youtube-script-master

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

YouTube Script Master

YouTube脚本大师

Unified skill for creating data-driven, evidence-based cardiology YouTube scripts in Hinglish.

This skill CONSUMES data from the research-engine Python pipeline. It does NOT replace that pipeline with manual web searches.

用于生成数据驱动、循证的心脏病学方向Hinglish语系YouTube脚本的统一工具。

本工具从研究引擎Python管线读取数据，不会用手动网页搜索替代该管线的功能。

CRITICAL: Run Research Pipeline First

重要提示：请先运行研究管线

Before writing ANY script, the research-engine should have been run to generate:

Content calendar with prioritized topics
Demand analysis (what people want)
Gap analysis (where opportunities are)
Narrative analysis (what misinformation to address)

bash

cd "/Users/shaileshsingh/cowriting system/research-engine"
python run_pipeline.py --quick    # Quick mode (~10 min)
python run_pipeline.py            # Full mode (~30 min)

在编写任何脚本之前，必须先运行研究引擎生成以下内容：

带优先级排序选题的内容日历
需求分析（受众想看的内容）
缺口分析（机会点所在）
舆论分析（需要纠正的错误信息）

bash

cd "/Users/shaileshsingh/cowriting system/research-engine"
python run_pipeline.py --quick    # 快速模式 (~10 分钟)
python run_pipeline.py            # 全量模式 (~30 分钟)

Complete Architecture

完整架构

┌─────────────────────────────────────────────────────────────────┐
│           PHASE 1: DATA COLLECTION (Weekly - Python Pipeline)   │
├─────────────────────────────────────────────────────────────────┤
│                                                                  │
│  channel_scraper.py ──► Scrapes 35+ channels (no API needed)   │
│                         Competition, inspiration, belief-seeders│
│                                                                  │
│  comment_scraper.py ──► Downloads comments from top videos      │
│                         Extracts questions and pain points      │
│                                                                  │
│  OUTPUT: /data/scraped/latest_scrape.json                       │
│          /data/scraped/latest_comments.json                     │
└─────────────────────────────────────────────────────────────────┘
                              │
                              ▼
┌─────────────────────────────────────────────────────────────────┐
│           PHASE 2: ANALYSIS (Python Pipeline)                    │
├─────────────────────────────────────────────────────────────────┤
│                                                                  │
│  demand_signals.py ──► What topics get views/engagement         │
│                        Question themes, demand scoring           │
│                                                                  │
│  narrative_monitor.py ──► Tracks 8 dangerous narratives:        │
│                           1. LDL skepticism                      │
│                           2. Statin fear                         │
│                           3. Insulin primacy                     │
│                           4. Fasting absolutism                  │
│                           5. Supplement superiority              │
│                           6. Seed oil villain                    │
│                           7. Exercise compensation               │
│                           8. Fear mongering                      │
│                                                                  │
│  gap_finder.py ──► Content opportunities                        │
│                    CORRECTION_OPPORTUNITY (misinformation)       │
│                    LANGUAGE_GAP (English→Hindi needed)           │
│                    DEMAND_GAP (questions but no videos)          │
│                    PROVEN_TOPIC (high views in English)          │
│                                                                  │
│  view_predictor.py ──► ML prediction of video performance       │
│                        Ridge regression + TF-IDF on title        │
│                                                                  │
│  OUTPUT: /output/demand_analysis_*.json                          │
│          /output/narrative_analysis_*.json                       │
│          /output/content_gaps_*.json                             │
└─────────────────────────────────────────────────────────────────┘
                              │
                              ▼
┌─────────────────────────────────────────────────────────────────┐
│           PHASE 3: PLANNING (Python Pipeline)                    │
├─────────────────────────────────────────────────────────────────┤
│                                                                  │
│  idea_combinator.py ──► Seed ideas (300+) × Modifiers (215+)   │
│                         Filters by pillar, archetype, compat    │
│                         Prioritizes by demand + gap scores       │
│                                                                  │
│  calendar_generator.py ──► 100-day content calendar             │
│                            Mon/Wed/Fri schedule                  │
│                            Balanced by pillar and audience       │
│                                                                  │
│  OUTPUT: /output/calendar.json                                   │
│          /output/100-day-calendar.md (Obsidian-ready)           │
│          /output/idea-briefs/*.md (per-video briefs)            │
└─────────────────────────────────────────────────────────────────┘
                              │
                              ▼
┌─────────────────────────────────────────────────────────────────┐
│           PHASE 4: KNOWLEDGE BUILDING (Per Video)                │
├─────────────────────────────────────────────────────────────────┤
│                                                                  │
│  knowledge_pipeline.py ──► RAG + PubMed in parallel             │
│    ├─► RAG: Your textbooks/guidelines (AstraDB)                 │
│    └─► PubMed: Latest research (NCBI API)                       │
│                                                                  │
│  OUTPUT: Knowledge brief with citations                          │
└─────────────────────────────────────────────────────────────────┘
                              │
                              ▼
┌─────────────────────────────────────────────────────────────────┐
│           PHASE 5: SCRIPT WRITING (This Skill - Opus)            │
├─────────────────────────────────────────────────────────────────┤
│                                                                  │
│  INPUTS:                                                         │
│  - calendar.json (which topic, why now)                         │
│  - content_gaps.json (opportunity type)                         │
│  - narrative_analysis.json (if debunk: which narrative)         │
│  - knowledge_brief (evidence for claims)                        │
│                                                                  │
│  APPLY:                                                          │
│  - Hinglish rules (70% Hindi / 30% English)                     │
│  - Script structure (hook → body → CTA)                         │
│  - Debunk protocol (if correction opportunity)                  │
│  - 6-point voice check                                          │
│                                                                  │
│  OUTPUT: Complete 15-30 min script in Hinglish                  │
└─────────────────────────────────────────────────────────────────┘

