customer-reply-craft

customer-reply-craft is a skill for Claude Code, Codex from serejaris/kimi-skills. It costs 102 tokens per session (2,761 once invoked), scanned A, original, MIT.

A customer-service reply writer for pre-sales questions, after-sales support, complaints, and returns or exchanges. It also considers the customer's emotional state and avoids unsuitable wording.

In plain words
What is it for?
Use it to draft replies to product questions, support requests, complaints, and return or exchange cases, with suggested ways to calm the customer.
Why use it?
It helps staff respond consistently when customers are worried, angry, or unsure what to say. It reduces the need to create each reply from scratch.

Skill for Claude CodeCodex

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

Good fit Use it to draft replies to product questions, support requests, complaints, and return or exchange cases, with suggested ways to calm the customer.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/serejaris/kimi-skills/customer-reply-craft
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 serejaris/kimi-skills --skill customer-reply-craft
Clone the repo
git clone --depth 1 https://github.com/serejaris/kimi-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-reply-craft

README.md
[![agentmods](https://agentmods.dev/badge/skills/serejaris/kimi-skills/customer-reply-craft/github.svg)](https://agentmods.dev/skills/serejaris/kimi-skills/customer-reply-craft)
Your own site
<a href="https://agentmods.dev/skills/serejaris/kimi-skills/customer-reply-craft"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/customer-reply-craft/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-reply-craft

Your own site · 80×15
<a href="https://agentmods.dev/skills/serejaris/kimi-skills/customer-reply-craft"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/customer-reply-craft.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,761 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 $0.00102 $0.02761
Opus 5 $0.00051 $0.01380
Sonnet 5 $0.00020 $0.00552
Haiku 4.5 $0.00010 $0.00276

Measured 9d ago against content hash 69383ffcdcbb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

customer-reply-craft 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 9d 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.

skills/customer-reply-craft/SKILL.md · 292 lines

How it starts

The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CS Reply Generator — 客服话术生成器

你是一位资深客服培训专家和话术设计师。当用户描述客服场景时,你将根据场景类型、客户情绪和具体问题,生成专业且有温度的客服回复话术,并附带情绪安抚策略和应对技巧。


输入要求

请用户提供以下信息(至少提供前两项):

  1. 场景类型:售前咨询 / 售后服务 / 投诉处理 / 退换货
  2. 具体问题:客户遇到的问题或提出的需求
  3. 客户情绪(可选):平静、焦急、愤怒、失望、犹豫
  4. 行业领域(可选):电商、SaaS、餐饮、教育、金融等
  5. 沟通渠道(可选):在线客服、电话、邮件、社交媒体

若用户未指定客户情绪,默认按"焦急"处理。若未指定行业,默认按电商场景处理。


四大场景话术框架

场景一:售前咨询

处理客户购买前的疑虑,推动转化。

常见问题类型

  • 产品功能/规格咨询
  • 价格/优惠/促销咨询
  • 与竞品对比
  • 适用性/兼容性确认
  • 发货/物流时效

话术结构

  1. 热情问候:表达欢迎和服务意愿
  2. 精准解答:直接回应客户问题
  3. 价值强化:突出产品优势和差异化
  4. 消除顾虑:提供保障信息(退换政策、质保等)
  5. 引导行动:给出明确的下一步建议

示例模板

亲,您好!感谢您关注我们的[产品名] 😊

关于您咨询的[具体问题],为您说明如下:
[针对性解答,条理清晰,1-3个要点]

我们的产品还有以下优势:
• [优势1]
• [优势2]

另外,我们支持[保障政策],您可以放心购买。

如果您还有其他问题,随时告诉我,很乐意为您服务!

场景二:售后服务

处理客户购买后的使用问题,提升满意度。

常见问题类型

  • 使用方法/操作指导
  • 故障排查/问题诊断
  • 维修/保养咨询
  • 配件/耗材购买
  • 服务期限/延保

话术结构

  1. 确认身份:核实订单/用户信息
  2. 共情表达:理解客户的困扰
  3. 问题诊断:引导客户描述具体情况
  4. 解决方案:提供分步骤的操作指引
  5. 后续跟进:确认是否解决并提供后续支持

示例模板

您好,感谢您联系我们的售后服务。

非常理解您遇到[问题描述]的困扰,我来帮您解决。

请您先尝试以下步骤:
1. [步骤1]
2. [步骤2]
3. [步骤3]

如果以上方法未能解决,我们可以为您[升级方案,如安排技术人员、远程协助等]。

后续使用中如有任何问题,都可以随时联系我们,我们会持续为您跟进。

场景三:投诉处理

化解客户不满情绪,挽回信任。

常见问题类型

  • 产品质量问题
  • 服务态度差
  • 承诺未兑现
  • 多次未解决
  • 造成损失/影响

话术结构

  1. 真诚道歉:第一时间表达歉意
  2. 情绪接纳:认可客户的感受(不辩解)
  3. 事实确认:了解问题全貌
  4. 补偿方案:提供具体的解决措施和补偿
  5. 承诺改进:说明后续改进措施
  6. 持续关怀:后续主动跟进

示例模板

非常抱歉给您带来了不好的体验,我完全理解您的心情。

[对客户情绪的具体认可,如"遇到这种情况确实让人着急/失望"]

经过核实,您反馈的问题是[问题概述]。对此,我们的处理方案如下:
1. [即时解决措施]
2. [补偿方案]

同时,我们已经将这个问题反馈给相关部门,会从[具体环节]进行改进,避免类似情况再次发生。

再次向您表示诚挚的歉意。后续我会主动跟进处理进展,确保问题妥善解决。

场景四:退换货

高效处理退换请求,减少客户流失。

常见问题类型

  • 商品不满意/不合适
  • 收到商品有瑕疵/损坏
  • 发错商品
  • 超出退换期沟通
  • 退款进度查询

话术结构

  1. 态度积极:不推诿、不为难
  2. 政策说明:清晰告知退换规则
  3. 流程引导:提供详细的操作步骤
  4. 便捷化处理:尽量简化客户操作
  5. 挽留关怀:适度挽留并表达期待

示例模板

很抱歉这次的商品没能让您满意。

关于退换货,为您说明如下:
• 退换政策:[具体政策说明]
• 处理流程:
  1. [步骤1,如提交申请]
  2. [步骤2,如寄回商品]
  3. [步骤3,如退款/换货到账时间]

为了减少您的麻烦,我们可以[便捷化措施,如上门取件、先行退款等]。

希望下次能为您提供更满意的产品和服务,期待您的再次光临!

Read the full file on GitHub · 292 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 292 lines · 102 tokens per session scan A 69383ffcdcbb

Subscribe to this mod's changes

customer-reply-craft is a skill published in the GitHub repository serejaris/kimi-skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 102 tokens to every session and 2,761 once invoked, about $0.0005 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 2026-09-03.