AI Marketing Skills Automation

AI营销技能自动化

Skill by ara.so — Marketing Skills collection.

This project provides battle-tested marketing automation workflows — not prompts, but complete Python scripts with scoring algorithms, expert panels, and automation pipelines. Built for Claude Code and other AI coding agents to execute real marketing operations.

由ara.so开发的技能集——营销技能合集。

本项目提供经过实战检验的营销自动化工作流——并非提示词，而是包含评分算法、专家评审机制和自动化管道的完整Python脚本。专为Claude Code及其他AI编码Agent打造，用于执行真实的营销运营任务。

What It Does

功能介绍

AI Marketing Skills gives you 15+ categories of marketing automation:

Growth Engine: Autonomous experiments with statistical testing
Sales Pipeline: Website visitor → qualified pipeline automation
Content Ops: Quality scoring and production workflows
Outbound Engine: ICP definition to cold emails
SEO Ops: Content gap analysis and keyword research
Finance Ops: AI CFO for cost analysis
Revenue Intelligence: Sales call insights and attribution
Conversion Ops: CRO audits and lead magnet generation
Podcast Ops: Episode → multi-platform content
Sales Playbook: Value-based pricing frameworks
Autoresearch: Evolutionary content optimization
Deck Generator: AI slide deck creation
YT Competitive Analysis: YouTube outlier detection
X Long-Form: Human-sounding X/Twitter posts

AI营销技能集为您提供15+类营销自动化能力：

Growth Engine：具备统计测试的自主实验
Sales Pipeline：网站访客→合格线索自动化
Content Ops：内容质量评分与生产工作流
Outbound Engine：理想客户画像（ICP）定义至冷邮件发送
SEO Ops：内容差距分析与关键词研究
Finance Ops：AI CFO成本分析
Revenue Intelligence：销售通话洞察与归因
Conversion Ops：转化率优化（CRO）审计与引流磁铁生成
Podcast Ops：播客剧集→多平台内容转化
Sales Playbook：基于价值的定价框架
Autoresearch：进化式内容优化
Deck Generator：AI幻灯片生成
YT Competitive Analysis：YouTube异常检测
X Long-Form：类人风格的X/Twitter长文

Installation

安装步骤

bash

undefined

bash

undefined

Clone the repository

克隆仓库

git clone https://github.com/ericosiu/ai-marketing-skills.git cd ai-marketing-skills

Navigate to a specific skill category

进入特定技能分类目录

cd growth-engine # or sales-pipeline, content-ops, etc.

cd growth-engine # 或 sales-pipeline、content-ops等

Install dependencies for that category

安装该分类的依赖

pip install -r requirements.txt

Set up environment variables

设置环境变量

cp .env.example .env

undefined

cp .env.example .env

undefined

Configuration

配置说明

Each category uses a

.env

file for API keys and configuration:

bash

undefined

每个分类使用

.env

文件存储API密钥和配置信息：

bash

undefined

Common environment variables across skills

各技能通用环境变量

ANTHROPIC_API_KEY=your_anthropic_key_here OPENAI_API_KEY=your_openai_key_here

Growth Engine specific

Growth Engine专属配置

GOOGLE_ANALYTICS_KEY=your_ga_key LINKEDIN_API_KEY=your_linkedin_key

Sales Pipeline specific

Sales Pipeline专属配置

RB2B_API_KEY=your_rb2b_key INSTANTLY_API_KEY=your_instantly_key APOLLO_API_KEY=your_apollo_key

SEO Ops specific

SEO Ops专属配置

GOOGLE_SEARCH_CONSOLE_CREDENTIALS=path/to/credentials.json

Revenue Intelligence specific

Revenue Intelligence专属配置

GONG_API_KEY=your_gong_key SALESFORCE_API_KEY=your_salesforce_key

undefined

GONG_API_KEY=your_gong_key SALESFORCE_API_KEY=your_salesforce_key

undefined

Growth Engine

Run autonomous marketing experiments with statistical rigor.

