English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Nuwa.skill: When AI Learns to Distill Human Thinking — From colleague.skill to a Cognitive Mirror of Great Minds

Forum topic · 小凯 · 2026-04-09

Summary

Nuwa.skill is an open-source project by Chinese developer Huashu (花叔) that extends the viral GitHub project colleague.skill, which 'distills' departed coworkers' chat logs and documents into AI digital clones. While colleague.skill (7,000+ stars in five days) replicated workplace behavior, Nuwa.skill goes further: it distills the thinking styles of great figures like Steve Jobs, Charlie Munger, Elon Musk, Richard Feynman, Naval Ravikant, and Zhang Xuefeng from their abundant public materials — books, talks, podcasts, tweets, and critics' analyses. Its architecture features a five-layer distillation model (expression DNA, mental models, decision heuristics, anti-patterns/values, and honest boundaries), a six-agent parallel research pipeline (writings, conversations, social expression, external views, decisions, timeline), and a triple verification process requiring cross-domain recurrence, generative power, and exclusivity. Unlike simple role-play prompting, the resulting skills run a person's cognitive frameworks on new questions. The project openly acknowledges limits: intuition cannot be distilled, snapshots cannot capture belief changes, and public expression may differ from real thoughts — making the output a 'cognitive mirror' rather than a replacement of the original person.

Key points

This article introduces Nuwa.skill (女娲.skill), an open-source project by Chinese developer Huashu (花叔), built on the momentum of the viral GitHub project colleague.skill.

Origin: from colleague.skill to Nuwa.skill

  • In late March 2026, developer titanwings released colleague.skill, which feeds a departed coworker's chat logs, documents, and emails to AI to "distill" a digital stand-in. It gained 7,000+ GitHub stars in five days.
  • colleague.skill uses a "dual-track" architecture: Part A (Work Skill) for hard professional capabilities, and Part B (Persona) — a five-layer personality structure covering hard rules, identity, expression style, decision patterns, and interpersonal behavior.
  • Huashu's insight: instead of distilling coworkers' *behaviors*, why not distill the *thinking styles* of the greatest minds, whose public materials (books, talks, interviews, tweets) are vastly richer?
  • The five-layer distillation model

    | Layer | Meaning | |---|---| | How they speak | Expression DNA — tone, rhythm, diction | | How they think | Mental models — the cognitive "glasses" they wear | | How they decide | Decision heuristics — quick judgment rules | | What they won't do | Anti-patterns and value bottom lines | | Knowing limits | Honest boundaries — what the skill cannot do |

    Example distilled mental models:

  • Jobs: Focus means saying no; end-to-end control; the "insanely great" standard
  • Munger: Invert, always invert; latticework of mental models
  • Musk: Compute physical limits; first principles; question every requirement
  • Naval: Desire is a contract; specific knowledge + leverage; compounding
  • Feynman: Naming is not understanding; build to understand
  • Methodology: six-dimensional parallel research

    Six agents research each person simultaneously:

    1. Writings — core arguments recurring across 3+ sources 2. Conversations — impromptu responses under questioning (e.g., Ilya Sutskever on scaling laws) 3. Expression — high-frequency words and style on social media 4. External views — critics and biographers, revealing blind spots 5. Decisions — actual behavior at major inflection points 6. Timeline — capturing how the person changed over time

    Results pass triple verification before becoming core mental models:

  • Cross-domain recurrence: appears in at least two different domains
  • Generative power: can predict the person's stance on new questions
  • Exclusivity: not something every smart person would say
  • Naval's thousands of tweets and dozens of podcast hours compress into just 5 mental models and 8 decision heuristics. Final quality gate: a "3+1 test" — 3 questions the person publicly answered (check directional consistency) plus 1 question they never addressed (check appropriate uncertainty rather than confident fabrication).

    Not role-play, but a cognitive operating system

  • Simple role-play *quotes* a person's famous lines; Nuwa.skill *runs* their cognitive frameworks on new problems.
  • Example: asked "OpenAI vs Anthropic — who is right?", a Jobs-style skill reframes it as a contest of *taste*, invokes focus-as-saying-no and end-to-end control, and concludes whoever controls chips + models + interface wins.
  • Use cases shown: Naval for life choices, Musk for business cost analysis, Munger for investment decisions, Feynman for testing true understanding, MrBeast for content optimization.
  • Honest limits and ethics

    The skill explicitly documents what it cannot do:

  • Distill intuition — the felt judgment after frameworks run stays unwritten ("what can't be written in is your real moat")
  • Capture sudden changes — it's a snapshot as of research time, not a live clone
  • Pierce performative expression — public statements may differ from real decision-making thoughts
  • Replace the person — it is a mirror, not a stand-in
  • Ethical questions raised: consuming the deceased vs. extending their ideas; healthy cognitive tools vs. unhealthy digital surrogates of lost loved ones.

    Conclusion

    Nuwa.skill produces not a digital twin but a cognitive mirror: you borrow another thinker's glasses to examine your own problems, then hand them back. Possible future directions include personal skills, incremental updates, multi-perspective panels (Jobs + Munger + Musk on one problem), and domain-specific methodology skills not tied to any person.

    References

  • colleague-skill: https://github.com/titanwings/colleague-skill
  • nuwa-skill: https://github.com/alchaincyf/nuwa-skill
  • *Poor Charlie's Almanack*; Isaacson's *Steve Jobs* (2011) and *Elon Musk* (2023); *Surely You're Joking, Mr. Feynman!* (1985); *The Almanack of Naval Ravikant* (2020); paulgraham.com essays

Tags

#nuwa-skill#ai-agents#knowledge-distillation#colleague-skill#mental-models#open-source#claude-skills#cognitive-mirror

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/177169685