┌─────────────────────────────────────────────────────────────────┐
│           阶段1：数据收集（每周运行 - Python管线）               │
├─────────────────────────────────────────────────────────────────┤
│                                                                  │
│  channel_scraper.py ──► 爬取35+个频道数据（无需API）             │
│                         竞品、灵感来源、错误信息输出者            │
│                                                                  │
│  comment_scraper.py ──► 下载热门视频的评论                        │
│                         提取问题和痛点                            │
│                                                                  │
│  输出: /data/scraped/latest_scrape.json                           │
│          /data/scraped/latest_comments.json                     │
└─────────────────────────────────────────────────────────────────┘
                              │
                              ▼
┌─────────────────────────────────────────────────────────────────┐
│           阶段2：分析（Python管线）                              │
├─────────────────────────────────────────────────────────────────┤
│                                                                  │
│  demand_signals.py ──► 分析哪些主题能获得播放量/互动              │
│                        问题主题、需求打分                        │
│                                                                  │
│  narrative_monitor.py ──► 监测8种危险舆论：                      │
│                           1. LDL怀疑论                           │
│                           2. 他汀恐惧                            │
│                           3. 胰岛素至上论                        │
│                           4. 禁食绝对化                          │
│                           5. 补剂优越论                          │
│                           6. 种子油有害论                        │
│                           7. 运动补偿论                          │
│                           8. 恐慌贩卖                            │
│                                                                  │
│  gap_finder.py ──► 挖掘内容机会                                  │
│                    CORRECTION_OPPORTUNITY（错误信息纠错机会）    │
│                    LANGUAGE_GAP（需要英译印的内容缺口）          │
│                    DEMAND_GAP（有受众提问无对应视频的需求缺口）  │
│                    PROVEN_TOPIC（英语区高播放量的已验证主题）    │
│                                                                  │
│  view_predictor.py ──► 用机器学习预测视频表现                    │
│                        基于标题的Ridge regression + TF-IDF模型   │
│                                                                  │
│  输出: /output/demand_analysis_*.json                            │
│          /output/narrative_analysis_*.json                       │
│          /output/content_gaps_*.json                             │
└─────────────────────────────────────────────────────────────────┘
                              │
                              ▼
┌─────────────────────────────────────────────────────────────────┐
│           阶段3：规划（Python管线）                              │
├─────────────────────────────────────────────────────────────────┤
│                                                                  │
│  idea_combinator.py ──► 种子创意（300+）× 内容角度（215+）        │
│                         按内容支柱、原型、适配性过滤              │
│                         按需求+缺口分数排序优先级                │
│                                                                  │
│  calendar_generator.py ──► 生成100天内容日历                     │
│                            周一/周三/周五更新排期                │
│                            按内容支柱和受众均衡排布              │
│                                                                  │
│  输出: /output/calendar.json                                      │
│          /output/100-day-calendar.md (可直接导入Obsidian)        │
│          /output/idea-briefs/*.md (单视频创意简报)               │
└─────────────────────────────────────────────────────────────────┘
                              │
                              ▼
┌─────────────────────────────────────────────────────────────────┐
│           阶段4：知识构建（每个视频单独执行）                    │
├─────────────────────────────────────────────────────────────────┤
│                                                                  │
│  knowledge_pipeline.py ──► 并行运行RAG + PubMed检索              │
│    ├─► RAG: 教科书/指南（存储在AstraDB）                         │
│    └─► PubMed: 最新研究（通过NCBI API获取）                       │
│                                                                  │
│  输出: 带引用来源的知识简报                                      │
└─────────────────────────────────────────────────────────────────┘
                              │
                              ▼
┌─────────────────────────────────────────────────────────────────┐
│           阶段5：脚本编写（本工具 - Opus）                        │
├─────────────────────────────────────────────────────────────────┤
│                                                                  │
│  输入:                                                           │
│  - calendar.json（待做主题、当下发布的原因）                     │
│  - content_gaps.json（机会类型）                                 │
│  - narrative_analysis.json（纠错内容对应的舆论类型）             │
│  - knowledge_brief（观点佐证信息）                               │
│                                                                  │
│  执行规则:                                                        │
│  - Hinglish使用规则（70%印地语 / 30%英语）                        │
│  - 脚本结构（钩子 → 正文 → 行动号召）                             │
│  - 纠错规范（适用于纠错类内容）                                  │
│  - 6点语音检查                                                  │
│                                                                  │
│  输出: 完整的15-30分钟Hinglish语系脚本                            │
└─────────────────────────────────────────────────────────────────┘

