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 yunshu0909/yunshu_skillshub --skill multi-perspective-analysisgit clone --depth 1 https://github.com/yunshu0909/yunshu_skillshubWrote 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/yunshu0909/yunshu_skillshub/multi-perspective-analysis)<a href="https://agentmods.dev/skills/yunshu0909/yunshu_skillshub/multi-perspective-analysis"><img src="https://agentmods.dev/badge/skills/yunshu0909/yunshu_skillshub/multi-perspective-analysis/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/yunshu0909/yunshu_skillshub/multi-perspective-analysis"><img src="https://agentmods.dev/badge/skills/yunshu0909/yunshu_skillshub/multi-perspective-analysis.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 | $0.00094 | $0.04854 |
| Opus 5 | $0.00047 | $0.02427 |
| Sonnet 5 | $0.00019 | $0.00971 |
| Haiku 4.5 | $0.00009 | $0.00485 |
Grade A, and why
multi-perspective-analysis 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.
多视角深度分析
用 10 个独立的 Sub-agent 分别扮演全球最强大脑的"顾问"，对用户提供的素材做并行分析，然后交叉汇总产出结构化报告。
阵容：Dan Sullivan、马斯克、张小龙、MrBeast、芒格、蒂尔、乔布斯、贝佐斯、张一鸣、任正非
核心价值：独立分析但结论趋同时可信度极高，结论分歧时往往是最有价值的洞察。
流程概览
| 阶段 | 名称 | 目标 | 执行方式 |
|---|---|---|---|
| 1 | 收敛需求 | 搞清楚分析什么、为什么分析、用什么视角 | 对话 |
| 2 | 准备素材 | 整理分析素材，确认每个 agent 的输入 | 对话确认 |
| 3 | 并行分析 | 10 个 Sub-agent 各自独立分析，产出独立报告 | Agent 工具并行 |
| 4 | 交叉汇总 | 找共识、找分歧、提炼可执行建议 | 主对话 |
| 5 | 输出报告 | 结构化报告 + 可选：保存为文件 | 主对话 |
阶段 1：收敛需求
目标：搞清楚三件事——分析什么、为什么、用什么视角。
必须确认的信息
1. 分析对象
- 用户要分析什么？（一段时间的复盘数据、一个产品策略、一个商业方向、一个决策……）
- 有没有现成的素材文件？（如果有，让用户提供路径或内容）
2. 分析目的
- 用户想从分析中得到什么？（诊断问题、验证方向、发现盲区、做决策……）
- 有没有特别想回答的核心问题？
3. 视角选择
默认提供 10 个内置视角（见下方"内置视角库"）。用户可以：
- 用默认全部 10 个：适合全面诊断（"全球最聪明的 10 个大脑同时当你顾问"）
- 选其中 3-5 个：适合聚焦特定维度
- 自定义视角：用户指定其他思想家/框架，AI 通过 WebSearch 临时构建语料
如果用户不确定选什么，根据分析对象推荐：
| 分析对象类型 | 推荐视角 |
|---|---|
| 个人/创作者全面复盘 | 全部 10 个 |
| 产品策略 | 马斯克（第一性原理）+ 张小龙（产品直觉）+ 乔布斯（极致体验）+ 贝佐斯（客户至上） |
| 内容增长 | MrBeast（增长）+ 张小龙（需求真伪）+ 张一鸣（算法思维）+ 任正非（压强原则） |
| 商业决策 | 芒格（多元思维）+ 蒂尔（垄断思维）+ 贝佐斯（飞轮）+ Dan Sullivan（10x思维） |
| 职业方向 | Dan Sullivan（10x vs 2x）+ 马斯克（反共识）+ 蒂尔（秘密）+ 任正非（长期艰苦奋斗） |
| 竞争策略 | 任正非（压强原则 + 针尖战略）+ 蒂尔（垄断）+ 芒格（能力圈） |
| 战略复盘 | 任正非（华为的冬天 + 自我批判）+ 芒格（反过来想）+ 马斯克（第一性原理） |
收敛完成的标准
- 分析对象清楚（有素材或能描述清楚）
- 分析目的明确（至少有一个核心问题）
- 视角已确认
阶段 2：准备素材
目标：把用户提供的素材整理成每个 agent 可以直接使用的输入。
素材整理规则
- 如果用户给了文件路径：读取文件内容，整理为文本摘要
- 如果用户在对话中描述：提炼关键信息，形成结构化的"分析简报"
- 如果素材过长（超过 5000 字）：提取核心数据和关键事实，压缩为每个 agent 可消化的版本
每个 Agent 的输入包
每个 Sub-agent 收到的输入必须包含：
- 角色设定：你是 [思想家名字]，用 [框架名] 的方法论来分析
- 分析素材：[整理后的素材]
- 核心问题：用户最想回答的问题
- 框架参考：对应的 reference 文件的 完整原文
- 输出要求：
⚠️ 关于框架参考的硬性规则：
- 不要在主 prompt 中预注入 reference 全文——5 份语料全塞进 prompt 会超长，导致 agent 丢失或降级
- 改为：在每个 agent 的 prompt 中告诉它自己去读对应的 reference 文件
- 每个 agent 只读自己那一份，负担可控
- reference 文件中包含思想家的原话引用、具体案例、分析问题模板——agent 必须基于这些做分析
- 必须用该框架的核心概念和术语
- 必须给出明确的判断和建议，不要模棱两可
- 必须包含"最刺耳的一句话"——一个用户可能不想听但必须听的诊断
- 字数不限，该写多少写多少
- 语气：以该思想家的第一人称口吻，直接对用户说话
What ships with it
11 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.
- reference/_how-to-create-reference.md 5.3 KB
- reference/01-10x-growth-dan-sullivan.md 18 KB
- reference/02-first-principles-elon-musk.md 19 KB
- reference/03-product-intuition-zhang-xiaolong.md 20 KB
- reference/04-creator-growth-mrbeast.md 25 KB
- reference/05-mental-models-charlie-munger.md 20 KB
- reference/06-zero-to-one-peter-thiel.md 24 KB
- reference/07-product-vision-steve-jobs.md 29 KB
- reference/08-customer-obsession-jeff-bezos.md 26 KB
- reference/09-algorithm-thinking-zhang-yiming.md 21 KB
- reference/10-strategic-survival-ren-zhengfei.md 23 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.
- 11d ago First seen · 359 lines · 94 tokens per session scan A fc770d58e0e0
multi-perspective-analysis is a skill published in the GitHub repository yunshu0909/yunshu_skillshub (757 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 4,854 once invoked, about $0.0005 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…