Fabric：用可复用提示词处理文本。把转写稿交给 summarize 模板，可整理成摘要、重点和启发，适合做学习笔记。
起步：fabric --setup 接好模型，再选 summarize 模板。
门槛：CLI 需配置模型服务，云端调用可能计费。
文档核验，未实测。
danielmiessler/Fabric
6 views
2) Fabric: linha de comando com mais de 200 prompts prontos. Com o yt-dlp instalado:
fabric -y "link do vídeo" -p create_video_chapters
puxa a transcrição do YouTube e devolve capítulos com tempo. Roda com Ollama ou com a API que você já usa.
danielmiessler/Fabric
8 views
每次让 AI 总结文章，都要重新写提示词？🧠
Fabric 收集可复用的 AI 提示模式，可在终端套用到文本任务。读论文、整理视频笔记都能试。⚙️
danielmiessler/fabric
#PromptEngineering #浇朋友 #蓝朋友 #互关 #fo
2 likes · 73 views
Fabric: An open-source framework for augmenting humans using AI (44k stars)
What it does
All text below is quoted directly from the project README.
>Fabric is an open-source framework for augmenting humans using AI. It provides a modular system for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere.
Too many prompts:
- Extracting the most interesting parts of YouTube videos and podcasts
- Writing an essay in your own voice with just an idea as an input
- Summarizing opaque academic papers
- Creating perfectly matched AI art prompts for a piece of writing
- Rating the quality of content to see if you want to read/watch the whole thing
- Getting summaries of long, boring content
- Explaining code to you
- Turning bad documentation into usable documentation
>Unix/Linux/macOS: curl -fsSL https://raw.githubusercontent.com/danielmiessler/fabric/main/scripts/installer/install.sh | bash
Repository
danielmiessler/Fabric
Repository stats
|Metric|Value|
|:-|:-|
|Stars|44,291|
|Forks|4,303|
|Last release|v1.4.523 (2026-10-16)|
|Languages|Go 74.7%, Svelte 8.8%, TypeScript 5.6%|
|Contributors|257|
|AI contributor accounts (Claude / Codex / Cursor / Copilot)|claude: 68|
|AI co-authored commits|Claude: 76, Copilot: 2|
Main contributor
|Field|Value|
|:-|:-|
|Name|Daniel Miessler|
|GitHub|@danielmiessler|
|Commits to this repo|940 (top contributor)|
|Bio|Helping people and companies transition from their Current to Ideal State.|
|Company / Location|Unsupervised Learning / San Francisco Bay Area|
|Website|danielmiessler.com|
|X / Twitter|@danielmiessler|
|Followers|17113|
|Public repos|81|
|On GitHub since|2009-01-31|
------------------------------------------------------------------------------------------------
Discover the best GitHub repos without the endless scrolling.
Get top repos organized by category (AI, DevOps, Databases & more), plus key takeaways from developers' most useful comments - all in one free, twice-weekly newsletter.
👉 Get the best repos & community insights - Free
2 points
1/3
每次读文章都重写“帮我总结”，可以看看 Fabric。它把总结、分析观点、解释代码等任务整理成可复用的提示词，叫 Patterns。可以先从一个经常重复的任务入手。
danielmiessler/fabric
6 views
2/3
最轻的上手方式：打开 data/patterns，找到 summarize，读里面的提示词，再复制到已有的 AI 工具，附上文章正文。可以加上“用中文回答”等要求。不安装命令行也能使用这部分资源。
github.com/danielmiessler/fabric/tree/main/data/p…
8 views
Is prompt engineering still a thing?
I recently stumbled over a project called fabric (danielmiessler/fabric) which is essentially a harness for any AI model API which can store your favorite prompts and pipe your text through them. For example you could have a prompt designed to correct your writing, pipe a text through it and receive an AI grading on it.
I tested it a bit and I did not really feel too much difference to using Claudes normal chat.
