Hello everyone, I'm programmer Yupi.

Recently, GitHub has witnessed a surge of "distillation" enthusiasm.

Not distilling liquor, but distilling people.

Colleague.skill, Ex-partner.skill, Nuwa.skill, Boss.skill, Self.skill... Various strange distillation projects are emerging one after another. Everyone is "encapsulating" people around them into AI skill packages.

Someone distilled a resigned colleague to let AI continue their work; someone distilled their ex-partner to chat with the AI version and recall old times; some even created an "Anti-Distillation.skill" specifically to prevent themselves from being distilled.

Wow, is this cyber confrontation?!

Having survived on the internet for 6 years, writing over a thousand articles, recording hundreds of videos, and answering countless student questions, I've accumulated quite a bit of material and corpus. Seeing this trend, I thought: will someone distill me into a Skill too?

No, rather than waiting to be distilled by others, 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" has been open-sourced.

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

Below, I'll take everyone through how I distilled myself into a Skill step by step. You can follow this process to distill yourself or people around you (legally, of course). The entire process requires no coding—anyone can do it.

Understanding Skills

Simply put, Skills are a type of AI "skill package." It's a directory 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.

Preparation

First, create a yupi-skill directory and open it with an AI programming tool. All distillation operations will be completed in this directory.

It's recommended to use a large model with strong capabilities and longer context for better distillation results. I used Claude Opus for this process.

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 is the foundation of the entire process. The more authentic and abundant the materials, the more the distilled "you" will resemble you.

You can provide these types of materials:

Self-Introduction/Resume: Your name, years of experience in XXX, MBTI type, etc. This distills your identity positioning and personality traits.

Personal Experiences: Key stories about education, work, and career transitions. This distills your values and growth path.

Chat Records: Exported conversations from WeChat, Feishu, or DingTalk. This captures your real speaking style and catchphrases.

Work Documents: Weekly reports, proposals, code review comments. This reveals your professional judgment and working methods.

Creative Content: Blogs, video scripts, social media posts. This shows your viewpoints and expression style.

Others' Evaluations: Feedback from colleagues, comments from friends. This uncovers your blind spots (characteristics you can't see yourself).

Taking myself as an example, the materials I provided included: personal resume and self-introduction, viral articles I wrote (to distill creative style), personal experience documents, work documents, and chat records with students.

Simply drop these material files into the project's references/ folder. Any format works—articles, screenshots, PDFs, exported chat records, memos. No need to categorize; just throw 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 online, saving you from searching one by one.

The prerequisite is that your AI tool supports online search. You can use its built-in online search function, web scraping tools, Firecrawl MCP, etc.

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 combine online search to supplement more information.

My basic information:

  • Name: [Your Name]
  • Identity: [e.g., Programmer, Product Manager, Independent Developer]

My public content channels (please visit and organize key content one by one):

  • ...

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, don't extract viewpoints or draw conclusions.
  2. Divide into several files by source type and save to references/ directory (such as personal content, others' evaluations, products and projects, experiences and events, etc., flexibly adjust based on content volume).
  3. Mark the source link and information type for each piece of information (original quote from me/my article/others' evaluation/media report).
  4. After organizing, tell me: how many pieces of information were collected, what aspects were covered, and which aspects have insufficient information."

Replace the content in the template with your actual information. For example, the prompt I actually sent included my Bilibili homepage, WeChat official account, Juejin blog, GitHub homepage, company homepage, personal product collection, and personal experience and programming learning route.

AI completed the material collection and created multiple files classified by category.

If AI says certain aspects of materials are missing, you can manually supplement them.

Step 2: Analyzing Materials and Generating Portrait

The materials are organized, but at this point, they're just a pile of scattered raw materials.

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 one document.

This report is the foundation for all subsequent steps.

Send this prompt to AI:

"The materials in references/ are now organized.

Now please read all materials thoroughly and conduct a comprehensive analysis of me, generating a 'Character Analysis Report' saved as references/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 see me

Mark the source basis for each conclusion (from which file/link), and directly state which dimensions have insufficient information."

