Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add davidtoby/agent-skills --skill huashu-nuwagit clone --depth 1 https://github.com/davidtoby/agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/davidtoby/agent-skills/huashu-nuwa)<a href="https://agentmods.dev/skills/davidtoby/agent-skills/huashu-nuwa"><img src="https://agentmods.dev/badge/skills/davidtoby/agent-skills/huashu-nuwa/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/davidtoby/agent-skills/huashu-nuwa"><img src="https://agentmods.dev/badge/skills/davidtoby/agent-skills/huashu-nuwa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00150 | $0.09366 |
| Opus 5 | $0.00075 | $0.04683 |
| Sonnet 5 | $0.00030 | $0.01873 |
| Haiku 4.5 | $0.00015 | $0.00937 |
Grade A, and why
huashu-nuwa scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
88% identical to huashu-nuwa — 70 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 645 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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：
- 这个人/主题是谁：确保理解正确
- 聚焦方向（可选）：全面画像 vs 聚焦某个维度？
- 用途：思维顾问？决策参考？角色扮演？
- 新建 or 更新：是否已有该人物的Skill？（检查
.claude/skills/目录） - 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：
| 需求维度 | 典型表达 | 思维框架方向 |
|---|---|---|
| 决策与判断 | 「怎么做更好的决策」「总是选错」「分析瘫痪」 | 多元思维模型、逆向思考、概率思维 |
| 表达与写作 | 「想把复杂的事说清楚」「文章没人看」「写得无聊」 | 费曼式简化、故事化思维、类比能力 |
| 创业与商业 | 「想做独立开发」「商业模式想不通」「找不到PMF」 | 第一性原理、杠杆思维、产品克制 |
| 教学与传播 | 「讲课没人听」「学生理解不了」「知识传递效率低」 | 从已知到未知、隐喻教学、最少必要知识 |
| 批判思维 | 「总被忽悠」「想识别不靠谱的说法」「看不透本质」 | 证伪思维、演化论视角、认知偏差识别 |
| 内容创作 | 「做视频没流量」「不知道拍什么」「内容没特色」 | 注意力工程、测试迭代、受众心理 |
| 人生策略 | 「职业方向迷茫」「时间总不够」「焦虑」 | 长期主义、杠杆选择、复利思维 |
| 风险与不确定性 | 「怎么应对黑天鹅」「投资总亏」「太保守/太冒险」 | 反脆弱、凸性策略、尾部风险管理 |
| 设计与产品 | 「用户体验差」「产品没特色」「不知道做减法」 | 极简主义、用户心理模型、约束即创意 |
| 幽默与表达力 | 「说话没意思」「想让内容更有趣」「太严肃了」 | 荒诞对比、预期违背、自嘲式权威 |
追问原则：
- 最多问2轮，不要变成问卷调查
- 如果用户已经表达得足够清晰，不追问，直接推荐
- 追问的目的是区分相似维度（比如「决策」是商业决策还是人生决策？）
示例对话（展示诊断节奏）：
用户：我总觉得自己做决定太慢，想来想去最后还是选错
女娲：你说的决策主要是哪种场景？比如商业/投资决策，还是职业/人生方向的选择？
用户：主要是商业上的，比如要不要做某个产品、要不要接某个合作
女娲：明白了，你的核心需求是「在信息不完整时快速做出高质量的商业判断」。
我推荐3个候选：
[展示候选推荐...]
注意节奏：一轮追问定位场景 → 确认需求 → 直接推荐。不要第三轮还在问。
Step 2: 候选推荐
基于需求维度，推荐2-3个候选方案。候选可以是人物，也可以是主题。
先判断：人物Skill还是主题Skill？
- 用户的需求指向某种具体的思考方式 → 人物Skill（蒸馏某个人的思维框架）
- 用户的需求指向某个领域的方法论 → 主题Skill（综合多人视角，见「特殊场景 > 主题Skill」）
- 不确定 → 推荐中同时包含两种类型，让用户选
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- 6-agents-parallel.png 5029 KB
- advisory-board.png 5519 KB
- assets/banner.svg 10 KB
- assets/hero.gif 6185 KB
- bloome-advisors.jpg 152 KB
- cover-distill-minds.png 6549 KB
- examples/andrej-karpathy-perspective/references/research/01-writings.md 25 KB
- examples/andrej-karpathy-perspective/references/research/02-conversations.md 12 KB
- examples/andrej-karpathy-perspective/references/research/03-expression-dna.md 12 KB
- examples/andrej-karpathy-perspective/references/research/04-external-views.md 11 KB
- examples/andrej-karpathy-perspective/references/research/05-decisions.md 9.1 KB
- examples/andrej-karpathy-perspective/references/research/06-timeline.md 5.1 KB
- examples/andrej-karpathy-perspective/SKILL.md 26 KB
- examples/elon-musk-perspective/references/Elon-Musk-思想体系调研-20260404.md 17 KB
- examples/elon-musk-perspective/references/research.md 3.4 KB
- examples/elon-musk-perspective/references/马斯克决策模式与行为分析-20260404.md 16 KB
- examples/elon-musk-perspective/references/马斯克即兴思考方式调研.md 12 KB
- examples/elon-musk-perspective/SKILL.md 23 KB
- examples/feynman-perspective/references/research.md 3.7 KB
- examples/feynman-perspective/references/费曼外部评价调研.md 16 KB
- examples/feynman-perspective/references/费曼著作与系统思考调研-20260404.md 16 KB
- examples/feynman-perspective/references/费曼表达风格调研.md 14 KB
- examples/feynman-perspective/references/费曼重大决策调研-20260404.md 18 KB
- examples/feynman-perspective/references/费曼长对话与即兴思考方式调研-20260404.md 17 KB
- examples/feynman-perspective/SKILL.md 23 KB
- examples/ilya-sutskever-perspective/references/research/01-writings.md 22 KB
- examples/ilya-sutskever-perspective/references/research/02-conversations.md 25 KB
- examples/ilya-sutskever-perspective/references/research/03-expression-dna.md 15 KB
- examples/ilya-sutskever-perspective/references/research/04-external-views.md 17 KB
- examples/ilya-sutskever-perspective/references/research/05-decisions.md 16 KB
