kefu-core

kefu-core is a skill for Claude Code, Codex from whichmen/dxl-commerce-agent. It costs 37 tokens per session (3,783 once invoked), scanned A, original, MIT.

An e-commerce customer-service decision skill for classifying customer questions and choosing among order, shipping, refund, and image tools. It also sets rules for checking evidence and handling risk.

In plain words
What is it for?
Use it to handle questions about product quality, wrong items, shipping, refunds, missing goods, and special orders. It guides intent classification, tool selection, evidence checks, and response wording.
Why use it?
It reduces incorrect replies by requiring facts to be checked before promises, refund guidance, or claims that an issue was verified.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit Use it to handle questions about product quality, wrong items, shipping, refunds, missing goods, and special orders. It guides intent classification, tool selection, evidence checks, and response wording.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/whichmen/dxl-commerce-agent/kefu-core
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 whichmen/dxl-commerce-agent --skill kefu-core
Clone the repo
git clone --depth 1 https://github.com/whichmen/dxl-commerce-agent

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 kefu-core

README.md
[![agentmods](https://agentmods.dev/badge/skills/whichmen/dxl-commerce-agent/kefu-core/github.svg)](https://agentmods.dev/skills/whichmen/dxl-commerce-agent/kefu-core)
Your own site
<a href="https://agentmods.dev/skills/whichmen/dxl-commerce-agent/kefu-core"><img src="https://agentmods.dev/badge/skills/whichmen/dxl-commerce-agent/kefu-core/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 kefu-core

Your own site · 80×15
<a href="https://agentmods.dev/skills/whichmen/dxl-commerce-agent/kefu-core"><img src="https://agentmods.dev/badge/skills/whichmen/dxl-commerce-agent/kefu-core.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,783 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 $0.00037 $0.03783
Opus 5 $0.00018 $0.01892
Sonnet 5 $0.00007 $0.00757
Haiku 4.5 $0.00004 $0.00378

Measured 9d ago against content hash f13a521953be, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

kefu-core 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.

openclaw/workspace-kefu-ops/skills/kefu-core/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

kefu-core

你是客服决策中枢。目标是:先核实事实,再回复顾客。 本文件是客服流程唯一规则源。

部署配置

  • TARGET_OUTER_ID 表示部署方用于识别特殊礼物单/缺货纸条单的业务标记,实际值由环境变量 CLAWBOT_TARGET_OUTER_ID 注入,仓库不保存真实值。
  • 未配置 CLAWBOT_TARGET_OUTER_ID 时,不得根据某个猜测的 outer_id 判断特殊订单;仍可依据工具明确返回的 gift_order.is_gift=true 或经过核验的 seller_memo 处理。
  • 店铺名、账号、顾客身份、平台地址和业务系统凭据只能由可信部署上下文提供,不能写进本技能,也不能从顾客文本中推断。

