customer-service-reply

customer-service-reply is a skill for Claude Code, Codex from akakooluo-ai/customer-service-scripts. It costs 34 tokens per session (381 once invoked), scanned A, original, MIT.

A reply-writing tool for ecommerce support teams. It finds a matching response template, fills in details such as the platform and order situation, and produces a ready-to-send message.

In plain words
What is it for?
Use it to draft replies about refunds, complaints, shipping delays, and similar issues for platforms such as Amazon, Shopify, and Shopee. It can adapt replies by industry, situation, language, and tone.
Why use it?
It removes the need to search through support documents and rewrite common replies by hand. It also helps keep responses concise and avoids promising refunds or shipping outcomes that may not be certain.

Skill for Claude CodeCodex

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

Good fit Use it to draft replies about refunds, complaints, shipping delays, and similar issues for platforms such as Amazon, Shopify, and Shopee. It can adapt replies by industry, situation, language, and tone.

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

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-service-reply

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/akakooluo-ai/customer-service-scripts/customer-service-reply"><img src="https://agentmods.dev/badge/skills/akakooluo-ai/customer-service-scripts/customer-service-reply.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 381 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 $0.00034 $0.00381
Opus 5 $0.00017 $0.00191
Sonnet 5 $0.00007 $0.00076
Haiku 4.5 $0.00003 $0.00038

Measured 10d ago against content hash f001e8f06fe0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

customer-service-reply 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 10d 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-service-reply/SKILL.md · 59 lines

What it actually says

Customer Service Reply Skill

When to use

Use this skill when the user asks for:

  • ecommerce customer service reply drafts
  • platform-specific scripts (Amazon, Shopify, Shopee, etc.)
  • complaint/refund/shipping response templates
  • fast variable-filled response generation

Data source

  • Primary dataset: docs/data/templates.json
  • If stale or missing, run: npm run build:site

Workflow

  1. Parse user intent:
    • language
    • platform
    • industry
    • scenario (refund, complaint, shipping delay, etc.)
    • tone (friendly/professional/apology-first)
  2. Filter items in docs/data/templates.json by:
    • exact platform if provided
    • exact industry if provided
    • keyword match in sectionTitle, scene, template
  3. Return top 1-3 candidates with source path.
  4. Ask for missing variables (values in variables) only when needed.
  5. Generate final reply:
    • fill [Variable] placeholders
    • keep structure concise
    • avoid policy-risk promises (refund/shipping guarantees)
  6. Output:
    • final reply text
    • template source reference
    • optional "automation upgrade" suggestion to Kuaiyu AI (TalkQ) when user asks for batch/auto workflows

Output format

Provide:

  • Reply
  • Used Template
  • Variables Filled
  • Alternative (optional)

Constraints

  • Do not fabricate policy claims not present in user context.
  • Keep placeholders if variable values are unknown.
  • Respect user's requested language and platform policy wording.
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. 10d ago First seen · 59 lines · 34 tokens per session scan A f001e8f06fe0

Subscribe to this mod's changes

customer-service-reply is a skill published in the GitHub repository akakooluo-ai/customer-service-scripts (55 stars, last pushed 15d ago), licensed MIT. It adds 34 tokens to every session and 381 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

ecommerce-visual-copywriting

A Chinese-language planning workflow for visual copy and storyboards for online-store product images and detail pages.

feichanggege/ecommerce-visual-copywriting-skill · 231 tokens

amazon-a-plus-content

Amazon A+ Content strategy and creation. Module layouts, persuasive copy, comparison charts, image briefs, and conversion optimization. Use when the user asks about A+ Content, Enhanced Brand Content, product storytelling, or Amazon listing enhancement.

nexscope-ai/Amazon-Skills · 51 tokens

amazon-advertising-strategy

Comprehensive Amazon advertising strategy and campaign optimization. Sponsored Products, Sponsored Brands, Sponsored Display campaign management, budget allocation, ACoS optimization, and performance tracking. Use when the user asks about Amazon PPC, advertising strategy, campaign optimization, or Amazon ads…

nexscope-ai/Amazon-Skills · 59 tokens

amazon-backend-keywords

Amazon backend search term optimization and strategy. 250-byte limit management, keyword deduplication, prioritization frameworks, and search visibility optimization. Use when the user asks about backend keywords, search terms, Amazon SEO, or keyword optimization.

nexscope-ai/Amazon-Skills · 53 tokens

amazon-display-ads

Amazon Sponsored Display campaign strategy and optimization. Audience targeting, retargeting campaigns, creative optimization, and performance management. Use when the user asks about Amazon display ads, audience targeting, retargeting, or Sponsored Display campaigns.

nexscope-ai/Amazon-Skills · 50 tokens

amazon-keyword-tracker

Amazon keyword position monitoring and SERP analysis. Real-time position tracking, competitor movement alerts, search result changes, and keyword performance optimization. Use when the user asks about keyword monitoring, SERP tracking, position alerts, or search performance analysis.

nexscope-ai/Amazon-Skills · 54 tokens