cs-draft-response

cs-draft-response is a skill for Claude Code from modu-ai/moai-cowork. It costs 87 tokens per session (1,794 once invoked), scanned A, original, Apache-2.0.

A customer-support reply writer for Korean email, chat, app messages, official letters, and social-media direct messages. It adapts the wording and level of formality to the communication channel.

In plain words
What is it for?
Use it to draft answers about refunds, exchanges, returns, delivery, and other customer questions, with versions suited to email, Kakao chat, app chat, official letters, or social DMs.
Why use it?
It helps support staff write consistent, polite replies that acknowledge the problem, explain the resolution, and tell the customer what happens next.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the moai-cs plugin — 6 skills, 2 agents shipped together

Good fit Use it to draft answers about refunds, exchanges, returns, delivery, and other customer questions, with versions suited to email, Kakao chat, app chat, official letters, or social DMs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/modu-ai/moai-cowork/cs-draft-response
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 modu-ai/moai-cowork --skill cs-draft-response
Clone the repo
git clone --depth 1 https://github.com/modu-ai/moai-cowork

Made for: Claude Code.

Or install moai-cs, the plugin that ships this one along with the rest of its 6 skills, 2 agents.

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 cs-draft-response

README.md
[![agentmods](https://agentmods.dev/badge/skills/modu-ai/moai-cowork/cs-draft-response/github.svg)](https://agentmods.dev/skills/modu-ai/moai-cowork/cs-draft-response)
Your own site
<a href="https://agentmods.dev/skills/modu-ai/moai-cowork/cs-draft-response"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/cs-draft-response/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 cs-draft-response

Your own site · 80×15
<a href="https://agentmods.dev/skills/modu-ai/moai-cowork/cs-draft-response"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/cs-draft-response.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,794 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00087 $0.01794
Opus 5 $0.00044 $0.00897
Sonnet 5 $0.00017 $0.00359
Haiku 4.5 $0.00009 $0.00179

Measured 5d ago against content hash c5f7b02edf6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

cs-draft-response 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 5d 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.

plugins/moai-cs/skills/cs-draft-response/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

응답 초안 작성 (Draft Response)

개요

고객 문의에 대한 응답 초안을 한국어 경어로 작성합니다. 이메일, 카카오채팅, 앱 내 메시지, 공식 답변서 등 채널별 어조와 형식에 맞춰 초안을 생성합니다. 2026년 한국 CX 트렌드에 맞춰 공감 우선 + 해결책 명확화 + AI 투명성 원칙을 준수합니다.

트리거 키워드

응답 초안, 답변 작성, 이메일 답장, 고객 응대, 메시지 초안, 공식 답변, CS 답변, 답변 템플릿, 문의 답변

워크플로우

  1. 문의 유형 파악: cs-ticket-triage 스킬 연동 또는 직접 입력된 문의 내용 분석
  2. 채널 선택: 이메일 / 카카오채널 / 앱 내 채팅 / 공식 서한 / SNS DM
  3. 어조 설정:
    • 공식: 공문서·법적 답변, 높임말 최고 수준
    • 표준: 이메일·헬프데스크, 정중한 비즈니스 어조
    • 친근: 채팅·SNS, 부드러운 고객 접점 어조
  4. 초안 생성: 공감 → 상황 확인 → 해결책 → 다음 단계 구조로 작성
  5. 품질 체크: 경어 일관성, 개인정보 마스킹, 부정적 표현 검토

응답 구조 원칙

1. 공감 인사: "고객님, 불편을 드려 진심으로 죄송합니다."
2. 상황 확인: "말씀하신 [주문번호/문제]를 확인하였습니다."
3. 해결책: 구체적인 처리 방안 또는 타임라인 명시
   — 환불·교환·반품 문의는 `references/kr-ecommerce-cs-law.md`(청약철회 7일·하자 기한·반품비 부담·소비자분쟁해결기준)를 확인해 법정 기준보다 불리한 안내를 하지 않도록 합니다
4. 다음 단계: 고객이 해야 할 행동 또는 처리 완료 예정일
5. 마무리: 지속적인 지원 의사 표명

채널별 어조 가이드

채널 어조 길이 특징
이메일 정중·공식 200-400자 제목 포함, 서명 필수
카카오채널 친근·간결 100-200자 이모지 선택적, 빠른 응답
앱 내 채팅 표준·신속 50-150자 실시간성 강조
공식 서한 격식·법적 500자+ 날짜·수신인·발신인 필수
SNS DM 친근·공개 100자 이내 공개 가능성 고려

