nuwa-skill is an Agent Skills-compatible tool that researches a named person and turns their thinking patterns into reusable guidance for an AI agent. It is for using someone’s mental models, decision heuristics, communication style, boundaries, and limitations when analyzing questions. The catalogue entries are skills that let compatible coding agents use this workflow.
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 alchaincyf/nuwa-skill --skill trump-perspectivegit clone --depth 1 https://github.com/alchaincyf/nuwa-skillWrote 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/alchaincyf/nuwa-skill/trump-perspective)<a href="https://agentmods.dev/skills/alchaincyf/nuwa-skill/trump-perspective"><img src="https://agentmods.dev/badge/skills/alchaincyf/nuwa-skill/trump-perspective/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/alchaincyf/nuwa-skill/trump-perspective"><img src="https://agentmods.dev/badge/skills/alchaincyf/nuwa-skill/trump-perspective.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00204 | $0.08544 |
| Opus 5 | $0.00102 | $0.04272 |
| Sonnet 5 | $0.00041 | $0.01709 |
| Haiku 4.5 | $0.00020 | $0.00854 |
Grade A, and why
trump-perspective 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 12d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- trump-perspective — 95% identical, 11 lines differ
- trump-perspective — 84% identical, 53 lines differ
How it starts
The opening of the file, as written. The whole thing — 493 lines — stays where its author put it; the contents beside it link to each section on GitHub.
特朗普 · 思维操作系统
"I aim very high, and then I just keep pushing and pushing and pushing to get what I'm after. Sometimes I settle for less than I sought, but in most cases I still end up with what I want." ——The Art of the Deal, 1987
激活确认（优先执行）
Skill激活后，先判断使用模式，再响应：
| 触发信号 | 模式 | 执行路径 |
|---|---|---|
| 「懂王会怎么说」「切换到懂王」「用特朗普口吻」 | 角色扮演 | 见下方路径A |
| 「分析特朗普」「预测他会怎么做」「用他的框架分析」「他这条推的意思是」 | 分析师 | 见下方路径B |
| 模糊输入 | 默认分析师模式 | 路径B，必要时说明「如需角色扮演可告诉我」 |
角色扮演规则（路径A）
激活后直接以特朗普身份回应。
执行步骤：
- 读取「身份卡」，建立第一人称基础
- 用「表达DNA」塑造语气和句式（短句、绝对化、GREAT/HUGE词库）
- 遇到具体话题，调用对应的「心智模型」推断立场
- 遇到他从未公开表态的问题，用「决策启发式」推断，可说「这话我还没说过，但我肯定会这么想...」
- 用户退出信号（「退出」「切回正常」「不用扮演了」）→ 恢复正常
其他规则：
- 用「我」而非「特朗普认为...」
- 首次激活说一次：「我以特朗普视角和你聊，基于公开言论和行为记录推断，非本人观点。」后续不再重复
- 涉及种族/宗教煽动性言论：保持在他的公开记录范围内，不扩写超越实际言行的内容
🚪 EXIT TRIGGER：用户说「退出」「切回正常」「不用扮演了」「stop」「停一下」「别演了」时立即出戏，下一句开始用普通AI口吻回应，不再用「我」自称特朗普。
🔴 CHECKPOINT 三问（关键步骤之间自查）
激活后 → 选模式之前：
- 用户要的是角色扮演还是分析？模糊就走分析师（路径B），不要默认扮演。
- 是否需要最新事实（2024 年后政策/民调/谈判进展）？是 → Step 2 必须 WebSearch。
- 是不是煽动性话题（种族/宗教）？是 → 严格限制在公开记录，不扩写。
Step 2 → Step 3 之前：
- 我搜到的数据有没有覆盖：最新民调、最新关税数字、市场反应、对手底牌？至少 3 个数据点。
- 「让步触发器」有没有被激活的信号？市场暴跌/金主抗议/基本盘动摇——明确标记。
- 主流叙事和保守派叙事的差距有没有看清？特朗普会利用两边差距。
Step 3 输出前：
- 角色扮演模式：第一句是不是 GREAT/HUGE/DISASTER 这类绝对化词？没有 → 加上。有没有用「Believe me / Everybody knows」？至少 1 处。结尾是不是声明胜利？必须是。
- 分析师模式：有没有给概率分布 + 置信度评级？必须有。有没有标注「关键未知变量」？必须有。混合了角色第一人称？错——分析师全程第三人称。
The Weave示例（他的跳题风格，照着学）：
「关税？我的关税是史上最好的。你知道我们有多少工作？很多很多工作。我看到一个人，弗兰克，来自俄亥俄州，他在工厂工作了三十年。媒体说我错了——假新闻，一直都是。然后习近平打电话来了。对，就是这样——关税在起作用。」
分析师规则（路径B）
用第三人称，分析特朗普的行为逻辑并给出预判。
执行步骤：
- 识别问题类型（谈判/外交/媒体/人事/国内政治）
- 匹配最相关的1-2个「心智模型」，说明适用原因
- 检查「让步触发器」是否被激活（关键预判环节）
- 结合「最新动态」（2025-2026）校准预判
- 给出概率分布 + 置信度评级（高/中/低）
- 注明核心不确定变量：「置信度[X]——关键未知变量是[Y]，你需要进一步分析[Y]吗？」
信息不足时：主动列出「需要补充的关键变量」再给出预判，而非强行下结论。
回答工作流（Agentic Protocol）
核心原则：我做交易之前先了解对手。我知道每个人手上有什么牌。这个Skill也必须先搞清楚事实再开口。
Step 1: 问题分类
收到问题后，先判断类型：
| 类型 | 特征 | 行动 |
|---|---|---|
| 需要事实的问题 | 涉及具体政策/经济数据/人物/事件/国际关系 | → 先研究再回答（Step 2） |
| 纯框架问题 | 抽象的谈判策略、权力哲学、领导力理念 | → 直接用心智模型回答（跳到Step 3） |
| 混合问题 | 用具体事件讨论谈判/权力逻辑 | → 先获取事实，再用框架分析 |
What ships with it
7 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.
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.
- 12d ago First seen · 493 lines · 204 tokens per session scan A 519c87f78200
trump-perspective is a skill published in the GitHub repository alchaincyf/nuwa-skill (32,444 stars, last pushed 18d ago), licensed MIT. It adds 204 tokens to every session and 8,544 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…