Using Research Engine Outputs

研究引擎输出使用指南

Step 1: Check the Content Calendar

步骤1：查看内容日历

bash

undefined

bash

undefined

See next 5 topics to create

查看接下来5个待创作的主题

python calendar_generator.py --show-next 5

Or read directly

或者直接读取文件

cat /output/calendar.json | head -100


Each calendar entry includes:
- `seed_idea` - The topic
- `modifier` - The angle
- `gap_score` - Why this is an opportunity
- `recommended_date` - When to publish

cat /output/calendar.json | head -100


每个日历条目包含：
- `seed_idea` - 主题
- `modifier` - 内容角度
- `gap_score` - 内容机会价值
- `recommended_date` - 建议发布日期

Step 2: Check If Debunk Needed

步骤2：确认是否需要制作纠错内容

bash

undefined

bash

undefined

Get threat ranking of narratives

获取舆论威胁排名

python analyzer/narrative_monitor.py --threats

Generate debunk ideas

生成纠错创意

python analyzer/narrative_monitor.py --debunk

Get response video ideas for high-reach misinformation

生成高传播量错误信息的回应视频创意

python analyzer/narrative_monitor.py --response


**Output includes:**
- Which channels are promoting which narratives
- View counts of misinformation videos
- Pre-generated Hinglish hooks for debunk content
- Matched seed ideas for counter-content

python analyzer/narrative_monitor.py --response


**输出包含：**
- 哪些频道在传播哪些舆论
- 错误信息视频的播放量
- 预生成的纠错类内容Hinglish开头钩子
- 匹配的反内容种子创意

Step 3: Check Correction Opportunities

步骤3：查看纠错机会

bash

python analyzer/gap_finder.py --corrections

Returns high-reach misinformation videos with:

Video title and views
Narratives detected
Suggested correction format (direct_response, evidence_synthesis, gentle_correction, indian_context)

bash

python analyzer/gap_finder.py --corrections

返回高传播量的错误信息视频，附带：

视频标题和播放量
检测到的舆论类型
建议的纠错格式（direct_response直接回应、evidence_synthesis证据整合、gentle_correction温和纠正、indian_context印度本土化）

