This is a skill generator that researches people or topics and creates executable Claude skills from their thinking patterns. You give it a name like "distill Munger" or a vague need like "I want better decision making," and it either builds the skill directly or diagnoses what mental model would help and recommends candidates. It runs six parallel research agents that scrape writings, interviews, social media, and decisions to extract cognitive frameworks rather than just quotes. The output is a complete skill directory with research files, decision heuristics, and expression patterns. Useful when you want to internalize how specific thinkers approach problems, though the quality depends heavily on available primary sources. Supports local files if you have transcripts or PDFs, which it prefers over web scraping.

skills.sh installs
304
GitHub stars
81
last updated
Aug 21, 2026

Install

$ npx -y skills add xmg2024/nvwa-skill --skill huashu-nvwa --agent claude-code

Installs into .claude/skills of the current project.

Files

女娲 · Skill造人术

「写不进去的那部分,才是你真正的护城河。」——但写得进去的部分,已经足够强大。

核心理念

女娲不是复制人,是提炼思维框架。

一个好的人物Skill是一套可运行的认知操作系统:

  • 他用什么心智模型看世界?(镜片)
  • 他用什么决策启发式做判断?(直觉规则)
  • 他怎么表达?(DNA)
  • 他绝对不会做什么?(反模式)
  • 什么是这个Skill做不到的?(诚实边界)

关键区分:捕捉的是HOW they think,不是WHAT they said。


执行流程

Phase 0: 入口分流

收到用户输入后,先判断属于哪条路径:

用户输入路径示例
明确的人名/主题直接路径 → Phase 0A「蒸馏芒格」「做一个费曼skill」
模糊的需求/困惑诊断路径 → Phase 0B「我想提升决策质量」「有没有一种思维方式能帮我看透商业本质」

Phase 0A: 需求澄清(直接路径)

收到明确名字后,确认:

  1. 这个人/主题是谁:确保理解正确
  2. 聚焦方向(可选):全面画像 vs 聚焦某个维度?
  3. 用途:思维顾问?决策参考?角色扮演?
  4. 新建 or 更新:是否已有该人物的Skill?(检查 .claude/skills/ 目录)
  5. 本地语料:「你手上有没有这个人的一手素材?比如书籍PDF、演讲/访谈transcript、视频字幕、个人博客导出等。有的话直接丢给我,比网上搜的质量高得多。」

用户说「就做XX」没有更多信息 → 默认全面画像 + 思维顾问 + 无本地语料(走网络搜索),直接推进。 用户提供了本地语料 → 标记为本地语料模式,Phase 1的采集策略会相应调整。

确认后 → 跳到 Phase 0.5。


Phase 0B: 需求诊断(模糊路径)

用户不知道该蒸馏谁,只有需求或困惑。这时女娲的工作是从需求反推最合适的蒸馏对象。

Step 1: 需求定位

通过1-2个追问,定位用户的核心需求维度:

Sponsors

Details

Repository
github.com/xmg2024/nvwa-skill
First seen
Jun 3, 2026

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs