

Action Plan

  1. Immediate: [respond to X negative reviews using templates]
  2. This week: [fix top reported bug, optimize rating prompt timing]
  3. This month: [implement top feature request, analyze competitor reviews]

Response Drafts

Provide specific response drafts for the most impactful negative reviews.

Related Skills

  • aso-audit — Reviews as part of broader ASO health check
  • retention-optimization — Fix retention issues causing bad reviews
  • competitor-analysis — Mine competitor reviews for insights
  • app-analytics — Track review metrics over time

相关技能

Agent 工作流

技能创建者Skill Creator

创造有效技能指南。 当用户想创造出新的技能(或更新现有的技能),以专业知识,工作流程,或工具集成来扩展克洛德的能力时,应该使用这种技能.

Agent 工作流

克劳德胡布Clawdhub

使用ClawdHub CLI搜索,安装,更新并发布从taladhub.com的代理技能. 需要获取苍蝇上的新技能时使用,将安装的技能同步到最新版本或特定版本,或者发布 npm-instainddhub CLI 的新/更新的技能文件夹.

Agent 工作流

团队指挥Agent Team Orchestration

管弦乐团多代理团队,任务设定周期,交接协议,审查工作流程. 使用时间: (1)建立2+特派员队伍,具有不同专业,(2)确定任务路线和生命周期(收录框_ spec_建设_审查_完成),(3)在特派员之间制定交接协议,(4)建立审查和质量关口,(5)管理特派员之间的交流和文物共享.

Agent 工作流

超级力量Superpowers

Spec-first,TDD,子代理驱动的软件开发工作流程. 当:(1)构建任何新功能或应用——触发脑暴_计划_子代理执行回路,(2)调试出一个bug或测试失败——触发系统性的根起过程,(3)用户说"让我们构建","帮助我计划","我想添加X",或"这个被打破",(4)完成一个功…