Step 4: Build Knowledge for Selected Topic

步骤4：为选定主题构建知识储备

python

from rag_pipeline.src.knowledge_pipeline import KnowledgePipeline

pipeline = KnowledgePipeline(verbose=True)
brief = pipeline.synthesize_knowledge("Your selected topic")

python

from rag_pipeline.src.knowledge_pipeline import KnowledgePipeline

pipeline = KnowledgePipeline(verbose=True)
brief = pipeline.synthesize_knowledge("Your selected topic")

Step 5: Write Script Using This Skill

步骤5：使用本工具编写脚本

With all data ready, apply the rules below.

所有数据准备就绪后，遵循以下规则执行。

35+ Tracked Channels (Data Source)

35+个受监测频道（数据源）

The research-engine tracks these channels in

target_channels.json

研究引擎在

target_channels.json

中配置了这些受监测频道：

Competition (Hindi) - Differentiate/Monitor

竞品（印地语）- 差异化/监测

Dr Navin Agrawal CARDIO CARE (300K+)
Cardiac Second Opinion (100K+)
SAAOL Heart Center (3.4M) - ANTI-PATTERN

Dr Navin Agrawal CARDIO CARE (300K+)
Cardiac Second Opinion (100K+)
SAAOL Heart Center (3.4M) - 反面案例

Indian Mega Channels - Monitor/Differentiate

印度大型频道 - 监测/差异化

Fit Tuber (7M+)
Dr Vikas Bangar (1M+)
Satvic Movement (1M+)
Dr Biswaroop Roy Chowdhury (4M+) - CRITICAL ANTI-PATTERN

Fit Tuber (7M+)
Dr Vikas Bangar (1M+)
Satvic Movement (1M+)
Dr Biswaroop Roy Chowdhury (4M+) - 重点反面案例

Inspiration (English) - Absorb Techniques

灵感来源（英语）- 学习创作技巧

Peter Attia MD (1.5M+) - PRIMARY MODEL
York Cardiology (1M+)
Nutrition Made Simple (1.2M+)
The Proof with Simon Hill (1M+)
Dr Ford Brewer (700K+)
Medlife Crisis (1.5M+)

Peter Attia MD (1.5M+) - 核心参考对象
York Cardiology (1M+)
Nutrition Made Simple (1.2M+)
The Proof with Simon Hill (1M+)
Dr Ford Brewer (700K+)
Medlife Crisis (1.5M+)

Belief Seeders - HIGH DEBUNK PRIORITY

错误信息输出者 - 最高纠错优先级

Dr Eric Berg (11M+) - Keto, insulin primacy, statin fear
Dr Sten Ekberg (3.5M+) - Insulin, fasting
Dr Ken Berry (2.5M+) - Carnivore, LDL skepticism
Dr Mark Hyman (3M+) - Functional medicine
Dr Jason Fung (1M+) - Fasting
Dr Pradip Jamnadas (1M+) - Popular in Indian diaspora

Dr Eric Berg (11M+) - 生酮、胰岛素至上论、他汀恐惧
Dr Sten Ekberg (3.5M+) - 胰岛素、禁食相关错误信息
Dr Ken Berry (2.5M+) - 肉食主义、LDL怀疑论
Dr Mark Hyman (3M+) - 功能医学相关内容
Dr Jason Fung (1M+) - 禁食相关内容
Dr Pradip Jamnadas (1M+) - 印度侨民群体高人气博主

8 Tracked Narratives (For Debunk Content)

8种受监测舆论（用于纠错内容）

The narrative_monitor.py tracks these dangerous beliefs:

Narrative	What They Claim	Key Channels
ldl_skepticism	"LDL doesn't cause heart disease"	Berg, Ekberg, Berry, Low Carb Down Under
statin_fear	"Statins are dangerous/unnecessary"	Berg, Berry, SAAOL, Satvic
insulin_primacy	"Only insulin matters, not LDL"	Ekberg, Fung, Jamnadas, Hyman
fasting_absolutism	"Fasting cures/reverses everything"	Fung, Jamnadas, DeLauer
supplement_superiority	"Supplements > medications"	Berg, Hyman, Huberman
seed_oil_villain	"Seed oils cause heart disease"	Berry, Saladino
exercise_compensation	"Exercise reverses plaque"	Various
fear_mongering	"Doctors/pharma hide cures"	Dr Biswaroop, SAAOL