2026년 한국 CS 응답 핵심 원칙

  • 반복 설명 방지: 고객 74%가 여러 상담사에게 같은 내용 반복 시 불만 표출. 이전 대화 컨텍스트를 응답에 반영
  • 24시간 응대: 소비자 74%가 24시간 응대 기대. 즉시 응답 불가 시 자동 접수 확인 메시지 초안 포함
  • AI 투명성: AI 생성 응답임을 표시할 경우 근거 설명 포함 권장 (고객 95% 요구)
  • 감정 우선: 필코노미 트렌드 — 해결책 전 공감 표현이 고객 만족도를 결정

산출물

  • 채널별 맞춤 응답 초안 (한국어 경어)
  • 대안 어조 버전 (공식/표준/친근 3종)
  • 후속 조치 안내문
  • 자동 접수 확인 메시지 (즉시 응답용)

참고 사항

  • 경어 레벨: "합니다/습니다" 체 사용 필수. "해요" 체는 채팅 채널에만 선택적 허용
  • 부정 표현 지양: "안 됩니다", "불가능합니다" 대신 "처리해 드릴 수 있는 방법은..." 형식 사용
  • 약속 주의: 정확한 처리 기한 미확인 시 "영업일 기준 3-5일 내" 등 범위 표현 사용
  • 개인정보: 응답에 고객 주민번호, 카드번호, 계좌번호 직접 기재 금지

문제 해결

상황 해결 방법
티켓 원문 접근 불가 문의 내용을 요약해서 입력해 주시면 그에 맞는 초안을 작성합니다
고객 정보 부족 "고객님" 형식의 일반 호칭으로 작성 후 나중에 맞춤화할 수 있습니다
사내 답변 가이드라인 존재 가이드라인 핵심 원칙을 알려주시면 그에 맞춰 조정합니다
법적 분쟁 가능성 있는 문의 법적 주의사항을 포함한 신중한 어조로 작성하며 법무팀 검토를 권장합니다

Read the full file on GitHub · 109 lines

Files

What ships with it

3 files 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. 5d ago First seen · 109 lines · 87 tokens per session scan A c5f7b02edf6e

Subscribe to this mod's changes

cs-draft-response is a skill published in the GitHub repository modu-ai/moai-cowork (298 stars, last pushed 6d ago), licensed Apache-2.0. It adds 87 tokens to every session and 1,794 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

xml-config-migrating

Use this skill when a Shopware plugin or app-server extension needs its XML configuration migrated to PHP — phrases like "migrate services.xml", "convert my plugin config to PHP", "xml to php migration", "fix the XML deprecation", "prepare my plugin for Shopware 6.8 / Symfony 8", or when a deprecation like "The XML…

shopwareLabs/ai-coding-tools · 106 tokens

dev-environment-bootstrapping

Use this skill when the user asks to bootstrap, set up, create, or initialize a Shopware development environment from scratch — phrases like "set up a Shopware dev environment", "clone and install Shopware", "initialize a Shopware plugin project", "bootstrap Shopware and a new plugin called X", "get a fresh Shopware…

shopwareLabs/ai-coding-tools · 144 tokens

recipe-log-deal-update

Append a deal status update to a Google Sheets sales tracking spreadsheet.

fakoli/fakoli-plugins · 19 tokens

product-configurator-design

Designing build-your-own product configurators (Tesla-style, custom-pricing, plan-builders) with constraint logic, real-time pricing, validation, and save-and-share mechanics. Honest about infinite-options (decision paralysis), canned-bundles-only (no real customization), and guided-configuration (smart defaults plus…

rampstackco/claude-skills · 129 tokens

marketplace-purchase-vetting

Use this when the user asks whether a local listing is a scam, "too good to be true," worth looking at, or a good deal. Also use this when he asks you to find options — search/discover candidates, then vet the best ones. The goal is not a generic buying guide; it is a practical risk read with clear next steps.

AtlasOmnia/donna-starter · 72 tokens

email-personalization

Write hyper-personalized cold email icebreakers for B2B leads using their company intelligence and LinkedIn data. Use this skill whenever the user says "write icebreakers", "personalize emails", "email personalization", "cold email first lines", "write opening lines", "personalize outreach", "create email openers", or…

naveedharri/benai-skills · 134 tokens