chuinb

Industry Mastery: Industry Crash Course Master

Transform from outsider to insider in hours, not months.

This skill creates immersive, research-backed learning experiences that make users feel like industry veterans. It combines proven learning methodologies with real-time web research to deliver knowledge that sticks.

Core Philosophy

The Three Pillars

┌─────────────────────────────────────────────────────────────────┐
│                    INDUSTRY MASTERY                             │
├─────────────────────────────────────────────────────────────────┤
│                                                                 │
│   🧠 FEYNMAN TECHNIQUE        ⚛️ FIRST PRINCIPLES               │
│   "If you can't explain       "Boil everything down             │
│    it simply, you don't        to fundamental truths,           │
│    understand it well enough"   then reason up from there"      │
│                                                                 │
│                    📊 80/20 PARETO                              │
│                    "20% of knowledge delivers                   │
│                     80% of practical value"                     │
│                                                                 │
└─────────────────────────────────────────────────────────────────┘

⚠️ CRITICAL: Execution Flow (MUST FOLLOW)

Overview

┌─────────────────────────────────────────────────────────────────┐
│                    EXECUTION FLOW                               │
├─────────────────────────────────────────────────────────────────┤
│                                                                 │
│  Phase 1: User Profiling ──────────────────────────────────     │
│           Ask 3 questions about goal, background, time          │
│                          ↓                                      │
│  Phase 2: Deep Research ───────────────────────────────────     │
│           WebSearch + WebFetch for content                      │
│                          ↓                                      │
│  Phase 3: Media Acquisition (MANDATORY) ───────────────────     │
│           Download images + videos + generate AI images         │
│                          ↓                                      │
│  Phase 4: Ask Save Path ───────────────────────────────────     │
│           Use AskUserQuestion to get save location              │
│                          ↓                                      │
│  Phase 5: Generate & Save ─────────────────────────────────     │
│           Create markdown file with embedded media              │
│                          ↓                                      │
│  Phase 6: Interactive Follow-up ───────────────────────────     │
│           Offer deep dives, practice scenarios                  │
│                                                                 │
└─────────────────────────────────────────────────────────────────┘

Phase 1: User Profiling (MANDATORY FIRST STEP)

Before ANY research begins, gather user context through conversational questions:

┌─────────────────────────────────────────────────────────────────┐
│  🎯 USER PROFILING QUESTIONS                                    │
├─────────────────────────────────────────────────────────────────┤
│                                                                 │
│  1. 「你的目标」What do you want to achieve?                    │
│     □ 社交谈资 (Casual conversation)                            │
│     □ 职业转型 (Career transition)                              │
│     □ 投资决策 (Investment decisions)                           │
│     □ 合作洽谈 (Business collaboration)                         │
│     □ 纯粹好奇 (Pure curiosity)                                 │
│                                                                 │
│  2. 「当前背景」What's your current profession/background?      │
│     (This helps tailor analogies and explanations)              │
│                                                                 │
│  3. 「时间预算」How much time can you invest?                   │
│     □ 30分钟速览 (Quick overview)                               │
│     □ 2小时深入 (Deep dive)                                     │
│     □ 持续学习 (Ongoing learning)                               │
│                                                                 │
└─────────────────────────────────────────────────────────────────┘

Present these questions conversationally, not as a form. Adapt based on context clues in the user's initial request.

Phase 2: Deep Research

Execute comprehensive web research covering:

Industry Fundamentals
- Core business models and value chains
- Key players (companies, organizations)
- Market size and growth trends
Key Figures & Events
- Influential people (founders, thought leaders, critics)
- Historical milestones and turning points
- Recent news and developments
Professional Vocabulary
- Industry jargon and acronyms
- Insider phrases and expressions
- Common misconceptions to avoid
Real Cases & Stories
- Success stories with specific details
- Notable failures and lessons learned
- Current controversies or debates

Research Tools:

Use WebSearch for current information, news, trends
Use WebFetch for detailed article content

