A workflow for researching a person's ideas and turning the resulting thinking patterns into a usable agent skill. For unclear requests, it first identifies the kind of adviser the user needs; for a named person, it distills that person's mental models, decision rules, writing style, limits, and things to avoid.

Use it to create or update a skill based on a named person's way of thinking, or to develop a thinking adviser for a vague decision-making need.

It provides a structured way to create a perspective-based skill instead of copying quotations or surface-level mannerisms. It also makes the skill's boundaries and research depth explicit.

huashu-nuwa — Skill for Claude Code and Codex by masteryee-labs

Install

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.

Any agent

npx skills add masteryee-labs/Tool.Agent-Harness-Deploy --skill nuwa-skill

Clone the repo

git clone --depth 1 https://github.com/masteryee-labs/Tool.Agent-Harness-Deploy

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/masteryee-labs/tool.agent-harness-deploy/nuwa-skill/github.svg)](https://agentmods.dev/skills/masteryee-labs/tool.agent-harness-deploy/nuwa-skill)

Your own site

<a href="https://agentmods.dev/skills/masteryee-labs/tool.agent-harness-deploy/nuwa-skill"><img src="https://agentmods.dev/badge/skills/masteryee-labs/tool.agent-harness-deploy/nuwa-skill/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/masteryee-labs/tool.agent-harness-deploy/nuwa-skill"><img src="https://agentmods.dev/badge/skills/masteryee-labs/tool.agent-harness-deploy/nuwa-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 187 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 10,611 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin 94% copy Near-identical to another mod in the catalogue.

Token cost

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	$0.00187	$0.10611
Opus 5	$0.00093	$0.05306
Sonnet 5	$0.00037	$0.02122
Haiku 4.5	$0.00019	$0.01061

Measured 9d ago against content hash f6783dfa91ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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 9d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/download_subtitles.sh, scripts/merge_research.py, scripts/quality_check.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

This is a copy

94% identical to huashu-nuwa — 13 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.

core/assets/skills/nuwa-skill/SKILL.md · 672 lines

How it starts

The opening of the file, as written. The whole thing — 672 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。」
蒸馏档位：告知用户成本量级并确认档位。完整蒸馏是多agent+多轮搜索的长任务，顶级模型单次可消耗数十美元（真实用户案例），必须在开跑前说清楚：

档位	调研规模	适用场景	成本量级
快速	3个维度（著作+对话+表达），每维度限5个来源	先试试效果 / 冷门人物 / 预算敏感	约标准档1/3
标准（默认）	6个维度完整调研	大多数场景	中等；换更轻量模型可显著降低
深度	6维度 + 一手素材全量下载（书籍/字幕/长文存档）	打算开源发布的精品Skill	最高

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）+ 标准档，直接推进。

确认不阻塞交付：凡是能给默认值的问题都给默认值；如果下一步产出（访谈提纲、执行计划等）不依赖用户的答案，先给出产出再让用户调整。不要把现成的价值卡在提问之后。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

Read the full file on GitHub · 672 lines

Files

What ships with it

35 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.

Changes

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.

9d ago First seen · 672 lines · 187 tokens per session scan A f6783dfa91ae

Subscribe to this mod's changes

huashu-nuwa is a skill published in the GitHub repository masteryee-labs/Tool.Agent-Harness-Deploy (5 stars, last pushed 1mo ago), licensed MIT. It adds 187 tokens to every session and 10,611 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to huashu-nuwa, differing in 13 lines, and is treated as a copy.

Building agents Research agent-harness agent-memory agentic agents-md ai-agent ai-coding-assistant

dev-team

A virtual AI software company. The user is the client; the main agent of ANY agentic CLI host acts as the orchestrator-agent and runs a host-agnostic collaboration protocol — route the request into the backlog, collect every relevant role's perspective (round 1), share perspectives across a second turn (round 2)…

VictorTomaili/agent-cli · 176 tokens

huashu-nuwa