# Fabric — AI Automation Patterns & Prompt Library

> Curated collection of 100+ reusable AI prompt patterns for summarizing, extracting wisdom, writing, and coding. Run any pattern from CLI with one command. 30,000+ GitHub stars.

## Install

Paste the prompt below into your AI tool:

## Quick Use

1. Install: `go install github.com/danielmiessler/fabric@latest`
2. Setup: `fabric --setup` (configure your LLM API key)
3. Run any pattern:

```bash
# Extract insights from a YouTube video
yt --transcript https://youtube.com/watch?v=abc | fabric --pattern extract_wisdom

# Summarize an article
cat article.txt | fabric --pattern summarize

# Improve code quality
cat code.py | fabric --pattern improve_code
```

---

## Intro

Fabric is an open-source framework with 100+ curated AI prompt patterns that turn complex AI tasks into simple one-line CLI commands, with 30,000+ GitHub stars. Each pattern is a battle-tested system prompt for tasks like extracting key insights, summarizing articles, improving code, and analyzing security threats. Best for power users who want repeatable, high-quality AI outputs without writing prompts from scratch. Works with: OpenAI, Anthropic, Ollama, any OpenAI-compatible API. Setup time: under 5 minutes.

---

## Popular Patterns

### `extract_wisdom`
The signature pattern — extracts key ideas, insights, quotes, and recommendations:
```bash
cat transcript.txt | fabric --pattern extract_wisdom
```

### `summarize`
Creates a concise summary with key points:
```bash
cat article.md | fabric --pattern summarize
```

### `improve_code`
Reviews and improves code quality:
```bash
cat main.py | fabric --pattern improve_code
```

### `create_keynote`
Turns content into presentation slides:
```bash
cat research.md | fabric --pattern create_keynote
```

### `analyze_threat`
Security threat analysis from vulnerability reports:
```bash
cat cve_report.txt | fabric --pattern analyze_threat
```

### `write_essay`
Generates well-structured essays on any topic:
```bash
echo "The future of AI agents" | fabric --pattern write_essay
```

### Building Custom Patterns

Create your own in `~/.config/fabric/patterns/my_pattern/system.md`:

```markdown
# IDENTITY and PURPOSE
You are an expert at [your specialty].

# STEPS
1. Read the input carefully
2. [Your specific instructions]

# OUTPUT
- [Expected format]
```

Then: `cat input.txt | fabric --pattern my_pattern`

### Key Stats
- 30,000+ GitHub stars
- 100+ built-in patterns
- 500+ community contributors
- Supports 10+ LLM providers
- Written in Go — fast and portable

### FAQ

**Q: What is Fabric?**
A: Fabric is a CLI framework with 100+ curated AI prompt patterns that turn complex tasks like summarization, analysis, and code improvement into simple one-line commands.

**Q: Is Fabric free?**
A: Yes, fully open-source under MIT license. You need your own LLM API key.

**Q: Can I use Fabric with local models?**
A: Yes, Fabric supports Ollama and any OpenAI-compatible local inference server.

---

## Source & Thanks

> Created by [Daniel Miessler](https://github.com/danielmiessler). Licensed under MIT.
>
> [fabric](https://github.com/danielmiessler/fabric) — ⭐ 30,000+

Thanks to Daniel Miessler for making AI prompt engineering accessible through reusable patterns.

---

<!-- ZH -->

## 快速使用

1. 安装: `go install github.com/danielmiessler/fabric@latest`
2. 设置: `fabric --setup`（配置 LLM API 密钥）
3. 运行任意模式:

```bash
# 提取视频精华
yt --transcript https://youtube.com/watch?v=abc | fabric --pattern extract_wisdom

# 总结文章
cat article.txt | fabric --pattern summarize
```

---

## 简介

Fabric 是一个拥有 100+ 精选 AI 提示词模式的开源框架，GitHub 30,000+ stars。每个模式都是经过实战验证的系统提示词，覆盖提取洞察、总结文章、改进代码等任务。适合希望获得高质量 AI 输出而无需从头写提示词的高级用户。支持 OpenAI、Anthropic、Ollama 等。

---

## 来源与感谢

> Created by [Daniel Miessler](https://github.com/danielmiessler). Licensed under MIT.
>
> [fabric](https://github.com/danielmiessler/fabric) — ⭐ 30,000+

---
Source: https://tokrepo.com/en/workflows/23b1fdf9-e297-41ac-9cc5-93ebb51b3aa4
Author: Prompt Lab