2.1 Source Credibility Guardrails (MANDATORY)

Before organizing the research results, the following credibility constraints must be implemented:

Minimum number of sources: cite at least 5 valid sources
Source type mix(cover at least 2 categories):
- Official/regulatory/institutional reports (company financial reports, government, associations, consulting agencies)
- Mainstream media or industry media
- Professional research articles or high-quality databases
Time window requirements：
- At least 2 pieces of information from the most recent 12 months
- When involving "latest developments," prioritize sources from the most recent 90 days
Traceability: key conclusions must be followed by source links or source explanations

2.2 Conflict Handling Protocol

When conflicting information appears across different sources, follow this process:

Clearly list the points of conflict (e.g., market size, growth rate, key event dates)
Provide the source and time for each version
Explain possible reasons for the differences (statistical scope, regional coverage, time dimension)
Provide the "currently most credible conclusion + explanation of uncertainty"

2.3 Citation & Evidence Rules (MANDATORY)

Strictly prohibited to fabricate sources: when no credible source can be found, clearly write "no authoritative source support available at this time"
Key conclusions must be traceable: core viewpoints must be followed by [来源名, 日期] + 链接
Data must carry timestamps: information such as market size, growth rate, and rankings must indicate the statistical year

It is recommended to use the following format in the output:

### 关键结论与证据

1. 结论 A（置信度：高）
   - 证据 1: [来源名称, 2026-03-10](https://example.com)
   - 证据 2: [来源名称, 2025-11-22](https://example.com)
   - 备注: 不同机构口径略有差异，已按“全球口径”统一

2.4 Reference Module Routing

Select the minimum necessary reference files by topic to avoid overload:

Terminology and expression:references/jargon-patterns.md
Industry classification research framework:references/industry-templates.md
Learning method explanation:references/learning-theories.md

Only load the parts relevant to the current user's goal; there is no need to expand everything each time.

Phase 3: Media Acquisition (MANDATORY - DO NOT SKIP)

⚠️ THIS PHASE IS REQUIRED FOR EVERY EXECUTION

Media assets are the key to making study notes vivid and powerful.Mustexecute the media acquisition process, but the quantity and types should be flexibly adjusted according to content needs.

3.1 Media acquisition principles

Core principle: choose the most appropriate acquisition method according to the content type

┌─────────────────────────────────────────────────────────────────┐
│                    媒体获取决策树                                │
├─────────────────────────────────────────────────────────────────┤
│                                                                 │
│  需要什么类型的图片？                                            │
│       │                                                         │
│       ├─→ 事实性图片 ──→ 优先网络下载真实图片                    │
│       │   • 人物照片（创始人、专家、名人）                       │
│       │   • 产品图片、公司 Logo                                  │
│       │   • 剧照、海报、新闻配图                                 │
│       │   • 历史事件照片                                         │
│       │   • 实物图片（咖啡豆、芯片、汽车等）                     │
│       │                                                         │
│       └─→ 概念性图片 ──→ 使用 AI 生成                           │
│           • 价值链/生态系统图                                    │
│           • 流程图、关系图                                       │
│           • 抽象概念的视觉化                                     │
│           • 数据可视化、信息图                                   │
│           • 氛围图、风格示意图                                   │
│                                                                 │
└─────────────────────────────────────────────────────────────────┘

3.2 Media quantity guide (flexible adjustment)

No hard quantity limit is set, determined according to content richness and topic characteristics:

Content type	Suggested media configuration	Description
People-intensive (e.g., film reviews, business leaders)	3-5 portrait photos + 1-2 interview videos	Prioritize downloading real photos
Concept-intensive (e.g., finance, technology)	2-4 concept images + 1-2 explanatory videos	Prioritize AI generation
Case-intensive (e.g., business analysis)	2-3 case images + 1-2 flowcharts	Mixed use
Visual arts (e.g., film, design)	4-6 stills/artwork images + 1-2 clips	Prioritize downloading real images

3.3 Image acquisition strategy

Strategy A: factual images → prioritize online downloads

Applicable scenarios：

Portrait photos (founders, CEOs, experts, artists, directors, actors, etc.)
Product images, company logos, brand visuals
Movie stills, posters, album covers
News event images, historical photos
Physical object images (food, equipment, buildings, etc.)

