Agent skill

Customer 360

by zj-unicom-ai in zj-unicom-ai/UniEmployee

客户 360 画像技能。当用户询问某个客户的综合情况、合作状态、历史消费、已购产品、联系人、在途商机、合同状态,或要求做客户盘点、拜访前背景调查时使用本技能。

MITAuto-check passedSales & Support

Install Customer 360

skills CLI
$ npx skills add zj-unicom-ai/UniEmployee --skill customer-360 -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install zj-unicom-ai/UniEmployee customer-360 --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/zj-unicom-ai/UniEmployee.git skills-src && mkdir -p .claude/skills && cp -r skills-src/backend/skills/customer-360 .claude/skills/customer-360 && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
customer-360
GitHub stars
360
Token cost
~393 tokens
SKILL.md length
87 words
Files
1
Skills in repo
22
Repo updated
First seen
Licence
MIT

At a glance

客户 360 画像技能。当用户询问某个客户的综合情况、合作状态、历史消费、已购产品、联系人、在途商机、合同状态,或要求做客户盘点、拜访前背景调查时使用本技能。

  • Works in 5 steps: 一句话结论:该客户当前合作状态与健康度 → 基本信息:客户、企业、行业、关键联系人 → 合作现状:已购产品、历史消费、在途订单 → …
  • Sales & Support work in your project
  • SKILL.md covers 触发条件, 执行步骤(按顺序执行) and 原则
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Customer 360 is an agent skill from zj-unicom-ai/UniEmployee. 客户 360 画像技能。当用户询问某个客户的综合情况、合作状态、历史消费、已购产品、联系人、在途商机、合同状态,或要求做客户盘点、拜访前背景调查时使用本技能。

Its SKILL.md is about 390 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Sales & Support. The repository describes itself as: 面向企业的数字员工构建与运行平台:把专业员工的经验、流程与判断标准,固化为可随时上岗、可配置、可审批、可观测的 AI 数字员工。 The licence is MIT.

When your agent uses it

  • Sales & Support work in your project

Example prompts

  • “/customer-360”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. 一句话结论:该客户当前合作状态与健康度
  2. 基本信息:客户、企业、行业、关键联系人
  3. 合作现状:已购产品、历史消费、在途订单
  4. 在途事项:商机(阶段 / 金额 / 最后跟进时间)、合同(到期日)、投诉工单
  5. 风险与建议动作:合同临期(≤ 30 天)、商机停滞(> 14 天未跟进)、

What it can do on your machine

Read from SKILL.md and the folder at commit c38a00a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Customer 360 loads about 393 tokens when it runs. Until then it costs about 23 tokens; SKILL.md has 87 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~23
When it runs · the whole SKILL.md, loaded when a task matches
~393

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from zj-unicom-ai/UniEmployee at commit c38a00a, republished under its MIT licence (© zj-unicom-ai). 87 words, ~393 tokens.

Download SKILL.mdSave it as .claude/skills/customer-360/SKILL.md (or your agent's skills folder).
name
customer-360
description
客户 360 画像技能。当用户询问某个客户的综合情况、合作状态、历史消费、已购产品、联系人、在途商机、合同状态,或要求做客户盘点、拜访前背景调查时使用本技能。
metadata.include_tools
ontology_customer_360

客户 360 画像

你是客户经理,回答客户综合情况必须基于真实检索结果,禁止编造或凭记忆给数。 所有结论用中文结构化输出,每一部分标注信息来源。

触发条件

  • 用户问某客户"什么情况"、"怎么样"、"盘一下"、"介绍一下"
  • 用户问某客户的合作状态、历史消费、已购产品、联系人、商机、合同
  • 用户要求做客户盘点或拜访前的客户背景调查
  • 用户问客户/联系人/合同/商机/产品之间的关系:某商机对应哪份合同、 某产品用在哪些客户、某联系人是对决策人还是技术对接人

执行步骤(按顺序执行)

步骤 1:查客户档案知识库

优先调用 kb_search 检索「客户档案」知识库:

  • 先查 客户名 + 客户档案(基本信息:企业、行业、职级、联系方式)
  • 再查 客户名 + 历史消费 + 已购产品
  • 再查 客户名 + 拜访记录(近期沟通与客户偏好)
步骤 2:查业务本体关系

用本体工具查客户的结构化关系(知识库是叙述性材料,本体是权威关系数据, 实体类型用英文代码 customer/contact/product/project/contract):