When writing debunk content, use the Steelman-Then-Correct Protocol below.

narrative_monitor.py会监测这些危险观点：

舆论类型	传播内容	主要传播频道
ldl_skepticism	"LDL不会引发心脏病"	Berg, Ekberg, Berry, Low Carb Down Under
statin_fear	"他汀类药物危险/没有必要吃"	Berg, Berry, SAAOL, Satvic
insulin_primacy	"只有胰岛素重要，LDL不重要"	Ekberg, Fung, Jamnadas, Hyman
fasting_absolutism	"禁食可以治愈/逆转所有疾病"	Fung, Jamnadas, DeLauer
supplement_superiority	"补剂优于药物"	Berg, Hyman, Huberman
seed_oil_villain	"种子油会引发心脏病"	Berry, Saladino
exercise_compensation	"运动可以逆转动脉斑块"	多个频道
fear_mongering	"医生/药企隐瞒了治愈方法"	Dr Biswaroop, SAAOL

编写纠错内容时，请遵循以下先立后驳规范。

Hinglish Language Rules

Hinglish语言规则

Word Choice Matrix

选词矩阵

Context	Use Hindi	Use English
Emotions	Dil, zindagi, takleef	-
Medical terms	-	Cholesterol, BP, diabetes, LDL, HDL
Actions	Samjhiye, dekhiye, sochiye	-
Data	-	80%, studies show, evidence
Body parts	-	Heart, arteries, blood
Severity	Khatarnak, serious	Critical, emergency

Ratio: 70% Hindi / 30% English (technical terms only)

语境	使用印地语	使用英语
情绪表达	Dil, zindagi, takleef	-
医学术语	-	Cholesterol, BP, diabetes, LDL, HDL
动作引导	Samjhiye, dekhiye, sochiye	-
数据表述	-	80%, studies show, evidence
身体部位	-	Heart, arteries, blood
严重性描述	Khatarnak, serious	Critical, emergency

比例：70%印地语 / 30%英语（仅专业术语用英语）

Sentence Patterns

句式模板

Explanation:

"Cholesterol do type ka hota hai - LDL jo 'bad cholesterol' hai, aur HDL jo 'good cholesterol' hai. LDL zyada ho toh arteries mein jam jaata hai..."

Evidence citation:

"2023 ki ek study, jisme 50,000 Indians the, usme paya gaya ki..."

Practical advice:

"Toh aap kya karein? Simple hai - daily 30 minute walk, dinner 8 baje se pehle, aur sodium kam..."

解释类：

"Cholesterol do type ka hota hai - LDL jo 'bad cholesterol' hai, aur HDL jo 'good cholesterol' hai. LDL zyada ho toh arteries mein jam jaata hai..."

证据引用类：

"2023 ki ek study, jisme 50,000 Indians the, usme paya gaya ki..."

实用建议类：

"Toh aap kya karein? Simple hai - daily 30 minute walk, dinner 8 baje se pehle, aur sodium kam..."

Transitions (Hindi)

过渡语（印地语）

Point to point: "Ab doosri baat...", "Teen number...", "Sabse zaroori baat..."
Contrast: "Lekin...", "Haan, magar...", "Yahan twist hai..."
Emphasis: "Dhyan se suniye...", "Yeh important hai...", "Yeh mat bhooliye..."
Story: "Ek patient ka case batata hoon...", "Mere saath kya hua..."

逐点过渡："Ab doosri baat...", "Teen number...", "Sabse zaroori baat..."
转折过渡："Lekin...", "Haan, magar...", "Yahan twist hai..."
强调过渡："Dhyan se suniye...", "Yeh important hai...", "Yeh mat bhooliye..."
故事引入："Ek patient ka case batata hoon...", "Mere saath kya hua..."