How to obtain：

# 方式 1: 使用 media-downloader（需要 API Key）
python ~/.claude/skills/media-downloader/media_cli.py image "关键词" -n 数量 -o 输出目录

# 方式 2: 通过 WebSearch 找到图片 URL，然后下载
# 搜索关键词示例：
# "[人名] portrait photo"
# "[公司名] logo high resolution"
# "[电影名] movie poster"
# "[产品名] product image"

Search keyword templates：

人物照片:   "[姓名] portrait" / "[姓名] headshot" / "[姓名] photo"
公司Logo:   "[公司名] logo png" / "[公司名] brand"
电影海报:   "[电影名] movie poster" / "[电影名] official poster"
剧照:       "[电影名] still" / "[电影名] scene" / "[电影名] screenshot"
产品图:     "[产品名] product photo" / "[产品名] official image"

Strategy B: Conceptual images → Use AI generation

Applicable scenarios：

Industry value chains, ecosystem diagrams
Business process diagrams, workflows
Visual expression of abstract concepts
Relationship diagrams, hierarchy diagrams
Atmosphere images, style reference images
Fallback when no suitable real images can be found

Generate using zimage-skill：

MODELSCOPE_API_KEY="your-key" python3 ~/.claude/skills/zimage-skill/generate.py "prompt" "output.jpg"

Prompt templates：

# 流程图/价值链
"[主题] value chain diagram, minimalist infographic style, [color] color scheme,
professional business design, clean flat design, white background"

# 概念图
"[概念] concept visualization, modern illustration style, simple and clear,
professional corporate design"

# 氛围图
"[主题] aesthetic, cinematic atmosphere, [风格描述], professional photography style"

# 生态系统图
"[行业] ecosystem diagram, showing key players and relationships,
minimalist business infographic, clean design"

Strategy C: Fallback options

When all of the above methods fail:

Provide external links:[查看图片](url)
Use text descriptions instead
Use Mermaid diagrams (applicable to flowcharts)

3.4 Video acquisition strategy

Use media-downloader to download YouTube videos：

python ~/.claude/skills/media-downloader/media_cli.py youtube "URL" -o "输出目录" --end 120

Video types and search keywords：

Video type	Search keyword templates	Applicable scenarios
Explanatory videos	`"[概念] explained"`, `"how [X] works"`	Explanation of complex concepts
Introductory videos	`"[行业] 101"`, `"[行业] for beginners"`	Industry introduction
Character interviews	`"[人名] interview"`, `"[人名] talk"`	Character introductions
TED talks	`"[主题] TED talk"`	Thought inspiration
Documentary clips	`"[主题] documentary"`	In-depth content
News reports	`"[事件] news report"`	Current affairs cases

Video requirements：

Duration: flexibly trim based on content value (recommended 60-180 seconds)
Content: directly related to the topic
Quality: at least 720p

3.5 Media file naming conventions

人物照片:   person-[姓名拼音或英文].jpg
概念图:     diagram-[描述].jpg
剧照/海报:  poster-[作品名].jpg / still-[作品名].jpg
案例图:     case-[案例名].jpg
产品图:     product-[产品名].jpg
视频:       video-[主题].mp4

3.6 Media embedding format (Obsidian)

图片: ![[media/filename.jpg]]
视频: ![[media/filename.mp4]]
带说明: ![[media/filename.jpg|这是图片说明]]

3.7 Media acquisition checklist

After completing media acquisition, confirm:

All key people mentioned have corresponding images (real photos preferred)
Core concepts have visual expressions (AI-generated or real images)
At least 1 related video clip
The number of images and videos matches the richness of the content
All media files have been downloaded to the local media folder
File naming is clear and standardized

