agentleFS
ITch8ITch8/customs-data-skills/skills/prospect-qualification/SKILL.md

prospect-qualification

Skill9 starsChanged 24 days agoMITView on GitHub

Qualify a prospect with explainable fit dimensions, evidence and confidence.

The file

Files
SKILL.md

Prospect Qualification

Input: ProspectCandidate, ICP, product knowledge and research evidence.

Output: qualification verdict, score, fit dimensions, reasons, positive/negative signals, evidence, missing information and confidence.

Possible verdicts: qualified, possible, needs_research, rejected, existing_relationship, suppressed.

A score without reasons or evidence is invalid. Qualification never grants send permission.

海关数据线索的评分口径

线索来自海关/提单数据时,本技能按customs-lead-sop 的评分卡执行。 评分卡全文见依赖技能 customs-lead-sop 的 references/scorecard.md。

五个维度,满分 100:

维度满分依据
Recency 采购新鲜度20近 3 个月 / 6 个月 / 12 个月 / 更久
Frequency 采购频次20近 12 个月出货次数
Product fit 产品匹配20官网/目录交叉验证,不是舱单关键词命中
Supplier structure 供应商结构20多供应商、近 6 个月新供应商加分
Company fit 公司匹配20渠道、规模、认证、价格带

分层:≥80 一对一 · 60–79 常规跟进 · 40–59 培育 · <40 降优先级。

三条不可绕过的约束

这些来自依赖技能 customs-pitfalls,与上面那句"评分不授予发送许可"是同一条链上的护栏:

  1. 无证据的维度必须留空(null),不得填 0。 null 表示"没查",0 表示"查了确实是零"。把没证据写成 0 分, 等于用假数据把一个本该 needs_research 的线索压成低分淘汰。
  2. 二次线索总分上限 59,且必须标 evidence_thin。 展会名录、协会会员、LinkedIn、新闻都属于二次线索—— 它们证明公司存在,不证明它买过。分数再高也不该进一对一。
  3. 必须区分角色:Consignee / Notify Party 默认不是终端买家。 货代、报关行、3PL、仓库要单独打标(possible_agent_or_3pl、 possible_customs_broker);To Order、银行、遮蔽收货人 一律标 consignee_masked_or_to_order,不作为买家评分。

表述纪律

  • 「查不到公开记录」只能写成公开数据不足, 不能写成「该公司不进口」——美国公开舱单主要是海运, 空运、陆运、第三方进口、关联公司都不会出现在那里。
  • 金额÷数量是统计单位价值,只能用于趋势比较, 不是成交价或竞品报价,不得作为定价基准。
  • UN Comtrade 与各国统计没有公司名,不得从统计反推买家名单。
  • 面向客户的文案不得提及海关数据、提单或任何数据平台, 必须把关务字段转译成产品/供应链观察。

输出要求

每个候选必须附带:source(工具名或 user_export)、evidence_window 时间窗、 各维度分值与理由、正负信号、置信度(high / medium / thin)、flags 列表。 缺任一项即本次评分无效。

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.