Distilling Yourself into an AI Skill: A Complete Guide to Creating Personal Digital Twins

The Rise of Skill Distillation: Turning People into AI Capabilities

Recently, GitHub has witnessed an intriguing trend: "skill distillation." No, this isn't about producing fine spirits—it's about distilling human beings into AI skill packages.

The phenomenon has exploded with creative variations: colleague.skill, ex-partner.skill, creator.skill, boss.skill, and even self.skill. Developers are encapsulating people around them into AI skill packages at an unprecedented rate. Some have distilled departed colleagues so AI can continue their work. Others have created digital versions of former partners to reminisce through AI conversations. There's even an "anti-distillation.skill" designed to prevent oneself from being distilled.

This represents a form of cyber confrontation—a digital arms race of personal AI avatars.

Why Create Your Own Skill Before Someone Else Does

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 material and language data. Observing this trend, one question arose: would someone distill me into a Skill without my consent?

Rather than waiting to be distilled by others, I decided to take matters into my own hands. The result: my "Yupi.Skill" is now open source.

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

This guide walks through the complete process of distilling yourself into a Skill. You can follow this workflow to distill yourself or others (legally and ethically, of course). The entire process requires no coding—literally anyone can do it.

Understanding Skills: AI Behavior Definition Packages

Skills are essentially AI "capability packages"—directories containing a SKILL.md file that uses Markdown instructions to define AI behavior patterns in specific scenarios. Once installed, AI systems think and respond according to the rules defined in the skill package.

Major AI programming tools including Claude Code, Cursor, and Codex all support Skills. This technology represents a significant advancement in AI personalization and customization.

Step 1: Gathering Raw Materials

AI cannot understand you without "raw materials" to extract your thinking patterns, communication style, and professional judgment from.

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

Types of Materials to Collect

In my case, I provided: personal resume and self-introduction, viral articles (for distilling creative style), personal experience documents, work documents, and chat records with students.

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

Automated Online Material Collection

If you have public content online (blogs, videos, social media), you can let AI help collect materials automatically, saving you from manually gathering everything.

This requires AI tools with internet search capabilities. You can use built-in search functions, web scraping tools, Firecrawl MCP, or similar utilities.

Here's a template prompt for material collection:

I want to distill myself into an Agent Skill and 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 online searches.

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]: [URL]
- [Platform 2]: [URL]
- ...

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. Divide 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. Label each item with source URL and information type (personal quote/personal article/others' evaluation/media report)
4. After completion, tell me: how many items collected, what aspects covered, which aspects lack sufficient information

After replacing the template content with your actual information, AI completes the material collection and creates multiple categorized files automatically.

If AI indicates missing material in certain areas, you can manually supplement those gaps.

Step 2: Analyzing Materials and Generating Profile

Once materials are gathered, they remain scattered raw ingredients. This step requires AI to read all materials comprehensively and distill a structured "Personality Analysis Report" encompassing your core viewpoints, expression style, working methods, and key experiences—all condensed into a single document.

This report serves as the foundation for all subsequent steps.

Send this prompt to AI:

The materials in references/ are now organized.

Please read all materials comprehensively and conduct a complete analysis of me, generating a "Personality Analysis Report" saved as references/Personality Analysis Report.md, including the following dimensions:

1. Identity summary: Who I am, what I do, key background
2. Core viewpoints and methodology: What I repeatedly emphasize, 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

Label the source basis for each conclusion (from which file/URL), and explicitly state which dimensions lack sufficient information.

AI will provide a detailed personality analysis report. For example, it might analyze my expression style as: conclusion first → point-by-point expansion → one-sentence summary; self-deprecating humor; short paragraphs with extensive white space; straightforward advice during consultations but warm conclusions.

To improve distillation quality, review AI's suggestions. For instance, AI might recommend supplementing with Bilibili video transcript styles and original student evaluation texts, prompting me to provide additional video scripts.