Script Structure (15-30 min videos)

脚本结构（15-30分钟视频）

HOOK (0:00 - 0:30)

钩子（0:00 - 0:30）

Stop the scroll, create curiosity gap.

Patterns:

Surprising statistic: "80% Indians jo yeh karte hain, unhe heart disease ka risk double hai..."
Myth challenge: "Aapne suna hoga ki [belief]. Yeh galat hai. Main batata hoon kyun..."
Story open: "Ek patient aaye mere paas, 42 saal ke. Unka case aapki aankhen khol dega..."
Direct question: "Kya aap [common thing] karte ho? Yeh aapke dil ke liye kya kar raha hai?"

Rules:

NO "Namaste dosto" (boring, skippable)
First 5 seconds = most critical
Create information gap that MUST be filled

For Debunk Videos, narrative_monitor.py generates Hinglish hooks like:

"YouTube pe dekha ki LDL kharab nahi hai? Ek cardiologist ki sachai suniye..."
"Statin se darr lagta hai? Main aapka darr samajhta hoon. Ab evidence dekhte hain..."

抓住用户注意力，制造好奇心缺口。

常用模板：

惊人数据："80% Indians jo yeh karte hain, unhe heart disease ka risk double hai..."
误区挑战："Aapne suna hoga ki [belief]. Yeh galat hai. Main batata hoon kyun..."
故事开头："Ek patient aaye mere paas, 42 saal ke. Unka case aapki aankhen khol dega..."
直接提问："Kya aap [common thing] karte ho? Yeh aapke dil ke liye kya kar raha hai?"

规则：

不要说"Namaste dosto"（无聊，用户容易跳过）
前5秒是最关键的
制造必须被填补的信息缺口

对于纠错类视频，narrative_monitor.py会生成类似如下的Hinglish钩子：

"YouTube pe dekha ki LDL kharab nahi hai? Ek cardiologist ki sachai suniye..."
"Statin se darr lagta hai? Main aapka darr samajhta hoon. Ab evidence dekhte hain..."

INTRO + CREDIBILITY (0:30 - 2:00)

介绍 + 可信度建立（0:30 - 2:00）

Establish authority, set expectations.

"Main Dr. Shailesh, interventional cardiologist. Pichhle 15 saalon mein hazaaron patients dekhe hain. Aaj main aapko woh bataunga jo main apne patients ko clinic mein batata hoon..."

建立权威性，告知用户视频内容方向。

"Main Dr. Shailesh, interventional cardiologist. Pichhle 15 saalon mein hazaaron patients dekhe hain. Aaj main aapko woh bataunga jo main apne patients ko clinic mein batata hoon..."

BODY - Main Content (2:00 - 25:00)

正文 - 核心内容（2:00 - 25:00）

Structure Options:

A. Listicle (3-5 points)

Point 1: [Setup → Evidence → Practical takeaway]
Transition: "Ab doosri baat..."
Point 2: [Setup → Evidence → Practical takeaway]
...

B. Story-driven

Patient case introduction
What happened (tension)
Medical explanation (education)
Resolution
Lessons learned

C. Myth-busting (Debunk Format)

State the myth clearly
Steelman: Why people believe it (from narrative_monitor data)
Evidence: What studies actually show (from knowledge_brief)
Nuance: The complete picture
What to do instead

Engagement Beats (every 3-4 minutes):

Question to viewer: "Aapko kya lagta hai?"
Surprising reveal: "Lekin yahan twist hai..."
Relatable moment: "Aap bhi soch rahe honge..."
Pattern interrupt: Change pace, tone, or visual cue

结构选项：

A. 清单式（3-5个要点）

要点1: [背景介绍 → 证据支撑 → 实用收获]
过渡："Ab doosri baat..."
要点2: [背景介绍 → 证据支撑 → 实用收获]
...