3.8 Media failure fallback strategy (MANDATORY)

When media acquisition fails, skipping directly is not allowed; fallback must be performed in order:

Factual image failure: Try an AI-generated substitute image, and clearly label it as an "AI-generated illustrative image"
AI image failure: Switch to Mermaid/ASCII diagrams or structured text descriptions
Video failure: Provide high-quality external links + a 60-120 second summary of key content

3.9 Copyright and compliance notice (MANDATORY)

Add in the document's "Further Reading" section or at the end:

Media source explanation (source platform/author/link)
Copyright status notice (for study reference only or commercially usable)
Commercial use risk reminder (it is recommended to prioritize reusable licensed materials)

Phase 4: Ask Save Path (MANDATORY)

⚠️ Before generating content, you must ask the user for the save path

Use AskUserQuestion The tool asks the user:

问题: "请告诉我你想把学习笔记保存到哪里？"

选项:
1. 当前目录 (Current directory)
2. 桌面 (Desktop)
3. 自定义路径 (Custom path)

If the user chooses a custom path:

Wait for the user to enter the full path
Verify whether the path exists; if not, create it

Default file structure:

[用户指定路径]/
├── [主题]速成指南.md          # 主文档
└── media/                      # 媒体文件夹
    ├── diagram-*.jpg
    ├── person-*.jpg
    ├── case-*.jpg
    └── video-*.mp4

Phase 5: Content Generation & Save

5.1 Output Structure Template

# [Industry/Field Name] 行业速成指南

> 🎯 **你的学习目标**: [Personalized based on user profile]
> ⏱️ **预计阅读时间**: X 分钟
> 📅 **生成日期**: YYYY-MM-DD

---

## 一句话看懂这个行业

[Feynman-style explanation in ONE sentence that a 12-year-old could understand]

---

## 第一性原理：行业的本质

[Break down to fundamental truths. What problem does this industry solve? Why does it exist?]

![[media/diagram-value-chain.jpg]]
*行业价值链图解*

### 核心价值链
[Visual diagram or clear explanation of how value flows]

### 关键驱动因素
[What makes this industry tick? 3-5 key factors]

---

## 行话速成：像内行人一样说话

| 术语 | 含义 | 使用场景 |
|------|------|----------|
| Term 1 | Meaning | When to use |
| Term 2 | Meaning | When to use |
| ... | ... | ... |

### 常用表达
- "[Insider phrase 1]" — 意思是...
- "[Insider phrase 2]" — 用于...

### 新手常犯的错误
- ❌ 不要说"..." → ✅ 应该说"..."

---

## 必知人物

### [Name 1] — [Title/Role]
> "[Famous quote]"

[Brief bio and why they matter]

### [Name 2] — [Title/Role]
...

---

## 经典案例

### 案例一：[Success/Failure Story Title]

**背景**: ...
**过程**: ...
**结果**: ...
**启示**: [Key takeaway in user's professional context]

![[media/case-example.jpg]]

---

## 精选视频片段

### [Video Title]
![[media/video-explanation.mp4]]
> 📌 **关键点**: [1-2 sentence summary of why this matters]

---

## 闪念卡片 (Flashcards)

<details>
<summary>🔮 点击展开卡片 1</summary>

**Q: [Question]**

---

**A: [Answer]**

</details>

[Generate 5-10 flashcards covering key concepts]

---

## 自测问答

### 问题 1
[Scenario-based question]

<details>
<summary>💡 查看答案</summary>

[Answer with explanation]

</details>

[Generate 3-5 quiz questions]

---

## 行动清单

基于你的目标「[user goal]」，建议的下一步：

- [ ] [Actionable item 1]
- [ ] [Actionable item 2]
- [ ] [Actionable item 3]

---

## 延伸阅读

- [Resource 1](url) — 推荐理由
- [Resource 2](url) — 推荐理由

---

> 💡 **学习小贴士**: [Personalized tip based on user's background]

