enterprise-sales SKILL.md skillA
enterprise-sales from zj-unicom-ai/uniemployee is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add zj-unicom-ai/uniemployee/enterprise-sales@git:20260912.5351272Pins git:20260912.5351272 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- zj-unicom-ai/uniemployee
- Path
backend/skills/enterprise-sales/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260912.5351272, committed Sep 12, 2026
- First version recorded
- Aug 15, 2026
- Size
- 3,732 bytes
- Repository stars
- 758
- License
- MIT
自研产品客户拜访技能。当客户经理需要拜访政企客户、准备解决方案、生成方案文档、或整理拜访纪要时使用本技能。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 政企客户拜访规程
## 触发条件
- 用户说"拜访客户"、"准备方案"、"出方案"、"生成文档"、"做方案"
- 用户提到政企客户名称（如"张总"、"应急局"、"教育局"等）
- 用户要求生成或导出 Word 文档
- 用户口述拜访情况，要求整理拜访纪要、记录客户反馈
## 执行步骤（按顺序，不可跳过）
### 步骤 1：查客户档案
优先调用 `kb_search` 检索「客户档案」知识库：
- 先查 `客户名 + 客户档案`
- 再查 `客户名 + 历史消费 + 已购产品`
- 客户所属企业、行业、职级、拜访记录也在该知识库中检索
若知识库未命中，再调用 CRM 的 `customer_profile` 查询客户档案；
仍未命中则告知用户补充客户信息。
### 步骤 2：分析客户行业
根据客户所属行业（如数字政府、应急消防、教育、工业互联网等），判断产品匹配方向：
- 通信需求 → 企业通信云服务（云录音/云转写/云名片等）
- 组网安全需求 → 云安全（组网专线/安全专线）
- 消防应急需求 → AI 视频分析（烟火识别）
- 园区/社区管理需求 → 智慧园区
- AI大模型/智能化需求 → 企业大模型应用平台
- 不确定时调 kb_search 检索产品目录
### 步骤 3：检索产品方案
调 `kb_search` 检索该行业相关的产品资料、解决方案和案例：
- 先查 `产品名 + 产品介绍`
- 再查 `行业名 + 行业方案 + 案例`
- 最后查 `产品名 + 竞品对比`
### 步骤 4：生成方案文档
生成 Word 文档的流程（按顺序执行）：
1. **读取脚本文件**：先执行 `read_file("/skills/enterprise-sales/scripts/gen_solution.js")` 查看生成脚本的参数格式
2. **准备参数**：把产品清单组装为 JSON 格式，格式为 `[{"name":"产品名","qty":"数量","price":"单价","subtotal":"小计"},...]`
3. **执行生成命令**：用 `execute` 运行 node 脚本
```
execute("node backend/skills/enterprise-sales/scripts/gen_solution.js workspace/data/解决方案_客户名.docx "客户名" "企业名" "需求分析" '[{"name":"产品A","qty":"1","price":"100","subtotal":"100"}]' "100.00")
```
4. **确认结果**：脚本输出"文档已生成：xxx"即表示成功，告知用户文档路径
生成的文档包含：
1. 客户名称、企业
…Read the whole file at its exact version.
How to install
mdr add zj-unicom-ai/uniemployee/enterprise-sales@sha256:eaaf3ac4f7edc3ceThe line at the top of this page pins the label git:20260912.5351272, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_w7kxrjtjrygxhnx6)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Aug 15, 2026 and Sep 12, 2026, about one every 28 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260912.5351272 latest | 2026-09-12 | 5351272 | 3,732 B | A | view · diff |
| git:20260815.4388611 | 2026-08-15 | 4388611 | 2,827 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3732 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
zj-unicom-ai/uniemployee · 758 stars · license MIT · pushed 2026-10-29 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_w7kxrjtjrygxhnx6 GET https://markdownregistry.com/api/v1/resolve?ref=zj-unicom-ai/uniemployee/enterprise-sales GET https://markdownregistry.com/api/v1/blob/eaaf3ac4f7edc3ce569e1aa2389102355fbafadb9a6e8f3b71d9965971a25ae1
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.