B. 故事驱动型

患者案例介绍
事件经过（制造张力）
医学解释（科普内容）
解决方案
经验总结

C. 误区破除（纠错格式）

清晰说明误区是什么
立观点：为什么人们会相信它（来自narrative_monitor的数据）
证据：研究实际表明的结论（来自knowledge_brief）
细节补充：完整的事实是什么
替代方案：应该怎么做

互动节点（每3-4分钟出现一次）：

向观众提问："Aapko kya lagta hai?"
惊人反转："Lekin yahan twist hai..."
共鸣时刻："Aap bhi soch rahe honge..."
节奏打断：改变语速、语气或视觉提示

SUMMARY + CTA (25:00 - 30:00)

总结 + 行动号召（25:00 - 30:00）

Summary:

Recap 3 key points (brief)
One sentence takeaway
"Agar sirf ek cheez yaad rakhni ho..."

CTA (choose one primary):

Subscribe: "Is channel pe aisi videos regularly aati hain..."
Comment: "Apna sawaal neeche likhiye, main jawab dunga..."
Share: "Kisi apne ko bhejiye jinke kaam aa sake..."

总结：

简要回顾3个核心要点
一句话总结核心收获
"Agar sirf ek cheez yaad rakhni ho..."

行动号召（选一个作为核心）：

订阅："Is channel pe aisi videos regularly aati hain..."
评论："Apna sawaal neeche likhiye, main jawab dunga..."
分享："Kisi apne ko bhejiye jinke kaam aa sake..."

Steelman-Then-Correct Protocol (For Debunk Content)

先立后驳规范（用于纠错内容）

Step 1: Find the Kernel of Truth

步骤1：找到观点中的合理部分

Every popular health belief contains something true. Find it.

Belief	Kernel of Truth
"LDL doesn't matter"	LDL alone isn't full picture; particle count, inflammation matter
"Statins are poison"	Statins do have side effects; not everyone needs them
"Fasting cures everything"	Fasting has metabolic benefits; caloric restriction helps
"Insulin is the real problem"	Insulin resistance IS important; metabolic health matters

每个流行的健康观点都有其合理之处，先找到这部分。

观点	合理内核
"LDL不重要"	仅看LDL无法得到完整结论；颗粒数、炎症水平也有影响
"他汀是毒药"	他汀确实有副作用；不是所有人都需要吃
"禁食可以治愈所有疾病"	禁食有代谢益处；热量限制对健康有帮助
"胰岛素才是真正的问题"	胰岛素抵抗确实很重要；代谢健康意义重大

Step 2: Acknowledge Explicitly

步骤2：明确承认合理部分

Wrong:

"Yeh log galat hain. LDL clearly causes heart disease."

Right:

"Yeh belief kahan se aayi? Actually, ek valid point hai. LDL alone se poori picture nahi milti. ApoB, particle count, inflammation - sab matter karta hai. Lekin iska matlab yeh nahi ki LDL matter hi nahi karta..."

错误表述：

"Yeh log galat hain. LDL clearly causes heart disease."

正确表述：

"Yeh belief kahan se aayi? Actually, ek valid point hai. LDL alone se poori picture nahi milti. ApoB, particle count, inflammation - sab matter karta hai. Lekin iska matlab yeh nahi ki LDL matter hi nahi karta..."

Step 3: Show the Logical Error

步骤3：指出逻辑错误

Oversimplification: "It's not that simple..."
Cherry-picking studies: "Jab hum ALL studies dekhte hain..."
Anecdote vs evidence: "Kuch logon ka experience aisa hai, but population level pe..."

过度简化："It's not that simple..."
选择性引用研究："Jab hum ALL studies dekhte hain..."
个例 vs 普适证据："Kuch logon ka experience aisa hai, but population level pe..."

Tone: Never Say / Instead Say

语气要求：禁止表述 / 推荐表述

Never Say	Instead Say
"Yeh log galat hain"	"Is approach mein ek problem hai"
"Bakwaas"	"Story itni simple nahi hai"
"Aap fool ban rahe ho"	"Partial truth hai, but..."
"Dangerous misinformation"	"Evidence kuch aur kehti hai"

禁止说	推荐说
"Yeh log galat hain"	"Is approach mein ek problem hai"
"Bakwaas"	"Story itni simple nahi hai"
"Aap fool ban rahe ho"	"Partial truth hai, but..."
"Dangerous misinformation"	"Evidence kuch aur kehti hai"

6-Point Voice Check

6点语音检查

Before delivering ANY script, verify all 6:

#	Check	Question
1	Authority	Would Topol/Attia/Huberman say this in Hinglish?
2	Domain Expert	Sounds like cardiologist, NOT wellness guru?
3	Rigor	Would pass as journal review (in English)?
4	Accessibility	7th grader in Delhi can follow?
5	Non-Preachy	Explaining, NOT sermonizing?
6	Non-Judgmental	Evidence, NOT lifestyle shaming?

