customer-complaint-four-categories

customer-complaint-four-categories is a skill for Claude Code, Codex from R2h1/my-book-skills. It costs 58 tokens per session (1,919 once invoked), scanned A, original, MIT.

A framework for sorting customer complaints into four types: resistance to change, unmet expectations, unmet needs, and deliberate fraud.

In plain words
What is it for?
Use it to interpret customer feedback, decide whether to change a product or its promises, find possible product opportunities, and handle dishonest complaints.
Why use it?
It helps teams respond appropriately instead of treating every complaint as the same problem or wasting effort on the wrong fix.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to interpret customer feedback, decide whether to change a product or its promises, find possible product opportunities, and handle dishonest complaints.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/r2h1/my-book-skills/v21
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add R2h1/my-book-skills --skill v21
Clone the repo
git clone --depth 1 https://github.com/R2h1/my-book-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for customer-complaint-four-categories

README.md
[![agentmods](https://agentmods.dev/badge/skills/r2h1/my-book-skills/v21/github.svg)](https://agentmods.dev/skills/r2h1/my-book-skills/v21)
Your own site
<a href="https://agentmods.dev/skills/r2h1/my-book-skills/v21"><img src="https://agentmods.dev/badge/skills/r2h1/my-book-skills/v21/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for customer-complaint-four-categories

Your own site · 80×15
<a href="https://agentmods.dev/skills/r2h1/my-book-skills/v21"><img src="https://agentmods.dev/badge/skills/r2h1/my-book-skills/v21.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,919 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00058 $0.01919
Opus 5 $0.00029 $0.00959
Sonnet 5 $0.00012 $0.00384
Haiku 4.5 $0.00006 $0.00192

Measured 12d ago against content hash afe9caca8651, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

customer-complaint-four-categories scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

百万富翁快车道/v21-客户抱怨四分类处理/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

客户抱怨四分类处理框架

R — 原文 (Reading)

抱怨有4类:变化、期望、无效投诉、欺诈投诉。对改变的抱怨信息含量极少时,最难破译。期望方面的投诉暴露了你的业务或营销策略方面的问题。无效投诉暴露了有待满足的需求。欺诈投诉是设计非法的投诉敲诈企业主。1个投诉意味着还有10个人也有同样的意见。 — MJ·德马科, 第40章

I — 方法论骨架 (Interpretation)

客户抱怨不是麻烦,而是免费的市场调研。关键是要学会分类——不同类别的抱怨需要完全不同的处理方式。乱分类会导致你把精力花在错误的地方。

四类投诉及其处理原则:

  1. 变化类(Change):用户对改变的自然抵触。即使改变是好的(如UI改版、流程优化),总有一部分用户会抱怨。处理原则:结合数据判断,如果核心指标(转化率、留存率)未下降,坚持改变;如果指标下降,回滚或调整。

  2. 期望类(Expectation):产品或服务未达到客户预期。这暴露了业务问题(产品有缺陷)或营销问题(过度承诺)。处理原则:真诚道歉+快速解决问题+调整营销话术,避免再次制造错误期望。

  3. 无效投诉(Invalid):客户表达了未被满足的需求——"要是能XX就好了"。这隐藏着商业机会。处理原则:认真记录,分析背后的真实需求,评估是否值得开发新功能或新产品。

  4. 欺诈投诉(Fraud):恶意投诉,设计来敲诈企业主(如"不给钱就给差评")。处理原则:优雅回应,提供合理范围内的补偿,但不屈服于勒索。大多数欺诈投诉会在你展现出专业和坚定后消失。

核心法则:1个投诉意味着还有10个人有同样的意见但没说出口。不要只看投诉本身,要看它代表了多少沉默的客户。

A1 — 书中的应用 (Past Application)

作者网站重新设计失败(变化类):作者花了6周重新设计网站,上线后用户大量抱怨。跳出率飙升,转化率暴跌,业务量从每天1200降到500。这是典型的变化类投诉——即使新设计客观上更好,用户也需要适应。但作者通过数据判断(核心指标全线下降)确认这不是"适应期",而是设计本身有问题。他立即回滚旧版本。如果核心指标没下降,他会坚持新设计。

银行1万美元错误扣款(期望类):作者在银行账单上发现1万美元错误扣款。他对致电银行的预期是自动语音系统、多层菜单转接、口音不清的外包客服——这就是客户服务现状带来的"低期望"。作者认为这是一个商业机会:如果你能提供"超越预期的客户服务"(真人接听、快速解决),就能把客户变成忠实传道者。

论坛用户的抱怨发现(无效投诉变机会):当客户说"要是能自动生成报告就好了",这不是投诉——是无效投诉,暴露了一个未被满足的需求。认真记录并评估,这可能是一个新功能、新产品,甚至是独立的新业务。

A2 — 触发场景 (Future Trigger)

触发场景

  1. 你收到客户投诉,不确定这是真问题还是用户瞎抱怨时
  2. 团队被大量投诉消耗精力,你不知道哪些该重视哪些该忽略时
  3. 你想从客户反馈中找到产品改进方向或新商业机会时
  4. 你发现同一类型的投诉反复出现时

语言信号

  • "客户又投诉了"
  • "这个用户太挑剔了"
  • "用户说不如以前好用了"
  • "客户要求我们做XX"
  • "客户说被骗了,要差评"

与相邻skill的区分:这个skill在你已经有生意/产品后使用,帮你分类处理收到的投诉。v19-抱怨是金矿是主动去发现机会(还没开始做生意时的需求发现),而这里是你已经有了客户基础后被动收到的反馈。

E — 可执行步骤 (Execution)

当技能被激活后,按以下步骤执行:

  1. 收集并记录所有投诉:将最近一周的所有客户投诉整理到一个文档中,包括投诉内容、来源、频率。
  2. 按四类分类:将每条投诉标记为变化类、期望类、无效投诉或欺诈投诉。注意:一条投诉可能包含多个类别的元素,以主导类别为准。
  3. 按优先级排序:优先级排序为:期望类(影响现有客户体验)> 无效投诉(隐藏新机会)> 变化类(需数据判断)> 欺诈投诉(最小化精力投入)。
  4. 期望类处理:立即修复产品问题或调整营销承诺。对受影响客户做出补偿,挽回信任。
  5. 无效投诉处理:将同类无效投诉归集,评估其背后的需求规模。如果5个以上客户提出同一需求,值得认真调研。
  6. 变化类处理:提取核心业务指标,对比变化前后的数据。指标上升→坚持并安抚用户;指标下降→回滚或调整。
  7. 欺诈投诉处理:按标准流程回应,不额外投入情绪和精力。如果反复出现同一种欺诈模式,升级防护措施。
  8. 建立投诉周报机制:每周汇总投诉分类数据,关注类别分布的变化趋势——期望类减少说明产品在变好,无效投诉增加可能说明市场有新需求。

Read the full file on GitHub · 94 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 94 lines · 58 tokens per session scan A afe9caca8651

Subscribe to this mod's changes

customer-complaint-four-categories is a skill published in the GitHub repository R2h1/my-book-skills (2 stars, last pushed 27d ago), licensed MIT. It adds 58 tokens to every session and 1,919 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.