# enterprise-user-management-ai-system

A skill that scaffolds a user management system with Kanban boards, support tickets and AI analytics for risk, anomalies and burnout.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 367 installs · ★ 5
- Author: reason-machines
- License: LicenseRef-Unknown · policy=link-only · description only; the file stays with the author
- Source: https://github.com/reason-machines/data-skills/tree/HEAD/skills/enterprise-user-management-ai-system/SKILL.md
- Updated: 2026-10-09
- HTML: https://affpapa.org/en/nevibecode/skills/enterprise-user-management-ai-system

## What it does

The skill covers a three-part stack: a Node.js backend, a Python ML service and a React frontend. It lays out role-based access with JWT auth, tasks on a Kanban board with time tracking, ticket creation and classification, admin user operations and audit logs. The analytics side handles risk prediction, anomaly detection, burnout analysis and project delay forecasting.

You need Node.js 14+, Python 3.8+ and MongoDB, local or remote. The backend listens on `http://localhost:5000`, the ML service on `http://localhost:8000`, the frontend on `http://localhost:3000`. Each part reads its own `.env`: the backend takes `MONGODB_URI`, `JWT_SECRET`, `JWT_EXPIRE` and `ML_SERVICE_URL`; the ML service takes `MODEL_PATH` and `LOG_LEVEL`; the frontend takes `REACT_APP_API_URL` and `REACT_APP_ML_URL`. Skip the ML service and the analytics endpoints stay silent, since the backend reaches them through `ML_SERVICE_URL`.

Endpoint examples are included for registration and login, user CRUD, tasks, tickets and the four AI calls. On the frontend side there is a `useAuth` hook and a `KanbanBoard` component to start from.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/data-skills --skill enterprise-user-management-ai-system -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/enterprise-user-management-ai-system/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/enterprise-user-management-ai-system/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/data-skills --skill enterprise-user-management-ai-system -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/enterprise-user-management-ai-system/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/data-skills --skill enterprise-user-management-ai-system -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/enterprise-user-management-ai-system/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install reason-machines/data-skills enterprise-user-management-ai-system
```

2. **Manually: put the files in place**
- File: `.github/skills/enterprise-user-management-ai-system/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/data-skills --skill enterprise-user-management-ai-system -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/reason-machines/data-skills --path skills/enterprise-user-management-ai-system
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/enterprise-user-management-ai-system/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/data-skills --skill enterprise-user-management-ai-system -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/reason-machines/data-skills/tree/HEAD/skills/enterprise-user-management-ai-system/SKILL.md

## When to use it
- stand up user management with roles and JWT auth
- build a Kanban board that tracks time spent per task
- file support tickets and classify them automatically
- wire in risk prediction and anomaly detection on user behaviour
- flag burnout risk and forecast project delays

## Example prompts
- Set up enterprise user management with AI analytics and a Kanban board
- Add a risk prediction endpoint that takes task load and overdue count
- Wire the `useAuth` hook so login stores the JWT

## Similar
- [mcp-builder](https://affpapa.org/en/nevibecode/skills/mcp-builder.md) — skill · 130949 installs
- [claude-api](https://affpapa.org/en/nevibecode/skills/claude-api.md) — skill · 74198 installs
- [lark-im](https://affpapa.org/en/nevibecode/skills/lark-im.md) — skill · 472900 installs
- [lark-event](https://affpapa.org/en/nevibecode/skills/lark-event.md) — skill · 466800 installs
- [caveman-discover](https://affpapa.org/en/nevibecode/skills/caveman-discover.md) — skill · 104400 installs
- [migration](https://affpapa.org/en/nevibecode/skills/migration.md) — skill · 103900 installs

From the same set: [reason-machines/data-skills](https://affpapa.org/en/nevibecode/by/reason-machines/data-skills.md) — 62 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md