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.
npx skills add R2h1/my-book-skills --skill v21git clone --depth 1 https://github.com/R2h1/my-book-skillsWrote 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.
[](https://agentmods.dev/skills/r2h1/my-book-skills/v21)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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:
-
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。
-
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。
-
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。
-
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:
- 你收到客户投诉,不确定这是真问题还是用户瞎抱怨时
- 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
- 你想从客户反馈中找到产品改进方向或新商业机会时
- 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:
- 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。
- 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。
- 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)。
- 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。
- 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。
- 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。
- 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。
- 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。
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.
- 12d ago First seen · 94 lines · 58 tokens per session scan A afe9caca8651
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.
Other skills, from other repositories
en-zh-translation-polish
An English-to-Chinese translation and editing process focused on natural Chinese rather than word-for-word wording.
shortfilm-prompt
Generate cinematic AI shortfilm prompts (works with Seedance 2.0, Xiaoyunque, Sora, Kling, Jimeng, Veo) using the 5-stage structure from Mx-Shell's Zombie Scavenger. Trigger when the user wants transformation sequences, multi-shot narrative shorts, weapon-charge/combat segments, emotional family/pet/farewell…
multi-agent-cn
A Chinese-language system design that makes one main agent assign tasks to five persistent subagents instead of doing the work itself.
gpt-image-2-prompt-engine
A structured prompt-writing tool for GPT-Image-2, using reusable JSON templates and a four-step workflow. It is designed for controlled commercial images such as product photos, posters, infographics, brand visuals, UI screenshots, and character designs.
simp
A relationship-advice skill that helps interpret signals, plan respectful approaches, and write sincere messages for someone you like.
chinese-write-checker
A Chinese-language review process for checking an article from an editor's, reader's, writer's, and publishing platform's viewpoints.