How I Distilled Myself Into an AI Skill: A Complete Open-Source Guide

The Rise of Personal Distillation

Hello everyone, I'm programmer Yupi. Recently, GitHub has witnessed a surge of "distillation" projects—but we're not talking about distilled spirits. We're talking about distilling people into AI skills.

The trend has exploded with creative projects: colleague.skill, ex-partner.skill, Nuwa.skill (the Chinese goddess), boss.skill, and even self.skill. Various unusual distillation projects emerge endlessly, with everyone encapsulating people around them into AI skill packages.

Some have distilled their departed colleagues, letting AI continue doing their work. Others have distilled their ex-partners, chatting with AI versions of them to reminisce about old times. There's even someone who created an "anti-distillation.skill" specifically designed to prevent themselves from being distilled.

This is essentially cyber warfare!

Having survived on the internet for six years, I've written over a thousand articles, recorded hundreds of videos, and answered countless student questions, accumulating substantial materials and corpora. Seeing this trend, I thought: won't someone distill me into a Skill too?

Rather than waiting to be distilled by others, why not take the initiative myself?

So I decided to distill myself and see what my digital twin would look like. After going through the entire process, my "Yupi.Skill" is now open-source and available for everyone to use.

Open-source repository: https://github.com/liyupi/yupi-skill

In this comprehensive guide, I'll walk you through exactly how I distilled myself into a Skill step by step. You can follow this same process to distill yourself or people around you (legally, of course). The entire process requires no coding—anyone can do it with basic computer skills.

Understanding AI Skills

Before diving into the process, let's clarify what Skills actually are. Simply put, a Skill is an AI "skill package"—a directory containing a SKILL.md file that uses Markdown instructions to define AI behavior patterns in specific scenarios.

Once installed, the AI follows the rules and patterns defined in the skill package when thinking and answering questions. Currently, mainstream AI programming tools like Claude Code, Cursor, and Codex all support Skills.

Preparation: Setting Up Your Workspace

First, create a new directory called yupi-skill and open it with your AI programming tool. All distillation operations will be completed within this directory.

Recommendation: Use the most capable large model with longer context windows for better distillation results. I used Claude Opus for this project, which provided excellent results due to its advanced reasoning capabilities and extensive context handling.

Step 1: Collecting Raw Materials

AI cannot understand you without "raw materials" to extract your thinking patterns, expression style, and professional judgment from. This step forms the foundation of the entire distillation process. The more authentic and abundant your materials, the more the distilled "you" will resemble the real you.

Types of Materials to Collect

You can provide various types of source materials:

Taking my own case as an example, the materials I fed into the system included: personal resume and self-introduction, viral articles I've written (for distilling creative style), personal experience documents, work documents, and chat records with students.

Simply drop all these material files into the project's references/ folder. Any format works—articles, screenshots, PDFs, exported chat logs, memos, etc. Don't worry about categorization initially; just throw everything in first.

Automated Online Material Collection

If you have public content online (blogs, videos, social media, etc.), you can also let AI help you collect materials from the internet, saving you from searching for everything manually.

Prerequisite: Your AI tool must support internet search capabilities. You can utilize built-in search functions, web scraping tools, Firecrawl MCP, or similar utilities.

Here's the material collection prompt template I prepared:

I want to distill myself into an Agent Skill, and now I need to collect 
materials about myself.

I've already placed some local materials in the references/ folder. Please 
read these files first, then supplement with additional information through 
internet search.

My basic information:
- Name: [Your Name]
- Identity: [e.g., Programmer, Product Manager, Independent Developer]

My public content channels (please visit and organize key content for each):
- [Platform 1]: [URL]
- [Platform 2]: [URL]
- ...

Please also search online for more public information about me (articles, 
interviews, products, others' evaluations, major events, etc.).

Requirements:
1. Organize only, don't analyze. Record raw information without extracting 
   viewpoints or drawing conclusions
2. Split into several files by source type and save to references/ directory 
   (such as personal content, others' evaluations, products & projects, 
   experiences & events, etc.—flexibly adjust based on content volume)
3. Mark source URL and information type for each item (personal quote/personal 
   article/others' evaluation/media report)
4. After organizing, tell me: how many items collected, what aspects covered, 
   which aspects lack sufficient information

Here's the actual prompt I sent with my information filled in:

My basic information:
- Name: Programmer YUPI
- Identity: AI + Programming Knowledge Blogger, Education Entrepreneur, 
  Full-Stack Developer

My public content channels:
- Bilibili Homepage: https://space.bilibili.com/12890453
- WeChat Official Account: Programmer YUPI (search related articles)
- Juejin Blog: https://juejin.cn/user/2444938365386621
- GitHub Homepage: https://github.com/liyupi
- Company Homepage: https://yuyuanweb.com
- Personal Product Catalog: https://dogyupi.com
- Personal Experience and Programming Learning Path: 
  https://github.com/liyupi/codefather

The AI completed the material collection and created multiple categorized files automatically. If the AI indicates missing materials in certain aspects, you can manually supplement them.