AI will provide a detailed character analysis report. For example, it analyzed my expression style: conclusion first → point-by-point expansion → one-sentence summary; self-deprecating humor; short paragraphs + extensive white space; straightforward but warm closing in consultations.

If you want better distillation results, check AI's suggestions. For example, AI suggested I supplement Bilibili video colloquial style transcripts and original student evaluations, so I fed it some video scripts.

AI supplemented more of my expression styles in the character analysis report.

Step 3: AI Questioning to Dig Deeper Thinking

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

The goal of this step is to dig out your mental models, decision logic, and internal contradictions through AI questioning, making the final Skill not just "speak like you" but "think like you."

Tell 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 of 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 digging out:

  • The deeper reasons and applicable boundaries behind viewpoints I repeatedly emphasize
  • My specific criteria for making judgments, and decisions I've made incorrectly
  • Inconsistencies between what I say and what I do
  • Things I would absolutely never do

Questions should be based on specific content in the analysis report, don't ask generic questions, use a conversational tone."

AI will provide my core mental models, full of jargon that I almost couldn't understand.

Then AI gave me 12 follow-up questions. These questions weren't generic templates but customized based on the materials I provided, each one sharp:

Answer simply in your usual speaking style. For example, the first question:

"You say 'persist and you will succeed,' but you also said Yucumi AI stopped losses in one month, and the script murder shop closed. How do you distinguish between 'should persist' and 'should cut losses immediately'? Is there a specific judgment criterion, such as time, amount, or some feeling?"

My answer: Persisting doesn't mean going down one path blindly, but doing what you believe is most worthwhile in the current situation 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 answers to AI to merge into the analysis report:

"Please integrate my answers into the analysis report and update the extraction of mental models and decision logic.
@[Your Answers]"

AI understood me better through my answers. The mental model made 6 key corrections and deepening.

Step 4: Supplementing Capabilities (Optional)

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

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

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 hope the Skill can automatically obtain the latest information from these websites when answering related questions.

The prompt prepared for AI:

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

1) Online Search: When encountering questions requiring specific information (such as latest technology trends, usage of certain tools), first use online search tools to gather information, then answer using my style and judgment framework.

2) Designated Information Sources: When answering questions related to me, prioritize obtaining latest information from these places:

  • https://dogyupi.com: When users ask 'What products does Yupi have' or want to understand my overall business, check the product collection here
  • https://www.codefather.cn: When users ask about programming learning routes, project tutorials, technical knowledge, check latest tutorials here
  • https://ai.codefather.cn: When users ask about AI-related 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 or modify 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 updates and optimization of Skill by supplementing new materials"

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

However, since many AI programming tools now come with built-in online search and web scraping functions, I won't write additional scripts here.

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

Step 5: Starting Distillation

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

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

You can install it with a single line of command:

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

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

"Now you have fully 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, the rules for making judgments, and speaking habits
  3. If online 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."

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

Mission accomplished!

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?

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

Then ask a question related to Yupi's experience:

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

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

Then ask an interview-related question:

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

AI not only provided time arrangements and battle preparation suggestions but also automatically recommended Yupi's tutorials and AI question bank on Interview Duck.

The results are pretty good—at least the speaking style and recommended resources sound quite like me.

Open Source Release

After testing confirms no issues, you can open-source the entire yupi-skill directory.

Note: All material files generated during the skill creation 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 may leak privacy.

But to be safe, still 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 generate an attractive README.md project introduction document:

Refer to 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

Done! Now everyone can use the distilled Yupi.

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

But honestly, something will definitely be lost in the distillation process. No matter how similar the digital avatar is, it's just a "shadow"—it still lacks the warmth of the real human Yupi.

Hmm, I choose to believe this is the case. Don't roll yourself out of existence...

Conclusion

The entire distillation process is not complicated. To summarize in five steps: collect raw materials → generate portrait → AI questioning → supplement capabilities → start distillation.

No coding required throughout—anyone can do it.

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.

I'm Yupi, focusing on AI programming knowledge sharing. If you find this tutorial useful, remember to like, save, and follow. Also welcome to chat in the comments about who you want to distill.