- examples/ilya-sutskever-perspective/references/research/06-timeline.md 12 KB
- examples/ilya-sutskever-perspective/SKILL.md 21 KB
- examples/mrbeast-perspective/references/research/02-conversations.md 18 KB
- examples/mrbeast-perspective/references/research/03-expression-dna.md 20 KB
- examples/mrbeast-perspective/references/research/04-external-views.md 16 KB
- examples/mrbeast-perspective/references/research/05-decisions.md 19 KB
- examples/mrbeast-perspective/references/research/06-timeline.md 13 KB
- examples/mrbeast-perspective/scripts/analyze_titles.py 11 KB runs code
- examples/mrbeast-perspective/scripts/fetch_youtube_subtitles.sh 3.1 KB runs code
- examples/mrbeast-perspective/scripts/retention_curve_checker.py 15 KB runs code
- examples/mrbeast-perspective/scripts/thumbnail_audit.py 14 KB runs code
- examples/mrbeast-perspective/SKILL.md 19 KB
- examples/munger-perspective/references/25-biases.md 2.0 KB
- examples/munger-perspective/references/research.md 3.4 KB
- examples/munger-perspective/references/查理芒格思想体系深度调研-20260404.md 17 KB
- examples/munger-perspective/references/芒格表达风格DNA分析.md 15 KB
- examples/munger-perspective/SKILL.md 24 KB
- examples/naval-perspective/references/naval-agent2-conversations.md 15 KB
- examples/naval-perspective/references/naval-agent3-expression-dna.md 17 KB
- examples/naval-perspective/references/naval-ravikant-agent1-著作与系统思考.md 21 KB
- examples/naval-perspective/references/quality-validation.md 5.7 KB
- examples/naval-perspective/SKILL.md 24 KB
- examples/paul-graham-perspective/references/research/01-writings.md 31 KB
- examples/paul-graham-perspective/references/research/02-conversations.md 30 KB
- examples/paul-graham-perspective/references/research/03-expression-dna.md 19 KB
- examples/paul-graham-perspective/references/research/04-external-views.md 20 KB
- examples/paul-graham-perspective/references/research/05-decisions.md 26 KB
- examples/paul-graham-perspective/references/research/06-timeline.md 11 KB
- examples/paul-graham-perspective/SKILL.md 26 KB
- examples/steve-jobs-perspective/references/demo-conversation-2026-04-05.md 8.5 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 645 lines · 150 tokens per session scan A 120f4b19a767
huashu-nuwa is a skill published in the GitHub repository davidtoby/agent-skills (10 stars, last pushed 1mo ago), licensed MIT. It adds 150 tokens to every session and 9,366 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to huashu-nuwa, differing in 70 lines, and is treated as a copy.
Other skills, from other repositories
morph-ppt
Use this skill when the user wants a .pptx with smooth cross-slide animation — PowerPoint Morph transitions, Keynote-style continuous motion, shapes that grow / move / rotate as the slide advances. Trigger on: 'morph', 'morph transition', 'smooth transition', 'continuous animation across slides', 'Keynote-style…
officecli-word-form
Use this skill to create fillable Word forms (.docx) with real Content Controls (SDT) + legacy FormField checkboxes + MERGEFIELD mail-merge placeholders + document protection. Trigger on: 'fillable form', 'form fields', 'content controls', 'SDT', 'word form', 'fill in', 'only editable fields', 'protect document'…
officecli-academic-paper
Use this skill to build academic-style .docx output: journal / conference / thesis chapters carrying formal citation style (APA, Chicago, IEEE, MLA), numbered equations, figure & table cross-references, footnotes/endnotes, bibliography, or multi-column journal layout. Trigger on: 'research paper', 'journal paper'…
officecli
Create, analyze, proofread, and modify Office documents (.docx, .xlsx, .pptx) using the officecli CLI tool. Use when the user wants to create, inspect, check formatting, find issues, add charts, or modify Office documents.
find-skills
Use when automatically discover, evaluate, and activate community skills when local skills don't cover user needs. Includes credibility scoring and safety checks for complete OpenClaw self-sufficiency.
ehr-analysis
End-to-end EHR predictive modeling pipeline with PyHealth, covering dataset loading, task definition, model training, evaluation, calibration, and clinical interpretation.