运行具备统计严谨性的自主营销实验。

Experiment Engine

实验引擎

python

from experiment_engine import ExperimentEngine

python

from experiment_engine import ExperimentEngine

Initialize the engine

初始化引擎

engine = ExperimentEngine( api_key=os.getenv("ANTHROPIC_API_KEY"), data_source="google_analytics" )

Create an experiment

创建实验

experiment = engine.create_experiment( hypothesis="Thread posts get 2x engagement vs single posts", variable="format", variants=["thread", "single"], metric="impressions", duration_days=14, traffic_split=0.5 )

experiment = engine.create_experiment( hypothesis="Thread帖子的互动量是单条帖子的2倍", variable="format", variants=["thread", "single"], metric="impressions", duration_days=14, traffic_split=0.5 )

Run the experiment

运行实验

results = engine.run_experiment(experiment.id)

Get statistical significance

获取统计显著性

analysis = engine.analyze_results( experiment.id, confidence_level=0.95, test_method="mann_whitney" )

print(f"Winner: {analysis['winner']}") print(f"P-value: {analysis['p_value']}") print(f"Confidence: {analysis['confidence_interval']}")

undefined

analysis = engine.analyze_results( experiment.id, confidence_level=0.95, test_method="mann_whitney" )

print(f"获胜变体: {analysis['winner']}") print(f"P值: {analysis['p_value']}") print(f"置信区间: {analysis['confidence_interval']}")

undefined

Pacing Alerts

投放节奏预警

python

from pacing_alert import PacingMonitor

monitor = PacingMonitor(
    budget_monthly=10000,
    platform="linkedin"
)

python

from pacing_alert import PacingMonitor

monitor = PacingMonitor(
    budget_monthly=10000,
    platform="linkedin"
)

Check daily pacing

检查每日投放节奏

alert = monitor.check_pacing( spend_to_date=3500, days_elapsed=8, days_in_month=30 )

if alert['status'] == 'overpacing': print(f"Alert: Overpacing by {alert['variance_percent']}%") print(f"Recommended daily spend: ${alert['recommended_daily']}")

undefined

alert = monitor.check_pacing( spend_to_date=3500, days_elapsed=8, days_in_month=30 )

if alert['status'] == 'overpacing': print(f"预警: 投放超支{alert['variance_percent']}%") print(f"建议每日投放金额: ${alert['recommended_daily']}")

undefined

CLI Usage

CLI使用方式

bash

undefined

bash

undefined

Create experiment

创建实验

python experiment-engine.py create
--hypothesis "Carousel posts outperform static images"
--variable post_type
--variants '["carousel", "static"]'
--metric engagement_rate
--duration 14

python experiment-engine.py create
--hypothesis "轮播帖子表现优于静态图片"
--variable post_type
--variants '["carousel", "static"]'
--metric engagement_rate
--duration 14

Check pacing

检查投放节奏

python pacing-alert.py check
--budget 10000
--spend 3500
--days-elapsed 8

Generate weekly scorecard

生成每周评分卡

python autogrowth-weekly-scorecard.py generate
--start-date 2026-05-01
--end-date 2026-05-07

undefined

python autogrowth-weekly-scorecard.py generate
--start-date 2026-05-01
--end-date 2026-05-07

undefined

Sales Pipeline

Turn anonymous website visitors into qualified pipeline.

将匿名网站访客转化为合格销售线索。

RB2B Router

RB2B路由工具

python

from rb2b_instantly_router import RB2BRouter

router = RB2BRouter(
    rb2b_key=os.getenv("RB2B_API_KEY"),
    instantly_key=os.getenv("INSTANTLY_API_KEY")
)

python

from rb2b_instantly_router import RB2BRouter

router = RB2BRouter(
    rb2b_key=os.getenv("RB2B_API_KEY"),
    instantly_key=os.getenv("INSTANTLY_API_KEY")
)

Fetch website visitors from RB2B

从RB2B获取网站访客数据

visitors = router.fetch_visitors( lookback_hours=24, min_intent_score=7 )

Route to Instantly campaigns

将访客导入Instantly营销活动

for visitor in visitors: # Score and enrich enriched = router.enrich_visitor(visitor)

