huashu-nuwa

Distill public figures' cognitive models into runnable SKILL.md files.

1|1|Updated Mar 5, 2026
One-click install
npx skills add https://github.com/tan-yong-sheng/GrowChat --skill huashu-nuwa-tan-yong-sheng
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: huashu-nuwa
Source: https://github.com/tan-yong-sheng/GrowChat/tree/main/.claude/skills/huashu-nuwa
Command: npx skills add https://github.com/tan-yong-sheng/GrowChat --skill huashu-nuwa-tan-yong-sheng

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires yt-dlp, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Huashu Nuwa perspective skill distills cognitive operating systems from public figures into runnable Skills that can be activated and used as independent thinking agents.

Core Features & Use Cases

  • Generates 3–7 core mind models, 5–10 decision heuristics, expression DNA, values and anti-patterns, and honest boundaries, all written into SKILL.md for activation.
  • Phase-driven workflow: research, synthesis, validation, and packaging into a self-contained Skill that can be deployed locally.
  • Supports cross-domain applications: business, tech, education, and creative thinking by adopting a given figure’s frame.
  • Includes references/research and a scripts suite to support on-demand extraction, quality checks, and incremental updates.

Quick Start

Trigger Nuwa to build or update a Skill by saying the activation phrases like “蒸馏XX” or “造Skill” followed by the target name or fuzzy request, then let it generate or refresh the Skill content.

Frequently Asked Questions about huashu-nuwa

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

FAQPage Schema
How do I distill a public figure's cognitive models and decision heuristics into a runnable skill?

To distill cognitive models and decision heuristics, trigger the skill using activation phrases like “蒸馏XX” or “造人” followed by the target name. It extracts 3–7 mind models and 5–10 heuristics, writing them into a SKILL.md file for deployment.

What is a perspective skill and how does it capture a figure's thinking framework?

A perspective skill captures a figure's thinking framework by distilling their cognitive operating system into runnable cognitive models and heuristics. It extracts expression DNA, values, anti-patterns, and honest boundaries to create an independent thinking agent.

How do I create a self-contained skill from a specific person's思维方式 using Claude Code?

You create a self-contained skill from a specific person's思维方式 by triggering the Nuwa workflow in Claude Code. Enter a fuzzy request or target name, and it runs research, synthesis, and validation phases to package the extracted cognitive models into a local skill.

Do I need yt-dlp installed to extract mental models and build cognitive skills?

Yes, you need yt-dlp installed to build cognitive skills, as it is a required dependency. The scripts suite uses it to support on-demand extraction, quality checks, and incremental updates during the research phase of the perspective skill workflow.

Can I update an existing perspective skill instead of generating a completely new one?

Yes, you can update an existing perspective skill instead of generating a new one. Use the activation triggers like “女娲” or “造Skill” followed by the target name to refresh the skill content and run incremental updates on the extracted heuristics.

What are the limitations when distilling cognitive operating systems for cross-domain applications?

Limitations when distilling cognitive operating systems include the reliance on available public data for accurate extraction of mind models and expression DNA. The skill explicitly defines honest boundaries and anti-patterns to prevent misapplication across business, tech, or creative domains.