This automates the creation of perspective skills by distilling someone's thinking patterns into a runnable skill file. Feed it a name like "芒格" or a vague request like "improve my decision making" and it spins up six parallel research agents that comb through writings, interviews, social media, critics, decisions, and timelines. Two independent agents cross-validate the extracted mental models and decision heuristics, then it builds the skill with full source citations and runs adversarial tests to check consistency, boundary awareness, and voice distinctiveness. The whole pipeline takes 30-60 minutes and outputs a complete skill plus research archive. It's overkill for casual use but makes sense if you're building a library of thinking frameworks or need rigorous sourcing for advisory personas.

skills.sh installs
178
GitHub stars
8
last updated
Jun 3, 2026

Install

$ npx -y skills add kylefu8/nuwa-openclaw-skill --skill nuwa --agent claude-code

Installs into .claude/skills of the current project.

Files

女娲 · 思维蒸馏术

捕捉 HOW they think,不是 WHAT they said。

导航

  • 方法论 → references/extraction-framework.md
  • 产出模板 → references/skill-template.md
  • 搜索脚本 → scripts/search.sh(Tavily 不可用时的 fallback)

Phase 0: 入口分流

输入类型路径
明确人名("蒸馏芒格")→ Phase 1
模糊需求("提升决策质量")→ 搜索推荐 1-3 人选,自主选最佳 → Phase 1
主题("X运营方法论")→ Phase 1(主题模式,见方法论)

Phase 1: 六路并行调研

创建输出目录 {outputDir}/research/,用 sessions_spawn 起 6 个 subagent 并行:

#维度产出搜索词示例
1著作/长文01-writings.md"[人名] book/著作/essay"
2播客/访谈02-interviews.md"[人名] interview/podcast/演讲"
3社交媒体03-social.md"[人名] twitter/X/知乎/公众号"
4批评者视角04-critics.md"[人名] criticism/争议/wrong"
5关键决策05-decisions.md"[人名] decision/为什么[事件]"
6人生时间线06-timeline.md"[人名] biography/经历/timeline"

Sponsors

Details

Repository
github.com/kylefu8/nuwa-openclaw-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