So Impressive: I Distilled Myself Into a Skill! Now Open Source

Introduction: The Distillation Trend

Hello everyone, I'm programmer Yupi (鱼皮).

Recently, GitHub has witnessed a surge in "distillation" enthusiasm. No, not distilling alcohol—distilling people.

Colleague.skill, Ex-partner.skill, Nuwa.skill (the Chinese goddess who created humanity), Boss.skill, Self.skill... All sorts of bizarre distillation projects are emerging. Everyone is "encapsulating" people around them into AI skill packages.

Some people distilled their resigned colleagues, letting AI continue doing their work. Others distilled their ex-partners, chatting with AI versions to reminisce about old times. There's even someone who created an "Anti-Distillation.skill" specifically designed to prevent themselves from being distilled.

Good heavens—is this cyber warfare?!

Having survived on the internet for six years, writing over a thousand articles, recording hundreds of videos, and answering countless student questions, I've accumulated substantial materials and corpora. Seeing this trend, I thought: will someone distill me into a Skill too?

No—rather than waiting for others to distill me, I might as well take action myself!

So I decided to distill myself and see what my digital avatar would look like.

After some work, my "Yupi.Skill" is now open source:

Open Source Repository: https://github.com/liyupi/yupi-skill

Below, I'll walk you through 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.

Understanding Skills

💡 Skills are essentially AI "skill packages." They're directories containing a SKILL.md file that uses Markdown instructions to define AI behavior patterns in specific scenarios. After installation, AI can think and answer questions according to the rules in the skill package. Currently, mainstream AI programming tools like Claude Code, Cursor, and Codex all support Skills.

You can refer to my article on AI Code Navigation to learn more about Skills.

Preparation

First, create a new yupi-skill directory and open it with an AI programming tool. All our 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.

Step 1: Collecting Raw Materials

AI doesn't understand you—it needs "raw materials" to extract your thinking patterns, expression style, and professional judgment.

This step forms the foundation of the entire process. The more authentic and abundant your materials, the more the distilled "you" will resemble the real you.

Material Types and Their Purpose

My Material Collection

Taking myself as an example, the materials I fed into the system included:

• Personal resume and self-introduction
• Viral articles I wrote (for distilling creative style)
• Personal experience documents
• Work documents
• Chat records with students

Simply throw all these material files into the project's references/ folder. Any format works—articles, screenshots, PDFs, exported chat logs, memos... Don't categorize yet—just dump everything in first.

Online Collection of Public Materials

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 individually.

Prerequisite: Your AI tool must support internet search. You can use built-in search functions, web scraping tools, Firecrawl MCP, etc.

Material Collection Prompt Template

Here's the prompt template I prepared for material collection:

I want to distill myself into an Agent Skill, and first 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 more information 
through internet search.

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

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

Also please 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 (e.g., personal content, others' evaluations, products 
   and projects, experiences and events—adjust flexibly based on 
   content volume)
3. Mark source links and information types for each entry 
   (personal quotes/personal articles/others' evaluations/media reports)
4. After organizing, tell me: how many items collected, what aspects 
   covered, which aspects lack sufficient information

My Actual Prompt

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

My basic information:
- Name: Programmer Yupi
- Identity: AI + Programming Knowledge Creator, Education Entrepreneur, 
  Full-stack Developer

My public content channels:
- Bilibili Homepage: https://space.bilibili.com/12890453
- WeChat Official Account: Programmer Yupi (search relevant 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

AI Collection Results

The AI completed material collection and created multiple categorized files automatically.

If the AI indicates certain materials are missing, you can manually supplement them.

Step 2: Analyze Materials and Generate Profile

With materials organized, they're still just a pile of scattered raw ingredients at this point.

This step requires AI to read all materials thoroughly and extract a structured "Character Analysis Report," condensing your core viewpoints, expression style, working methods, and key experiences into a single document.

This report forms the foundation for all subsequent steps.

Analysis Prompt

Send this prompt to AI:

Materials in references/ are now organized.

Now please read all materials thoroughly and conduct comprehensive 
analysis on me, generating a "Character Analysis Report."

Save as references/人物分析报告.md (Character-Analysis-Report.md), 
including the following dimensions:

1. Identity Summary: Who I am, what I do, key background
2. Core Viewpoints and Methodologies: What I repeatedly say, what I 
   truly believe
3. Expression Style: Sentence 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 for each conclusion (which file/link), and 
explicitly state dimensions with insufficient information.

Analysis Results Example

The AI provided a detailed character analysis report. For example, it analyzed my expression style:

• Structure: Conclusion first → Point-by-point expansion → One-sentence summary
• Humor: Self-deprecating humor
• Formatting: Short paragraphs + extensive white space
• Consultation style: Frank and direct but warm conclusions

Iterative Improvement

If you want better distillation results, review the AI's suggestions. For instance, the AI suggested I supplement Bilibili video transcript styles and original student evaluations, so I fed it some video scripts.

The AI then added more of my expression style details to the character analysis report.

Step 3: AI Follow-up Questions, Mining 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'd change your mind.

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

Deep Dive Prompt

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 expression habits.

