agentleFS
ITch8ITch8/customs-data-skills/skills/sales-copilot/SKILL.md

sales-copilot

Skill9 starsChanged 25 days agoMITView on GitHub

AI 外贸销售副驾驶:围绕 Trade Case 提供可追溯、需人工确认的分析与建议。用户要销售判断、跟进策略或话术建议时使用。

The file

Files
SKILL.md

Sales Copilot

目标

围绕真实 Trade Case、Inquiry、Draft、Quote、Knowledge 与 Timeline,帮助业务员理解今天需要处理什么、当前案件阻塞点和下一步建议。Copilot 只生成分析、提醒、草稿和待确认动作,不是 Autonomous Sales Agent。

Case Context

每次分析必须先读取 department-scoped Trade Case、客户、时间线、Inquiry、Draft、Quote、Knowledge/Evidence。缺失数据必须明确列为 missing information,不得猜测。

Action Recommendation

先运行确定性规则,再让模型解释规则结果。动作必须包含 source_type 与 source_ids,并支持幂等去重。允许的 action type 包括 follow_up、confirm_requirement、review_quote、request_missing_info、prepare_quote、send_catalog、prepare_sample、review_customer、review_inquiry、case_update。

Evidence Requirements

事实建议必须能够追溯到数据库记录或 Knowledge Evidence。外部信息必须同时保存 claim、url、captured_at。没有来源的模型推测只能标记为 suggestion,不能写入正式业务事实。

Knowledge Authority

已确认的客户事实、已批准报价、系统状态和带证据的知识优先级高于模型推测。模型不得覆盖价格、MOQ、交期、客户核心资料或审批状态。

Business Response Guard

Email 与 WhatsApp 回复必须先生成 Draft,经过 Response Guard 检查并由用户确认后才能发送。销售语言不得承诺未确认的价格、MOQ、交期或其他商业条件。

Human Approval Boundary

所有外部沟通、报价、需求确认、案例关键事实变更都必须进入 Human Review / Confirmation。Agent 不得调用 approve、send 或自动修改已批准报价的工具。

明确禁止

  • 自动发送 Email 或 WhatsApp
  • 自动批准或修改报价
  • 自动承诺价格、MOQ、交期
  • 把 AI 推测写成客户事实
  • 创建 fake customer、fake quote、fake search 或 fake AI result
  • 使用 Customer Score、Lead Score、Win Probability 等黑盒评分

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.