# llamaguard

> Meta's 7-8B specialized moderation model for LLM input/output filtering.

Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.

- Type: Skill
- Made by: Orchestra-Research
- Category: AI & agents
- Formats: Skills
- Version: 69a6b24
- Source: https://github.com/orchestra-research/ai-research-skills/tree/HEAD/07-safety-alignment/llamaguard
- Page: https://pluginboard.ai/skills/llamaguard-orchestra-research

## Works with

- ChatGPT
- Claude
- Gemini
- GitHub Copilot
- Cursor
- Claude Code
- Codex
- Antigravity
- Gemini CLI
- Replit
- OpenClaw
- OpenCode
- Hermes Agent

## Install

### ChatGPT

In ChatGPT: Download the llamaguard folder and zip it, then Plugins → Skills → Create → Upload from your computer. Business and Enterprise plans.

View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/07-safety-alignment/llamaguard

### Claude

In Claude (web or desktop): Download the llamaguard folder and zip the folder itself, then upload it in Customize → Skills.

View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/07-safety-alignment/llamaguard

### Gemini

In Gemini: Download the llamaguard folder, then at gemini.google.com click Customize → Skills → Create → Upload and pick the folder (or a .zip of it).

View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/07-safety-alignment/llamaguard

### GitHub Copilot

Run in your terminal:

```shell
npx -y degit Orchestra-Research/AI-Research-SKILLs/07-safety-alignment/llamaguard ~/.copilot/skills/llamaguard
```

View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/07-safety-alignment/llamaguard

### Cursor

Run in your terminal:

```shell
npx -y degit Orchestra-Research/AI-Research-SKILLs/07-safety-alignment/llamaguard ~/.cursor/skills/llamaguard
```

View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/07-safety-alignment/llamaguard

### Claude Code

Run in your terminal:

```shell
npx -y degit Orchestra-Research/AI-Research-SKILLs/07-safety-alignment/llamaguard ~/.claude/skills/llamaguard
```

View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/07-safety-alignment/llamaguard

Or all of AI Research Skills (Orchestra), in Claude Code:

```text
/plugin marketplace add Orchestra-Research/AI-Research-SKILLs
/plugin install rag@ai-research-skills
```

### Codex

Run in your terminal:

```shell
npx -y degit Orchestra-Research/AI-Research-SKILLs/07-safety-alignment/llamaguard ~/.agents/skills/llamaguard
```

View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/07-safety-alignment/llamaguard

### Antigravity

In Antigravity: Copy the llamaguard folder into ~/.gemini/config/skills (Antigravity app and IDE) or ~/.gemini/antigravity-cli/skills (Antigravity CLI).

View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/07-safety-alignment/llamaguard

### Gemini CLI

Run in your terminal:

```shell
npx -y degit Orchestra-Research/AI-Research-SKILLs/07-safety-alignment/llamaguard ~/.gemini/skills/llamaguard
```

View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/07-safety-alignment/llamaguard

### Replit

Run in your terminal:

```shell
npx -y degit Orchestra-Research/AI-Research-SKILLs/07-safety-alignment/llamaguard .agents/skills/llamaguard
```

View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/07-safety-alignment/llamaguard

### OpenClaw

Run in your terminal:

```shell
npx -y degit Orchestra-Research/AI-Research-SKILLs/07-safety-alignment/llamaguard ~/.openclaw/skills/llamaguard
```

View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/07-safety-alignment/llamaguard

### OpenCode

Run in your terminal:

```shell
npx -y degit Orchestra-Research/AI-Research-SKILLs/07-safety-alignment/llamaguard ~/.config/opencode/skills/llamaguard
```

View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/07-safety-alignment/llamaguard

### Hermes Agent

Run in your terminal:

```shell
npx -y degit Orchestra-Research/AI-Research-SKILLs/07-safety-alignment/llamaguard ~/.hermes/skills/llamaguard
```

View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/07-safety-alignment/llamaguard

---
From Pluginboard (https://pluginboard.ai).