  • 先调用 ontology_customer_360(customer_name="客户名") 获取客户全景: 跟进人、联系人、项目/商机、合同、订单、产品和中文关系路径;
  • ontology_find_entities(entity_type="customer", keyword="客户名关键词") 定位客户实体
  • 对全景结果中需要追证的部分,再用 ontology_query_relations / ontology_find_paths 核验签约合同(sign)、在途项目(serve)、联系人(belongs_to)及商机对应的存量合同
  • 定位客户联系人用 entity_type="contact";沿合同继续查 include 关系可得产品清单, 沿商机查 correspond_to 可得关联存量合同
步骤 3:CRM 补充

以下情况调用 CRM 连接器补充:

  • 知识库与本体均未覆盖时:customer_profile(customer_name=客户名)
  • 涉及订单履约状态时:order_query(order_id=订单号)
步骤 4:汇总输出(结论先行)

按以下结构输出,每节标注来源(客户档案知识库 / 业务本体 / CRM):

  1. 一句话结论:该客户当前合作状态与健康度
  2. 基本信息:客户、企业、行业、关键联系人
  3. 合作现状:已购产品、历史消费、在途订单
  4. 在途事项:商机(阶段 / 金额 / 最后跟进时间)、合同(到期日)、投诉工单
  5. 风险与建议动作:合同临期(≤ 30 天)、商机停滞(> 14 天未跟进)、 投诉在途等风险逐条列出,并给出建议的下一步动作

原则

  • 任一节检索未命中时如实说明"暂无记录",不得编造
  • 金额、日期、数量必须与查询结果一致
  • 发现风险项时主动建议下一步动作(如"建议本周内安排续约沟通")
  • 需要批量扫描全量客户时,转到 renewal-scan 技能流程执行

© zj-unicom-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in backend/skills/customer-360 of zj-unicom-ai/UniEmployee.

Open the folder on GitHubat commit c38a00a

Compare with similar skills

Customer 360 next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Customer 360 compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Customer 360 this skillzj-unicom-ai/UniEmployee360—~393Automated safety check: PassMIT
Cold Outbound Optimizerericosiu/ai-marketing-skills3.6k1 repos~1.7kAutomated safety check: PassMIT
Doc Coauthoringaws-samples/sample-strands-agent-with-agentcore19540 repos~3.2kAutomated safety check: PassMIT
Amazon Buy Box Monitorbrowser-act/skills6.1k1 repos~1.6kAutomated safety check: PassMIT
Review Analysisliangdabiao/amazon-sorftime-research-MCP-skill9591 repos~2.5kAutomated safety check: PassNone
Deskcomm Extensaomelgarafael/DeskcommCRM4.5k—~2.7kAutomated safety check: PassMIT

Similar skills

  • Cold Outbound Optimizer

    ericosiu/ai-marketing-skills

    Design, analyze, and optimize cold outbound email campaigns for Instantly.

    3.6k GitHub starsUsed in 1 repo~1.7k tokens
    Sales & SupportAuto-check passed
  • Doc Coauthoring

    aws-samples/sample-strands-agent-with-agentcore

    Official

    Guide users through a structured workflow for co-authoring documentation.

    195 GitHub starsUsed in 40 repos~3.2k tokens
    Sales & SupportAuto-check passed
  • Amazon Buy Box Monitor

    browser-act/skills

    Pulls Amazon product details, competing seller prices and seller ratings for a given ASIN through the BrowserAct API, without browser automation.

    6.1k GitHub starsUsed in 1 repo~1.6k tokens
    Sales & SupportAuto-check passed
  • Review Analysis

    liangdabiao/amazon-sorftime-research-MCP-skill

    对亚马逊商品评论进行深度分析,自动识别产品痛点、分析退货原因,生成改进建议和客服回复模板。Invoke when user uses /review-analysis command with a product ASIN.

    959 GitHub starsUsed in 1 repo~2.5k tokens
    Sales & SupportAuto-check passed
  • Deskcomm Extensao

    melgarafael/DeskcommCRM

    Guia para criar uma extensão do DeskcommCRM — o pacote declarativo — em vez de abrir um PR no núcleo.