Step 3: AI Follow-up Questions: Digging Deeper into Thinking Patterns

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

This step aims to extract your mental models, decision logic, and internal contradictions through AI follow-up questions—enabling the final Skill to not just "speak like you" but "think like you."

Tell AI:

Based on the personality analysis report you just created, I need you to understand me more deeply.

The goal is to extract my "thinking operating system," including how I view problems, my judgment logic, and expression habits.

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挖掘:
- Deeper reasons and applicable boundaries behind viewpoints I repeatedly emphasize
- Specific criteria I use for making judgments, and decisions I've gotten 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 will provide your core mental models (potentially filled with jargon that's nearly incomprehensible).

Then AI generates follow-up questions. These aren't generic template questions but are customized based on the materials you provided—each question is incisive.

Answer simply using your normal speaking style. For example, to the first question:

"You say 'persist and you'll succeed,' but you also said Yucoding AI stopped losses within a month and the script murder mystery store closed. How do you distinguish between 'should persist' and 'should cut losses immediately'? Is there a specific judgment criterion—time, amount, or some feeling?"

My answer: Persisting doesn't mean stubbornly following 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 circumstances, then pour your full effort into the direction you believe is correct.

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]

Through your answers, AI understands you better. The mental model section receives 6 key corrections and deepening updates.

Step 4: Supplementing Capabilities (Optional)

At this point, AI 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 before giving recommendations, just like a human would.

This step elevates the Skill from "parroting" to "genuinely helpful."

You can tell AI what special capabilities your Skill needs.

In my case, since I have extensive resources for learning programming, job hunting, and AI studies distributed across different websites, I want the Skill to automatically fetch latest information from these sites when answering related questions.

Prepare this prompt:

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 locations:
- https://dogyupi.com: When users ask "What products does Yupi have" or want to understand my overall business
- https://www.codefather.cn: When users ask about programming learning paths, project tutorials, technical knowledge
- https://ai.codefather.cn: When users ask about AI tools, tutorials, information
- https://mianshiya.com: When users ask about interview questions, practice problems, job preparation
- https://laoyujianli.com: When users ask how to write or revise resumes
- https://github.com/liyupi: When users ask about my open source projects or want to view source code

3) Continuous evolution: Support updating and optimizing Skill through supplementary new materials

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

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

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

Step 5: Beginning Distillation

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

First, install Anthropic's official skill-creator skill. This is a "skill-creating skill" that guides AI to automatically generate Skill structures meeting specifications.

Install with a single command:

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

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

Now you fully understand 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, my judgment rules, my speaking habits
3. If internet search and information sources were configured in the previous step, write them into the Skill
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 responses resemble me.

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

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 provides a very pragmatic response, not only recommending self-study methods but automatically fetching 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 university?

AI's response fits my style well—one word: "Just do it!"

Then ask an interview-related question:

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

AI not only provides scheduling arrangements and preparation suggestions but automatically recommends Yupi's tutorials and AI question banks on Mianshiya.

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

Open Source Publication

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

Important: All material files generated during skill creation (chat records, personal experience documents, personality analysis reports, etc.) should generally not be open sourced together. Especially when distilling yourself or others, these materials may leak privacy.

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

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

Reference 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

Honestly, the distillation process inevitably loses something. No matter how similar the digital twin is, it remains just a "shadow"—it lacks the warmth of the real human Yupi.

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

Final Summary

The entire distillation process isn't complex. In summary, five steps:

1. Collect raw materials → Gather authentic, abundant source materials
2. Generate profile → Create structured personality analysis report
3. AI follow-up questions → Extract deeper thinking patterns and mental models
4. Supplement capabilities → Add internet search and designated information sources
5. Begin distillation → Assemble everything into standard SKILL.md file

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

Today, anyone 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 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.

This comprehensive guide demonstrates the complete process of creating a personalized AI skill, from material collection through final open source publication, enabling anyone to create their own digital twin without coding expertise.