# Route based on criteria
if enriched['seniority'] in ['C-Level', 'VP', 'Director']:
    router.add_to_campaign(
        email=enriched['email'],
        campaign_id="high-intent-vp",
        personalization={
            'company': enriched['company'],
            'trigger': enriched['page_visited']
        }
    )

undefined

for visitor in visitors: # 评分并丰富访客信息 enriched = router.enrich_visitor(visitor)

# 根据条件路由
if enriched['seniority'] in ['C-Level', 'VP', 'Director']:
    router.add_to_campaign(
        email=enriched['email'],
        campaign_id="high-intent-vp",
        personalization={
            'company': enriched['company'],
            'trigger': enriched['page_visited']
        }
    )

undefined

Deal Resurrector

沉睡线索激活工具

python

from deal_resurrector import DealResurrector

resurrector = DealResurrector(
    crm_api_key=os.getenv("SALESFORCE_API_KEY")
)

python

from deal_resurrector import DealResurrector

resurrector = DealResurrector(
    crm_api_key=os.getenv("SALESFORCE_API_KEY")
)

Find stale deals with departed champions

查找关键联系人已离职的沉睡线索

stale_deals = resurrector.find_stale_deals( days_inactive=90, min_deal_value=10000 )

Track champions to new companies

追踪关键联系人的新任职公司

for deal in stale_deals: champion_moves = resurrector.track_champion( champion_email=deal['primary_contact'], linkedin_api_key=os.getenv("LINKEDIN_API_KEY") )

if champion_moves['new_company']:
    resurrector.create_new_opportunity(
        company=champion_moves['new_company'],
        contact=champion_moves['new_email'],
        context=deal['previous_context']
    )

undefined

for deal in stale_deals: champion_moves = resurrector.track_champion( champion_email=deal['primary_contact'], linkedin_api_key=os.getenv("LINKEDIN_API_KEY") )

if champion_moves['new_company']:
    resurrector.create_new_opportunity(
        company=champion_moves['new_company'],
        contact=champion_moves['new_email'],
        context=deal['previous_context']
    )

undefined

ICP Learner

理想客户画像（ICP）学习工具

python

from icp_learning_analyzer import ICPLearner

learner = ICPLearner()

python

from icp_learning_analyzer import ICPLearner

learner = ICPLearner()

Analyze win/loss patterns

分析赢单/丢单模式

deals = learner.fetch_closed_deals(months_back=12) patterns = learner.analyze_patterns(deals)

Update ICP definition

更新ICP定义

new_icp = learner.update_icp( current_icp=""" Company size: 50-500 employees Industry: SaaS, E-commerce Tech stack: React, Python """, win_loss_data=patterns )

print(new_icp)

undefined

new_icp = learner.update_icp( current_icp=""" 公司规模: 50-500名员工行业: SaaS、电商技术栈: React、Python """, win_loss_data=patterns )

print(new_icp)

undefined

Content Ops

Ship content that scores 90+ every time.

每次产出评分90+的内容。

Expert Panel

专家评审机制

python

from expert_panel import ExpertPanel

panel = ExpertPanel(
    api_key=os.getenv("ANTHROPIC_API_KEY")
)

python

from expert_panel import ExpertPanel

panel = ExpertPanel(
    api_key=os.getenv("ANTHROPIC_API_KEY")
)

Load expert personas

加载专家角色

panel.load_experts([ 'experts/seo_expert.json', 'experts/conversion_expert.json', 'experts/content_strategist.json' ])

Score content

评分内容

content = """ Your blog post content here... """

scores = panel.score_content( content=content, rubric='scoring-rubrics/blog_post.json', min_score=90 )

content = """ 你的博客文章内容... """

scores = panel.score_content( content=content, rubric='scoring-rubrics/blog_post.json', min_score=90 )

