# mm2-analytics-roblox-toolkit

A skill that lets your coding agent run the MM2 Analytics dashboard: track knife skins and gamepasses, review match stats, export reports.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 2300 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/mm2-analytics-roblox-toolkit/SKILL.md
- Updated: 2026-10-09
- HTML: https://affpapa.org/en/nevibecode/skills/mm2-analytics-roblox-toolkit

## What it does

The skill wires an agent into the MM2 Analytics dashboard, a toolkit for Roblox Murder Mystery 2. It keeps tabs on your knife skin collection and gamepasses, flags duplicates, and reports how much of a set you still need. Match statistics cover win/loss ratios and per-role performance, and everything can go out as CSV or JSON.

Under the hood there are Python modules `InventoryManager` and `AnalyticsEngine`, a `main.py` CLI with `analytics`, `inventory` and `strategy` modes, and profile files at `config/profiles.yaml`. Python 3.8+ with `pandas`, `numpy`, `matplotlib`, `pyyaml` and `requests` is required, plus Node.js 18+ for the web dashboard. OpenAI or Claude API keys matter only for the AI features; plain tracking and exports run without them.

Profiles carry the role you play, the refresh rate and inventory filters by rarity. Live tracking is a `--live` flag with an interval in seconds, and with `ENABLE_LIVE_TRACKING` off the agent reads local data only.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/data-skills --skill mm2-analytics-roblox-toolkit -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/mm2-analytics-roblox-toolkit/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/mm2-analytics-roblox-toolkit/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/data-skills --skill mm2-analytics-roblox-toolkit -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/mm2-analytics-roblox-toolkit/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/data-skills --skill mm2-analytics-roblox-toolkit -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/mm2-analytics-roblox-toolkit/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install reason-machines/data-skills mm2-analytics-roblox-toolkit
```

2. **Manually: put the files in place**
- File: `.github/skills/mm2-analytics-roblox-toolkit/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/data-skills --skill mm2-analytics-roblox-toolkit -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/reason-machines/data-skills --path skills/mm2-analytics-roblox-toolkit
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/mm2-analytics-roblox-toolkit/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/data-skills --skill mm2-analytics-roblox-toolkit -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/mm2-analytics-roblox-toolkit/SKILL.md

## When to use it
- pull match statistics into one report
- spot duplicate knives in a collection
- break down win rate by sheriff and innocent roles
- export metrics to CSV for outside analysis
- check how many items are missing from a set

## Example prompts
- Show me the stats for `default_profile` over the last 30 days
- Find duplicate knives and write the report to `duplicates_report.json`
- Compare `aggressive_sheriff` and `passive_innocent` by win rate

## Similar
- [roblox-analytics](https://affpapa.org/en/nevibecode/skills/roblox-analytics.md) — skill · 1800 installs
- [roblox-growth-design](https://affpapa.org/en/nevibecode/skills/roblox-growth-design.md) — skill · 1600 installs
- [roblox-datastores](https://affpapa.org/en/nevibecode/skills/roblox-datastores.md) — skill · 5900 installs
- [google-analytics-data-api-basics](https://affpapa.org/en/nevibecode/skills/google-analytics-data-api-basics.md) — skill · 7364 installs
- [roblox-luau](https://affpapa.org/en/nevibecode/skills/roblox-luau.md) — skill · 6400 installs
- [campaign-analytics](https://affpapa.org/en/nevibecode/skills/campaign-analytics.md) — skill · 793 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