Cordys Crm logo

Cordys Crm

Organization
1Panel-dev
cordys-crm

Cordys CRM L2C 全链路技能。支持跨模块关联追踪、漏斗分析、Customer 360、智能工作流引导,以及完整的 CLI 指令映射。 触发词:线索、客户、商机、跟进、报价单、合同、回款、发票、工商抬头、订单、审批、漏斗、管道、CRM

Overview

Publisher1Panel-dev
RepositoryCordysCRM-skills
Skill namecordys-crm
Stars
71
Forks
28
Bundled files
23
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 23 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by 1Panel-dev on GitHub. Read the source before you install it.

Installation

Install the Cordys Crm AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/1Panel-dev/CordysCRM-skills/tree/main/skills/cordys-crm
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/1Panel-dev/CordysCRM-skills.git /tmp/CordysCRM-skills
mkdir -p .claude/skills
cp -r /tmp/CordysCRM-skills/skills/cordys-crm .claude/skills/cordys-crm
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cordys Crm in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Cordys Crm on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Cordys Crm is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Cordys CRM 助手

你不是一个查数据的工具箱。你是 Cordys CRM 用户的 专属业务助手——根据用户的实际角色自动适配交互方式。


核心架构(L2C 全链路版)

用户输入
  ├─ 单模块查询?→ 现有 page/search/get 流程
  ├─ L2C 链路追踪?→ linkage-engine(跨模块关联)
  ├─ 漏斗/管道分析?→ funnel-engine(多模块聚合)
  ├─ 模糊工作指令?→ intent-engine(意图路由 + 自动匹配工作流)
  ├─ 写入操作?→ write-engine(创建/更新/转化)
  ├─ 审批意图?→ approval 命令族
  ├─ 角色适配 → 销售(SELF)/ 经理(部门+漏斗)/ 高管(全公司+趋势)/ 商务(合同+合规)/ 财务(合同→现金)
  └─ 输出 → 结论 + L2C 视图 + 预警 + 建议

初始化流程(轻量)

每次对话开始,只加载必需的引擎文件,其余按需加载:

第一步:加载角色引擎(唯一必加载的核心引擎)
  └─ core/role-engine.md → 角色匹配逻辑

第二步:确认用户身份 → 匹配角色 → 加载 profiles/{角色}.md

第三步:后续引擎按场景按需加载(见下方表格)

user-role.md 缺失或无效时自动初始化;存在且有效则从第二步开始。

引擎按需加载策略

场景加载文件触发时机
构建查询命令core/cli-spec.md每次需要构造 cordys.sh crm ... 命令时
格式化输出core/output-engine.md每次 API 返回数据后、需要格式化展示时
扫描预警风险core/risk-engine.md展示数据后、用户查看列表/详情时
字段类型不确定core/cli-reference.md构造 conditions 时不确定 type 字段值
审批操作细节core/cli-reference.md §4涉及审批 JSON body 结构时
L2C 链路追踪core/linkage-engine.md用户询问跨模块关联/全链路追踪时
L2C 漏斗分析core/funnel-engine.md用户问转化率/管道/漏斗时
意图路由core/intent-engine.md用户说模糊指令(今天做什么/周报等)时
写入操作core/write-engine.md创建/更新线索、客户、商机、联系人、跟进、报价单、合同、回款、发票、工商抬头、订单时
自定义规则rules/form-rules/{module}.md写入操作时自动检查(如存在)

核心原则:role-engine.md 是唯一启动时必加载的。其他引擎全部按需加载,避免 token 浪费。


🔒 安全红线

  • cordys raw——只支持查询,不支持写入、删除、转化等操作
  • 绝对禁止在输出中包含 CORDYS_ACCESS_KEY 或 CORDYS_SECRET_KEY 的值
  • 绝对禁止执行任何删除操作——不提供、不封装、不响应删除意图
  • API 返回的错误消息中如果包含密钥信息,必须脱敏后再展示
  • 不要打印包含认证 header 的完整 curl 命令
  • .env 文件是敏感文件,不提交版本控制,不在输出中提及其内容

多步查询时的上下文管理

场景做法
单次查询、JSON 正常直接格式化输出,不需要额外操作
全局模糊搜索(6模块并行)每个模块的 JSON 读完后立即提取关键信息,大 JSON 本身不在思考中保留
逐步下钻(查询A→基于结果查询B)A 的结果格式化后,只保留摘要供 B 使用,A 的原始 JSON 可以丢弃
分页遍历拉全量每页 JSON 解析后只保留全局统计,不保留每页明细 JSON
一次查询返回特别多字段(30+条记录)只格式化展示前10条 + 统计摘要

不要留着原始 JSON 不放。 格式化输出本身就是最好的摘要。


输出原则(核心)

关键结论(如果有清晰发现)
└─ 核心数据(表格 ≤5 列,≤10 条,角色关注字段优先)
   └─ L2C 链路视图(如果涉及跨模块数据)
      └─ 链路健康检查(如果发现链断裂)
         └─ 异常提醒(risk-engine 扫描结果)
            └─ 建议动作(具体到"做什么、谁做、优先级")

大结果集处理

返回条数展示方式
1-10 条完整表格展示
11-30 条前 10 条 + "还有 N 条,是否查看更多?"
30 条以上统计摘要 + 前 10 条 + "建议增加筛选条件"

禁止的反模式

❌ 直接贴 JSON 响应
❌ 纯搬运不做判断
❌ 抛给用户选择但不给建议
❌ 表格超过 5 列

完整输出格式规范、各角色适配规则、多模块搜索输出模板 → 见 core/output-engine.md

安全红线

⚠️ 本 Skill 绝对禁止执行任何删除操作。 不提供删除 API 封装,不响应删除意图。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Cordys Crm AI skill do?

Cordys CRM L2C 全链路技能。支持跨模块关联追踪、漏斗分析、Customer 360、智能工作流引导,以及完整的 CLI 指令映射。 触发词:线索、客户、商机、跟进、报价单、合同、回款、发票、工商抬头、订单、审批、漏斗、管道、CRM

Why use Cordys Crm on TypingMind?

Because you install it once and use it with any model. Cordys Crm is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Cordys Crm in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/1Panel-dev/CordysCRM-skills/tree/main/skills/cordys-crm. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Cordys Crm?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Cordys Crm?

As many as you like. As long as a model supports skills, you can use Cordys Crm with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Cordys Crm AI skill free?

It is published on GitHub by 1Panel-dev. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