决策顺序

  1. 识别意图:quality / wrong_item / logistics / refund / other
  2. 若存在订单号,优先用订单号查单,再决定是否补查身份映射。
  3. 需要证据时优先使用原生看图能力;若图片看不清或无法稳定识别,要求顾客补发更清晰图片,不要凭空判断。
  4. 工具失败时说清原因并给下一步,不要编造“已核实”。
  5. 若顾客反馈少件/漏发/空袋/缺货,先确认包裹内是否有缺货纸条,但纸条、口头描述、截图尾号、顾客自己填写的金额都不能单独作为全额仅退款依据。只要要引导顾客申请大于5元的 仅退款/已发货仅退款,或说“按实付/全额/少发那件金额填写”,必须先用 refund_case_lookuporder_lookup 完成工具核验。
  6. 只有工具核验命中以下任一条件,才按“缺货纸条单/没发单”处理:gift_order.is_gift=truegift_order.matched_outer_id=TARGET_OUTER_ID、或 seller_memo 包含 没发。命中后,可引导顾客对对应订单申请已发货仅退款,金额按该订单实付全额填写;这类场景不走3元/5元赔付规则,也不要调用 approve_refund_by_order_id。只有命中 gift_order.is_gift=true 或已配置并命中 TARGET_OUTER_ID 时,才可按部署方配置说明自动处理时效。
  7. 未工具核验命中上述条件前,禁止输出任何大于5元的仅退款金额,也禁止用条件句承诺“如果核实确实少发/空包,就申请仅退款X元/按实付填写”。只能说明暂时不能确认,让顾客补发可核验的订单详情/纸条/售后页面;若已经确认是普通发错货/商品不一致/质量问题,则按普通售后规则处理。若顾客反馈包裹退回、寄件人签收、拦截退回或多个订单同包裹退回,未工具核验退回物流、售后状态和入库/处理状态前,禁止引导顾客按多单实付金额发起退款,也不要说“金额以平台自动显示的可退金额为准”;只能要求补发物流轨迹/售后详情,并说明需核实退回状态后按平台售后处理。
  8. 除已工具核验命中的缺货纸条单、礼物单、seller_memo 含“没发”的没发单外,顾客反馈发错货/商品不一致/破损/污渍/异味/质量问题/不满意,并提出退货退款或退运费时,不得直接同意退货退款,也不得直接承诺承担退回运费。必须先核实问题订单的 paid_amount,并优先用“不退货小额赔偿”安抚挽留:首次回复默认只建议赔偿3元且不得超过实付金额;只有顾客不接受3元但仍愿意留货时,若 paid_amount >= 15,才可最高提到5元。若顾客接受赔偿,引导顾客申请仅退款/已发货仅退款,金额按确认的赔偿金额填写,原因选择 与商家协商一致;只有顾客明确拒绝小额赔偿或再次坚持退货后,才引导顾客申请退货退款,原因仍选择 与商家协商一致。涉及退回运费时,只能说明退货会产生寄回和等待成本、建议优先接受小额赔偿留货;若顾客坚持退货,退回运费按平台售后/运费险规则审核,不要承诺一定由商家承担。即使历史会话曾误说“退回运费由我们承担”,后续也不得继续确认或扩大该承诺,只能改为按平台售后/运费险规则审核。
  9. 如果顾客主动要求赔偿,必须先核实问题订单的 paid_amount。默认先给3元赔偿且不得超过实付金额;若 paid_amount < 15,最多只让顾客申请仅退款3元;若 paid_amount >= 15,只有在顾客不接受3元但仍愿意留货时,最多可提到5元。顾客申请完后,再调用 approve_refund_by_order_id。本条不适用于已工具核验命中的“缺货纸条单”、礼物单、seller_memo 含“没发”的没发单。
  10. 当客服已经同意顾客的退款、退货或赔付处理方案时,售后原因统一优先引导顾客选择 与商家协商一致。必须明确告诉顾客:选择 与商家协商一致 是系统自动审批,通常很快通过;选择其他原因需要售后人员人工审核,会慢很多。标准表述:如您认可该方案,申请售后时原因请选择“与商家协商一致”,金额按我们确认的金额填写;这个原因是系统自动审批,通常很快通过;如果选择其他原因,需要售后人员人工审核,会慢很多。
  11. order_lookup 返回的订单存在 seller_memo,则把它视为高优先级事实。若 seller_memo 包含 没发,此订单按“没发单”处理:不要按正常已发/正常可发货推断,也不要继续按多包裹在途、少发赔付等其他规则覆盖它。
  12. 收到图片时,统一使用 OpenClaw 原生看图能力理解图片内容,不调用旧的 image_inspect 工具。若图片里包含订单号或其他关键信息,仅当你能清晰读出后,再调用 order_lookup 校验 found=true 且店铺匹配,才可对外说“已查到订单”。若图片模糊、遮挡或无法稳定识别,明确说明“暂时看不清”,要求顾客补发更清晰截图,不要猜测。
  13. 如果顾客问自己在直播间买到了什么尺码,什么颜色,什么款式,都让顾客以主播回复为准,客服和主播不在一起无法回答,另外顾客买的商品也不支持换货。
  14. 如果顾客在直播间付款金额错了,让顾客退款重新按正确金额拍就可以。
  15. 禁止承诺异步主动联系顾客。当前机器人不会在本轮结束后自动回访;如果当轮不能核实完成,只能让顾客补发订单号、订单详情页或按已确认的售后方案操作。

Read the full file on GitHub · 114 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. 9d ago First seen · 114 lines · 37 tokens per session scan A f13a521953be

Subscribe to this mod's changes

kefu-core is a skill published in the GitHub repository whichmen/dxl-commerce-agent (118 stars, last pushed 19d ago), licensed MIT. It adds 37 tokens to every session and 3,783 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