    4.5k GitHub stars~2.7k tokensUpdated today
    Sales & SupportAuto-check passed
  • Tourmind Booking

    tourmind-com/Tourmind-Booking-Skills

    MUST USE for any hotel or accommodation intent in any language, including hotel search, hotel recommendations, nearby accommodation, hostels, guesthouses, resorts, where-to-stay questions, room…

    1.8k GitHub stars~13k tokensUpdated yesterday
    Sales & SupportAuto-check passed

More from zj-unicom-ai/UniEmployee

All 22 skills in this repo
  • Enterprise Customer Visit Playbook

    zj-unicom-ai/UniEmployee

    Prepares account managers for visits to government and enterprise customers: looks up the customer file, matches products, builds a Word solution document and files visit minutes.

    360 GitHub stars~458 tokensUpdated 2 days ago
    Auto-check passed
  • Tencent ima Knowledge Base Reader

    zj-unicom-ai/UniEmployee

    Exports the article list and original article text from a Tencent ima knowledge base through a logged-in Chrome session, using browser automation.

    360 GitHub stars~1k tokensUpdated 2 days ago
    Auto-check passed
  • Business Overview Analysis

    zj-unicom-ai/UniEmployee

    Produces a full business health analysis from sales, finance, inventory and customer CSV files: core KPIs, monthly trends, drill-downs and recommendations.

    360 GitHub stars~662 tokensUpdated 2 days ago
    Auto-check passed
  • Competitor Deep-Dive Dashboard

    zj-unicom-ai/UniEmployee

    Produces a competitor benchmarking dashboard as an HTML page with an ECharts price comparison, from built-in profile cards plus fresh web research.

    360 GitHub stars~1.7k tokensUpdated 2 days ago
    Auto-check passed
  • Insurance Operations Analysis

    zj-unicom-ai/UniEmployee

    Analyzes insurance operating data such as premium, loss ratio, renewal rate and expense ratio by branch, product and channel, flags anomalies and builds an HTML dashboard.

    360 GitHub stars~646 tokensUpdated 2 days ago
    Auto-check passed
  • Market Alert Triage

    zj-unicom-ai/UniEmployee

    Assesses a reported market event such as a competitor price cut, new launch or negative press, verifies it, grades urgency from P0 to P2 and produces a short alert card.

    360 GitHub stars~778 tokensUpdated 2 days ago
    Auto-check passed

Categories

Questions about Customer 360

What does Customer 360 do?

客户 360 画像技能。当用户询问某个客户的综合情况、合作状态、历史消费、已购产品、联系人、在途商机、合同状态,或要求做客户盘点、拜访前背景调查时使用本技能。. Customer 360 is an agent skill from zj-unicom-ai/UniEmployee.

When should I use Customer 360?

Customer 360 fits situations like: sales & Support work in your project.

How do I install Customer 360 in Claude Code?

Run `npx skills add zj-unicom-ai/UniEmployee --skill customer-360 -a claude-code`. Or copy the skill folder (backend/skills/customer-360 in zj-unicom-ai/UniEmployee) into .claude/skills/customer-360 in your project. Claude Code loads it when a task matches its description.

How do I install Customer 360 in Codex?

Run `npx skills add zj-unicom-ai/UniEmployee --skill customer-360 -a codex`. Or copy the skill folder (backend/skills/customer-360 in zj-unicom-ai/UniEmployee) into .agents/skills/customer-360 in your project. Codex loads it when a task matches its description.

Can I use Customer 360 in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add zj-unicom-ai/UniEmployee --skill customer-360 -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/customer-360, .gemini/skills/customer-360, .github/skills/customer-360 and .opencode/skills/customer-360 in your project.

What does Customer 360 need to run?

SKILL.md names no scripts, command-line tools or credentials: Customer 360 is instructions for the agent only.

Does Customer 360 access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Customer 360 safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Customer 360 use?

Customer 360 is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Customer 360 use?

About 393 tokens (SKILL.md is roughly 1.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Customer 360?

Skills that share tags, products or a category with Customer 360: Cold Outbound Optimizer (ericosiu/ai-marketing-skills, 3.6k stars), Doc Coauthoring (aws-samples/sample-strands-agent-with-agentcore, 195 stars), Amazon Buy Box Monitor (browser-act/skills, 6.1k stars) and Review Analysis (liangdabiao/amazon-sorftime-research-MCP-skill, 959 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Customer 360?

zj-unicom-ai (a GitHub organization) maintains it in zj-unicom-ai/UniEmployee, which has 360 GitHub stars. The repository holds 22 skills in this directory. The repository was last updated on October 8, 2026.

Source: zj-unicom-ai/UniEmployee on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.