First, please 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 mining:
- Deeper reasons and applicable boundaries behind viewpoints I 
  repeatedly emphasize
- Specific criteria I use for judgments, and decisions I got wrong
- 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 questions. Use a conversational tone.

AI's Core Mental Model Extraction

The AI provided my core mental models—the jargon was so dense I almost couldn't understand it myself!

Customized Follow-up Questions

The AI then gave me 12 follow-up questions. These weren't generic templates but customized based on materials I provided. Each question was sharp and insightful:

Example Question 1:

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

My Response (answer simply in your normal speaking style):

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

Saving Q&A Records

Best practice: save questions and answers to a separate document to prevent loss. After completing all answers, send your responses to AI for integration into the analysis report:

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

@[Your Answers]

Report Updates

Through my answers, the AI understood me better. The mental model received 6 key corrections and deepening updates.

Step 4: Supplement Capabilities (Optional)

At this point, AI understands you very well. But a good Skill isn't just about "sounding like you"—it needs to "act like you" too. When facing specific problems, it should research information first before giving recommendations, just like a human would.

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

Capability Configuration Prompt

You can tell AI what special capabilities your Skill needs.

Taking myself as an example: since I have extensive resources for learning programming, job hunting, and learning AI 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 (e.g., 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 fetching latest information from these places:
   - https://dogyupi.com: When users ask "What products does Yupi 
     have?" or want to understand my overall business, check product 
     catalog here
   - https://www.codefather.cn: When users ask about programming 
     learning paths, project tutorials, technical knowledge, check 
     latest tutorials here
   - https://ai.codefather.cn: When users ask about AI tools, 
     tutorials, information, check AI navigation and knowledge base 
     here
   - https://mianshiya.com: When users ask about interview questions, 
     practice problems, job preparation, check interview question 
     bank here
   - https://laoyujianli.com: When users ask how to write/revise 
     resumes, recommend this tool
   - https://github.com/liyupi: When users ask about my open source 
     projects or want to see source code, check here

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

Advanced: Scripts Directory

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

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

AI Confirmation

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

Step 5: Begin Distillation

The previous four steps have collected all information. This step has AI assemble everything into a standard SKILL.md file.

Installing skill-creator

First, install Anthropic's official skill-creator Skill. It's a "Skill that creates Skills," guiding AI to automatically generate Skill structures conforming to specifications.

Installation requires just one command line:

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

Using skill-creator

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

Now you've 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 myself am answering
2. Extract how I view problems, rules for making judgments, speaking 
   habits
3. If internet search and information sources were configured in 
   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.

Generation Complete

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

Mission accomplished!

Testing the Results

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

Test Question 1: Learning Direction

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

AI Response: Very pragmatic—not only recommended self-study methods but also automatically fetched information from my programming navigation website, recommending AI programming beginner tutorials.

Test Question 2: Personal Experience

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

AI Response: Very much matches my style—one word: "Just do it!" (干就完了!)

Test Question 3: Interview Preparation

/yupi-skill Pi-er, I'm interviewing for an AI application development position, how should I prepare!

AI Response: Not only provided timeline arrangement and battle preparation suggestions but also automatically recommended Yupi's tutorials and AI question banks on Mianshiya.

Evaluation

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

Open Source Release

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

Privacy Considerations

Important: All material files created during the Skill-making process (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 may leak privacy.

As a precaution, confirm the generated Skill doesn't depend on documents from the creation process. Of course, without involving privacy exposure, if you want better results and more accurate answers, you can retain some reference files as needed.

Generate README

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

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

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

Publish to GitHub

Then publish 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

A Note on Digital Avatars

Honestly, the distillation process will inevitably lose some things. No matter how similar the digital avatar is, it's just a "shadow"—it lacks the warmth of the real Yupi.

Yes, I choose to believe this is true. Otherwise, I might work myself into oblivion...

Summary: The Five-Step Distillation Process

The entire distillation process isn't complex. Summarized in five steps:

1. Collect Raw Materials: Gather authentic materials reflecting your personality, work, and communication style
2. Generate Profile: Have AI analyze materials and create structured character analysis report
3. AI Follow-up Questions: Let AI ask deep questions to extract your mental models and decision logic
4. Supplement Capabilities: Add special capabilities like internet search and designated information sources
5. Begin Distillation: Use skill-creator to assemble everything into a standard SKILL.md file

The entire process requires no coding—anyone can do it.

Ethical Considerations

Nowadays, 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.

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

Conclusion

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!

The distillation trend represents a fascinating intersection of AI capability and personal identity. As these tools become more accessible, we're entering an era where digital twins transition from science fiction to everyday reality. The question isn't whether this technology will proliferate, but how we'll choose to use it responsibly.

Whether you're looking to preserve your expertise for future projects, create a consistent brand voice across applications, or simply explore the philosophical implications of digital identity, the distillation process offers a structured pathway to achieving these goals.

The key is approaching this technology thoughtfully—respecting privacy, obtaining consent, and understanding that while digital avatars can mimic our patterns, they remain tools rather than replacements for genuine human connection.

This tutorial was originally published on 2026-04-11 by programmer Yupi and provides a comprehensive step-by-step guide to creating personal AI Skills through the distillation process.