Recursive improvement

迭代优化

while scores['average'] < 90: feedback = panel.get_improvement_suggestions(scores) content = panel.improve_content(content, feedback) scores = panel.score_content(content, 'scoring-rubrics/blog_post.json')

print(f"Final score: {scores['average']}") print(f"Expert breakdown: {scores['by_expert']}")

undefined

while scores['average'] < 90: feedback = panel.get_improvement_suggestions(scores) content = panel.improve_content(content, feedback) scores = panel.score_content(content, 'scoring-rubrics/blog_post.json')

print(f"最终评分: {scores['average']}") print(f"专家评分明细: {scores['by_expert']}")

undefined

Quality Gate

质量审核关卡

bash

undefined

bash

undefined

CLI quality gate

CLI质量审核

python quality-gate.py check
--file blog-post.md
--rubric scoring-rubrics/blog_post.json
--min-score 90
--experts seo conversion content-strategy

undefined

python quality-gate.py check
--file blog-post.md
--rubric scoring-rubrics/blog_post.json
--min-score 90
--experts seo conversion content-strategy

undefined

Outbound Engine

ICP to inbox automation.

从ICP定义到收件箱的自动化流程。

Cold Outbound Optimizer

冷触达优化工具

python

from cold_outbound_optimizer import OutboundEngine

engine = OutboundEngine(
    apollo_key=os.getenv("APOLLO_API_KEY"),
    instantly_key=os.getenv("INSTANTLY_API_KEY")
)

python

from cold_outbound_optimizer import OutboundEngine

engine = OutboundEngine(
    apollo_key=os.getenv("APOLLO_API_KEY"),
    instantly_key=os.getenv("INSTANTLY_API_KEY")
)

Define ICP

定义ICP

icp = { 'titles': ['VP Marketing', 'CMO', 'Head of Growth'], 'company_size': [50, 500], 'industries': ['SaaS', 'E-commerce'], 'technologies': ['HubSpot', 'Salesforce'] }

Build lead list

构建线索列表

leads = engine.build_lead_list( icp=icp, limit=1000, exclude_domains=['competitor1.com', 'competitor2.com'] )

Generate personalized emails

生成个性化邮件

for lead in leads: email = engine.generate_email( lead=lead, template='references/cold_email_template.md', personalization_depth='high' )

engine.add_to_sequence(
    email=lead['email'],
    campaign='q2-outbound',
    message=email
)

undefined

for lead in leads: email = engine.generate_email( lead=lead, template='references/cold_email_template.md', personalization_depth='high' )

engine.add_to_sequence(
    email=lead['email'],
    campaign='q2-outbound',
    message=email
)

undefined

SEO Ops

Find keywords your competitors missed.

发现竞争对手遗漏的关键词。

Content Attack Brief

内容攻击简报

python

from content_attack_brief import SEOBrief

brief = SEOBrief(
    gsc_credentials=os.getenv("GOOGLE_SEARCH_CONSOLE_CREDENTIALS")
)

python

from content_attack_brief import SEOBrief

brief = SEOBrief(
    gsc_credentials=os.getenv("GOOGLE_SEARCH_CONSOLE_CREDENTIALS")
)

Analyze content gaps

分析内容差距

gaps = brief.find_content_gaps( target_domain='yoursite.com', competitor_domains=['competitor1.com', 'competitor2.com'], topic='marketing automation' )

Generate brief

生成简报

content_brief = brief.generate_brief( keyword=gaps[0]['keyword'], search_intent=gaps[0]['intent'], top_ranking_urls=gaps[0]['serp_results'] )

print(content_brief)

undefined

content_brief = brief.generate_brief( keyword=gaps[0]['keyword'], search_intent=gaps[0]['intent'], top_ranking_urls=gaps[0]['serp_results'] )

print(content_brief)

undefined

GSC Optimizer

GSC优化工具

bash

undefined

bash

undefined

CLI GSC optimization

CLI GSC优化

python gsc_client.py analyze
--domain yoursite.com
--lookback-days 90
--min-impressions 1000
--position-range 11-20

undefined

python gsc_client.py analyze
--domain yoursite.com
--lookback-days 90
--min-impressions 1000
--position-range 11-20

undefined

Finance Ops

AI CFO for cost analysis.