5.2 Save Files

Create the media folder
Save all media files to the media folder
Save the main markdown file

5.3 Scenario Modes (Output Adaptation)

Automatically select the output focus based on the user's goal (mode can be explicitly declared):

mode=networking: Emphasize talking points, people, and hot topics
mode=interview: Emphasize high-frequency Q&A, structured expression, and case breakdowns
mode=investment: Emphasize business models, growth drivers, risks, and the competitive landscape
mode=learning: Emphasize the conceptual system, learning path, and memory cards

5.4 Output Quality Rubric (Self-check)

Before delivery, self-rate on a 1-5 scale and briefly strengthen weak areas:

Clarity (understandable to beginners)
Accuracy (credible and traceable sources)
Practicality (usable for meetings/interviews/investment discussions)
Memorability (quality of flashcards and quizzes)
Readability (structure, layout, correspondence between text and images)

If the total score is < 18, at least 2 low-scoring dimensions must be strengthened before delivery.

Phase 6: Interactive Elements

After delivering the main note, offer interactive follow-ups:

Deep Dive Options
- "Want to dive deeper into [specific topic]?"
- "Need more [cases/videos/terminology]?"
Practice Scenarios
- "Suppose you're in [scenario], and the other person asks you [question], how would you answer?"
- Provide feedback on user's responses
Knowledge Checks
- Generate additional flashcards on demand
- Create scenario-based quizzes
Connection Building
- "How does this relate to your [user's profession]?"
- Help user find bridges between new knowledge and existing expertise

Content Guidelines

Writing Style

Conversational yet professional — Like a knowledgeable friend explaining things
Rich in analogies — Connect new concepts to familiar ones (based on user's background)
Concrete over abstract — Always include specific examples, numbers, names
Visual thinking — Use diagrams, tables, and formatting liberally

Personalization Markers

Throughout the note, include personalized elements:

「结合你的[background]来理解」 — Bridge to user's expertise
「对于[goal]来说，关键是...」 — Goal-oriented framing
「这就像你熟悉的[analogy from user's field]」 — Familiar analogies

Quality Checklist

Before delivering the note, verify:

User profile questions were asked and answers incorporated
At least 5 web searches performed for current information
At least 5 valid references collected and traceable
At least 2 references are from the last 12 months
At least 2 source types covered (official/media/research)
Conflicting facts (if any) are explicitly reconciled
Minimum 3 real cases with specific details
10+ industry terms explained
2+ key figures profiled
5+ flashcards generated
3+ quiz questions created
Media acquisition complete：
- Factual images (people, stills, etc.) should preferably be real images downloaded from the internet
- Conceptual images (flowcharts, value chains) should be generated using AI
- The number of images should match the richness of the content (no hard limit)
- At least 1 relevant video clip
User was asked for save path before saving
Markdown file saved with embedded media
Media source and copyright/compliance note included
Output mode selected or inferred from user goal
Rubric self-check completed (target total >= 18)
Personalization markers present throughout
Actionable next steps provided

Tool Integration

Required Tools

Tool	Purpose	When to Use
`WebSearch`	Search industry information	Always used
`WebFetch`	Retrieve detailed webpage content	Always used
`zimage-skill`	Generate concept diagrams	Conceptual images (flowcharts, value chains, etc.)
`media-downloader`	Download images and videos	Factual images + YouTube videos
`AskUserQuestion`	Ask for the save path	Always used before saving

zimage-skill (AI image generation)

Function: Use AI to generate concept diagrams, flowcharts, etc.

How to use:

MODELSCOPE_API_KEY="your-key" python3 ~/.claude/skills/zimage-skill/generate.py "prompt" "output.jpg"

Prompt best practices:

"[主题] diagram/infographic, minimalist style, [color] color scheme,
professional design, clean flat design, white background"

media-downloader (media downloader)

Function: Download and trim YouTube videos