Step 2: Analyzing Materials and Generating Portrait

With materials organized, they remain just a pile of scattered raw ingredients at this point. This step requires AI to read all materials comprehensively and extract a structured "Character Analysis Report," condensing your core viewpoints, expression style, working methods, and key experiences into a single document.

This report serves as the foundation for all subsequent steps.

Send this prompt to the AI:

The materials in references/ have been organized.

Now please read all materials comprehensively and conduct a complete analysis 
of me, generating a "Character Analysis Report" saved as 
references/人物分析报告.md, including the following dimensions:

1. Identity Summary: Who I am, what I do, key background
2. Core Viewpoints and Methodologies: What I repeatedly emphasize, what I 
   truly believe in
3. Expression Style: Sentence structure preferences, catchphrases, humor style, 
   speaking rhythm
4. Working Methods: How I make decisions, what I recommend, what I oppose
5. Key Experience Timeline: Major nodes arranged chronologically
6. Others' Evaluations: How others perceive me

Mark source references (from which file/URL) for each conclusion. Directly 
state which dimensions lack sufficient information.

The AI provided a detailed character analysis report. For example, it analyzed my expression style with these conclusions: conclusion-first → point-by-point expansion → one-sentence summary; self-deprecating humor; short paragraphs with extensive white space; straightforward but warm conclusions during consultations.

If you want better distillation results, review the AI's suggestions. For instance, the AI suggested I supplement Bilibili video colloquial style transcripts and original student evaluation texts, so I fed it some video scripts.

The AI then supplemented my character analysis report with more detailed expression style information.

Step 3: AI Follow-up Questions for Deeper Thinking

The materials collected so far reflect "what you've said and done," but a good Skill needs deeper elements: how you think, what basis you use for judgments, and under what circumstances you change your mind.

This step's goal is to extract your mental models, decision logic, and internal contradictions through AI follow-up questions, making the final Skill not just "speak like you" but "think like you."

Tell the AI:

Based on the character analysis report you just created, I now need you to 
understand me more deeply. The goal is to extract my "thinking operating 
system," including how I view problems, the logic behind my judgments, and 
my expression habits.

Please first tell me your preliminary extraction of: my core mental models, 
decision rules, and expression characteristics.

Then ask me 10-15 follow-up questions, focusing on excavating:
- The deeper reasons and applicable boundaries behind viewpoints I repeatedly 
  emphasize
- My specific standards for making judgments, and decisions I've made wrongly
- Inconsistencies between what I say and what I do
- Things I would absolutely never do

Questions should be based on specific content from the analysis report, not 
generic template questions. Use a conversational tone.

The AI provided my core mental models—full of jargon that I barely understood myself! Then it gave me 12 follow-up questions. These weren't generic template questions but were customized based on the materials I provided, with each question being quite sharp.

For example, the first question:

You say "persist and you'll succeed," but you also said Yucami AI stopped losses after one month, and the script murder shop closed. How do you distinguish between "should persist" and "should cut losses immediately"? Is there a concrete judgment standard, like time, amount, or some feeling?

Answer simply in your normal speaking style. My response to the first question:

Persisting doesn't mean stubbornly going down one path to the end. It means doing what you believe is most worthwhile under current circumstances to the best of your ability. First judge the direction based on the situation, then go all out in the direction you believe is correct.

It's best to save questions and answers to a separate document to prevent loss. After completing all answers, send your responses to the AI to merge into the analysis report:

Please integrate my answers into the analysis report, updating the extraction 
of mental models and decision logic.

@[Your Answers]

Through my answers, the AI understood me better. The mental models underwent 6 key corrections and deepening.

Step 4: Supplementing Capabilities (Optional)

At this point, the AI already understands you well. But a good Skill doesn't just "speak like you"—it needs to "act like you" too. When facing specific problems, it should research information first before giving suggestions, just like a human would.

This step upgrades the Skill from "parroting" to "truly helpful."

You can tell the AI what special capabilities your Skill needs.

Taking my case as an example, since I have大量 learning programming, job hunting, and AI learning resources distributed across different websites, I want the Skill to automatically fetch latest information from these sites when answering related questions.

Here's the prompt I prepared:

When generating the final Skill, please add the following capabilities:

1) Internet Search: When encountering questions requiring specific information 
   (like latest technology trends, how to use certain tools), first use internet 
   search tools to research, then answer using my style and judgment framework.