This made me wonder if prompt engineering is still necessary or this is unnecessary syntactic sugar that get's handled by anthropics pre-processing anyways.
19 comments
Mentions
Fabric：用可复用提示词处理文本。把转写稿交给 summarize 模板，可整理成摘要、重点和启发，适合做学习笔记。 起步：fabric --setup 接好模型，再选 summarize 模板。 门槛：CLI 需配置模型服务，云端调用可能计费。 文档核验，未实测。 danielmiessler/Fabric
2) Fabric: linha de comando com mais de 200 prompts prontos. Com o yt-dlp instalado: fabric -y "link do vídeo" -p create_video_chapters puxa a transcrição do YouTube e devolve capítulos com tempo. Roda com Ollama ou com a API que você já usa. danielmiessler/Fabric
每次让 AI 总结文章，都要重新写提示词？🧠 Fabric 收集可复用的 AI 提示模式，可在终端套用到文本任务。读论文、整理视频笔记都能试。⚙️ danielmiessler/fabric #PromptEngineering #浇朋友 #蓝朋友 #互关 #fo
Fabric: An open-source framework for augmenting humans using AI (44k stars) What it does All text below is quoted directly from the project README. >Fabric is an open-source framework for augmenting humans using AI. It provides a modular system for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere. Too many prompts: - Extracting the most interesting parts of YouTube videos and podcasts - Writing an essay in your own voice with just an idea as an input - Summarizing opaque academic papers - Creating perfectly matched AI art prompts for a piece of writing - Rating the quality of content to see if you want to read/watch the whole thing - Getting summaries of long, boring content - Explaining code to you - Turning bad documentation into usable documentation >Unix/Linux/macOS: curl -fsSL https://raw.githubusercontent.com/danielmiessler/fabric/main/scripts/installer/install.sh | bash Repository danielmiessler/Fabric Repository stats |Metric|Value| |:-|:-| |Stars|44,291| |Forks|4,303| |Last release|v1.4.523 (2026-10-16)| |Languages|Go 74.7%, Svelte 8.8%, TypeScript 5.6%| |Contributors|257| |AI contributor accounts (Claude / Codex / Cursor / Copilot)|claude: 68| |AI co-authored commits|Claude: 76, Copilot: 2| Main contributor |Field|Value| |:-|:-| |Name|Daniel Miessler| |GitHub|@danielmiessler| |Commits to this repo|940 (top contributor)| |Bio|Helping people and companies transition from their Current to Ideal State.| |Company / Location|Unsupervised Learning / San Francisco Bay Area| |Website|danielmiessler.com| |X / Twitter|@danielmiessler| |Followers|17113| |Public repos|81| |On GitHub since|2009-01-31| ------------------------------------------------------------------------------------------------ Discover the best GitHub repos without the endless scrolling. Get top repos organized by category (AI, DevOps, Databases & more), plus key takeaways from developers' most useful comments - all in one free, twice-weekly newsletter. 👉 Get the best repos & community insights - Free
1/3 每次读文章都重写“帮我总结”，可以看看 Fabric。它把总结、分析观点、解释代码等任务整理成可复用的提示词，叫 Patterns。可以先从一个经常重复的任务入手。 danielmiessler/fabric
2/3 最轻的上手方式：打开 data/patterns，找到 summarize，读里面的提示词，再复制到已有的 AI 工具，附上文章正文。可以加上“用中文回答”等要求。不安装命令行也能使用这部分资源。 github.com/danielmiessler/fabric/tree/main/data/p…
Is prompt engineering still a thing? I recently stumbled over a project called fabric (danielmiessler/fabric) which is essentially a harness for any AI model API which can store your favorite prompts and pipe your text through them. For example you could have a prompt designed to correct your writing, pipe a text through it and receive an AI grading on it. I tested it a bit and I did not really feel too much difference to using Claudes normal chat. This made me wonder if prompt engineering is still necessary or this is unnecessary syntactic sugar that get's handled by anthropics pre-processing anyways.