create-yourself

Generate a runnable digital-self Skill from chat logs, diaries, and photos.

Updated Aug 15, 2026
One-click install
npx skills add https://github.com/qqlcx5/skills-hub --skill create-yourself-qqlcx5
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: create-yourself
Source: https://github.com/qqlcx5/skills-hub/tree/main/skills/create-yourself
Command: npx skills add https://github.com/qqlcx5/skills-hub --skill create-yourself-qqlcx5

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, Pillow, pypinyin, and includes scripts (resource) and references (resource) components.

What problem does it solve? It turns scattered personal data—WeChat/QQ chat exports, diaries, social media posts, and photos—into a structured, invocable AI persona that thinks and speaks like you, without manual prompt engineering. ## Core Features & Use Cases - Multi-source ingestion: Parses WeChat (WeChatMsg, LiuHen, PyWxDump), QQ (txt/mht), social media text, and photo EXIF metadata to extract speech patterns, values, and life timelines. - Dual-layer generation: Produces Part A (Self Memory: experiences, values, habits, relationships) and Part B (Persona: 5-layer personality model from hard rules to interpersonal behavior), combined into a runnable SKILL.md. - Evolution and versioning: Supports appending new materials, conversational corrections ("I wouldn't say that"), automatic version backups, and rollback. - Use Case: Export your WeChat history, run the intake flow, and get a /{slug} command that replies in your tone, catchphrases, and decision logic. ## Quick Start Ask the agent to create a self skill from your chat history by saying: help me distill myself into a skill using my exported WeChat chat logs.

Frequently Asked Questions about create-yourself

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create an AI persona from my chat history?

Run the /create-yourself command, answer three intake questions (alias, basic info, self-portrait), then provide chat exports or other materials. The skill analyzes your messages and generates self.md and persona.md files combined into an invocable SKILL.md.

What chat export formats are supported for persona generation?

The WeChat parser supports WeChatMsg exports (txt/html/csv), LiuHen JSON, PyWxDump SQLite, and plain pasted text. The QQ parser handles txt and mht exports from QQ Message Manager. Format detection is automatic based on file extension and content.

Can I update my generated persona with new data later?

Yes. Append new chat logs, diaries, or photos and the skill analyzes only the incremental content, merging it into the existing self.md or persona.md without overwriting prior conclusions. Each update is automatically backed up for rollback.

How do I fix responses that don't sound like me?

Say phrases like "I wouldn't say that" or "that's wrong" during conversation. The correction handler classifies the fix as a memory or persona issue, appends it to the Correction section of the relevant file, and regenerates the combined SKILL.md immediately.

What are the limitations of generating a persona from text alone?

Fidelity depends heavily on raw material quality; chat logs plus diaries outperform narration alone. Dimensions lacking evidence are marked as insufficient rather than inferred, and the persona only represents who you were at distillation time.