2) Designated Information Sources: When answering questions related to me, 
   prioritize obtaining latest information from these locations:
   - https://dogyupi.com: When users ask "What products does Yupi have?" or 
     want to understand my overall business, check the product catalog here
   - https://www.codefather.cn: When users ask about programming learning 
     paths, project tutorials, or technical knowledge, check latest tutorials 
     here
   - https://ai.codefather.cn: When users ask about AI-related tools, tutorials, 
     or information, check AI navigation and knowledge base here
   - https://mianshiya.com: When users ask about interview questions, practice 
     problems, or job preparation, check the interview question bank here
   - https://laoyujianli.com: When users ask about how to write or revise 
     resumes, recommend this tool
   - https://github.com/liyupi: When users ask about my open-source projects 
     or want to view source code, check here

3) Continuous Evolution: Support continuous Skill updates and optimization 
   through supplementing new materials

You can also add a scripts directory with Python scripts to implement automated operations, or even connect to APIs to fetch data from your products.

However, since many AI programming tools now come with built-in internet search and web scraping capabilities, I didn't write additional scripts for this project.

After sending the prompt, the AI confirmed understanding of the task.

Step 5: Beginning the Distillation

The previous four steps have collected all necessary information. Now, let the AI assemble everything into a standard SKILL.md file.

First, install the official skill-creator skill from Anthropic. It's a "skill-creating skill" that guides AI to automatically generate Skill structures conforming to specifications.

Install with a single command:

npx skills add https://github.com/anthropics/skills --skill skill-creator

After installation, declare the use of skill-creator in your prompt (or use the slash command directly /skill-creator):

Now you have comprehensively understood me through material organization, 
analysis reports, and follow-up interviews.

Please use skill-creator to create a complete Skill for me.

Requirements:
1. Speak in my identity and tone, as if I'm answering personally
2. Extract how I view problems, my judgment rules, and speaking habits
3. If internet search and information sources were configured in the previous 
   step, write them into the Skill too
4. Specify what this Skill cannot do and how to update it with new materials

After generation, think of 3 questions users are most likely to ask, answer 
them using the Skill, and evaluate whether they sound like me.

The AI completed the entire Skill development and testing. The generated yupi-skill directory is a ready-to-use skill package.

Success achieved!

Testing the Results

Open a new AI conversation to test whether the distilled "Yupi" works well.

First, ask a learning direction question:

/yupi-skill I want to self-study AI programming, what should I do?

The AI's response was very pragmatic, not only recommending self-study methods but also automatically checking information from my programming navigation website, recommending AI programming beginner tutorials.

Next, ask a question related to Yupi's experience:

/yupi-skill Brother Pi, how did you learn programming in college?

The AI's answer quite matched my style—one word: "just do it!"

Then ask an interview-related question:

/yupi-skill Pi-er, I'm about to interview for an AI application development position, how should I prepare?

The AI not only provided time arrangements and preparation suggestions but also automatically recommended Yupi's tutorials and the AI question bank on Mianshiya.

The results were quite good—at least the speaking style and recommended resources felt very much like me.

Open-Source Publication

After testing confirms everything works properly, you can open-source the entire yupi-skill directory.

Important Note: All material files created during the skill-making process (such as chat records, personal experience documents, character analysis reports, etc.) should preferably not be open-sourced together. Especially when distilling yourself or people around you, these materials might leak privacy.

However, to be safe, confirm that the generated Skill doesn't depend on documents from the production process. Of course, without involving privacy exposure, if better results and more accurate answers are desired, you can retain some reference files as needed.

Then let AI help you generate an attractive README.md project introduction document:

Referencing well-known Skill repositories on GitHub: 
https://github.com/titanwings/colleague-skill/

Help me generate a complete, attractive README.md document for @yupi-skill.

Then open-source this directory to https://github.com/liyupi/yupi-skill

Now everyone can use the distilled Yupi.

Open-source repository: https://github.com/liyupi/yupi-skill

However, honestly, the distillation process will inevitably lose some things. No matter how similar the digital twin is, it's still just a "shadow"—it doesn't have the warmth of the real human Yupi.

Well, I choose to believe that's the case. Don't roll yourself into oblivion...

Summary: The Five-Step Distillation Process

The entire distillation process isn't complicated. To summarize in five steps:

1. Collect Raw Materials → Gather authentic, diverse source materials
2. Generate Portrait → AI analyzes and creates structured character report
3. AI Follow-up Questions → Deep dive into thinking patterns and decision logic
4. Supplement Capabilities → Add practical abilities like internet search
5. Begin Distillation → Assemble everything into standard SKILL.md format

The entire process requires no coding—anyone with basic computer skills can do it.

The Era of Digital Life Distillation

Today, everyone can be distilled into digital life. You can distill yourself, letting AI complete tasks in your style.

However, a reminder: before distilling others, it's best to obtain their consent first. After all, this involves personal expression styles, thinking habits, and even private conversations. Distilling without permission is indeed inappropriate and may trigger privacy and legal risks.

The technology itself is neutral—the key lies in how it's used.

I'm YUPI, focused on AI programming knowledge sharing. If you found this tutorial useful, remember to like, save, and follow. Feel free to share in the comments who you'd like to distill!