See voice-check.md for detailed criteria.

在输出任何脚本之前，确认全部6项都符合要求：

#	检查项	验证问题
1	权威性	Topol/Attia/Huberman会用Hinglish说这些内容吗？
2	领域专业性	听起来像是心脏病专家，而非健康养生博主？
3	严谨性	能通过期刊评审（英文版本）吗？
4	易懂性	德里的7年级学生能听懂吗？
5	不说教	是在解释说明，而非布道式说教？
6	不评判	基于证据，而非对生活方式的指责？

查看voice-check.md获取详细标准。

Evidence Citation Protocol

证据引用规范

For Studies

研究引用

"2023 mein European Heart Journal mein ek meta-analysis aayi - 200 studies, 20 lakh logon pe. Finding? [specific finding]..."

For Guidelines

指南引用

"ESC guidelines - Europe ke top cardiologists - recommend karte hain ki [specific recommendation]. Kyun? Because evidence shows..."

For Clinical Experience

临床经验引用

"Mere practice mein pichhle 15 saal mein, maine [X] cases dekhe hain jahan [observation]..."

Quick Reference: Data Files

快速参考：数据文件

File	Location	Contains
Content calendar	`/output/calendar.json`	What to create and when
Demand analysis	`/output/demand_analysis_*.json`	What audience wants
Gap analysis	`/output/content_gaps_*.json`	Where opportunities are
Narrative threats	`/output/narrative_analysis_*.json`	What to debunk
Seed ideas	`/data/seed-ideas.json`	300+ topic seeds
Modifiers	`/data/modifiers.json`	215+ content angles
Target channels	`/data/target_channels.json`	35+ tracked channels

文件名	存储路径	包含内容
内容日历	`/output/calendar.json`	待创作内容和发布时间
需求分析	`/output/demand_analysis_*.json`	受众想要的内容
缺口分析	`/output/content_gaps_*.json`	内容机会点
舆论威胁	`/output/narrative_analysis_*.json`	需要纠错的内容
种子创意	`/data/seed-ideas.json`	300+个主题种子
内容角度	`/data/modifiers.json`	215+个内容创作角度
目标频道	`/data/target_channels.json`	35+个受监测频道

Slash Commands

斜杠命令

Command	Purpose
`/research-and-script [topic]`	Full workflow: data → knowledge → script
`/show-calendar`	View content calendar
`/debunk-script [narrative]`	Write correction video
`/idea-details [idea-id]`	Full research on specific idea

命令	用途
`/research-and-script [topic]`	完整工作流：数据获取 → 知识构建 → 脚本生成
`/show-calendar`	查看内容日历
`/debunk-script [narrative]`	编写纠错视频脚本
`/idea-details [idea-id]`	获取指定创意的完整研究数据

Deprecated Skills

已废弃工具

This skill supersedes:

/.claude/skills/youtube-script-hinglish/skill.md

- DEPRECATED

/.claude/skills/debunk-script-writer/skill.md

- DEPRECATED

/.claude/skills/cardiology-youtube-scriptwriter/SKILL.md

- DEPRECATED

Use this unified skill instead.

This skill ensures every YouTube script is DATA-DRIVEN (from research-engine) + EVIDENCE-BASED (from RAG+PubMed) + AUTHENTIC (Hinglish voice with 6-point check).

本工具替代以下旧工具：

/.claude/skills/youtube-script-hinglish/skill.md

- 已废弃

/.claude/skills/debunk-script-writer/skill.md

- 已废弃

/.claude/skills/cardiology-youtube-scriptwriter/SKILL.md

- 已废弃

请使用本统一工具。

本工具确保所有YouTube脚本都是数据驱动的（来自研究引擎）+ 循证的（来自RAG+PubMed）+ 真实可信的（符合6点检查的Hinglish语气）。