用于成本分析的AI CFO工具。

CFO Briefing

CFO简报

python

from cfo_briefing import FinanceAnalyzer

analyzer = FinanceAnalyzer()

python

from cfo_briefing import FinanceAnalyzer

analyzer = FinanceAnalyzer()

Upload financial data

上传财务数据

analyzer.load_data( expenses='data/expenses_q1.csv', revenue='data/revenue_q1.csv' )

Generate CFO briefing

生成CFO简报

briefing = analyzer.generate_briefing( focus_areas=['hidden_costs', 'vendor_optimization', 'budget_variance'] )

Get cost-saving recommendations

获取成本节约建议

recommendations = analyzer.find_savings_opportunities( min_impact=5000 # Minimum $5k annual savings )

print(briefing) for rec in recommendations: print(f"{rec['category']}: Save ${rec['annual_savings']:,.0f}")

undefined

recommendations = analyzer.find_savings_opportunities( min_impact=5000 # 年度最低节约5000美元 )

print(briefing) for rec in recommendations: print(f"{rec['category']}: 预计年度节约${rec['annual_savings']:,.0f}")

undefined

Revenue Intelligence

Sales call insights and attribution.

销售通话洞察与归因分析。

Gong Insight Pipeline

Gong洞察管道

python

from gong_insight_pipeline import GongAnalyzer

analyzer = GongAnalyzer(
    gong_api_key=os.getenv("GONG_API_KEY")
)

python

from gong_insight_pipeline import GongAnalyzer

analyzer = GongAnalyzer(
    gong_api_key=os.getenv("GONG_API_KEY")
)

Fetch recent calls

获取近期通话记录

calls = analyzer.fetch_calls( date_range='last_7_days', min_duration_minutes=20 )

Extract insights

提取洞察信息

for call in calls: insights = analyzer.extract_insights(call['id'])

# Key patterns
print(f"Objections: {insights['objections']}")
print(f"Competitor mentions: {insights['competitors']}")
print(f"Next steps: {insights['next_steps']}")

# Update CRM
analyzer.sync_to_crm(
    call_id=call['id'],
    insights=insights,
    crm='salesforce'
)

undefined

for call in calls: insights = analyzer.extract_insights(call['id'])

# 关键模式
print(f"客户异议: {insights['objections']}")
print(f"竞争对手提及: {insights['competitors']}")
print(f"后续步骤: {insights['next_steps']}")

# 更新CRM
analyzer.sync_to_crm(
    call_id=call['id'],
    insights=insights,
    crm='salesforce'
)

undefined

Troubleshooting

故障排除

API Rate Limits

API速率限制

python

undefined

python

undefined

All scripts include retry logic with exponential backoff

所有脚本均包含指数退避重试逻辑

from utils import retry_with_backoff

@retry_with_backoff(max_retries=5, base_delay=2) def api_call(): return client.make_request()

undefined

from utils import retry_with_backoff

@retry_with_backoff(max_retries=5, base_delay=2) def api_call(): return client.make_request()

undefined

PII Sanitization

PII数据清理

bash

undefined

bash

undefined

Scan for sensitive data before commits

提交前扫描敏感数据

python3 security/sanitizer.py --scan --dir . --recursive

Install pre-commit hook

安装提交前钩子

cp security/pre-commit-hook.sh .git/hooks/pre-commit chmod +x .git/hooks/pre-commit

undefined

cp security/pre-commit-hook.sh .git/hooks/pre-commit chmod +x .git/hooks/pre-commit

undefined

Dependencies Issues

依赖问题

bash

undefined

bash

undefined

Each category has isolated dependencies

每个分类有独立的依赖

cd growth-engine pip install --upgrade -r requirements.txt

If conflicts, use virtual environment

若存在冲突，使用虚拟环境

python -m venv venv source venv/bin/activate # or venv\Scripts\activate on Windows pip install -r requirements.txt

undefined

python -m venv venv source venv/bin/activate # Windows系统使用 venv\Scripts\activate pip install -r requirements.txt

undefined

Data Privacy

数据隐私

All scripts sanitize PII by default:

python

from security.sanitizer import sanitize_output

所有脚本默认会清理PII数据：

python

from security.sanitizer import sanitize_output

Automatically removes emails, phone numbers, API keys

自动移除邮箱、电话号码、API密钥等敏感信息

safe_data = sanitize_output(raw_data)

undefined

safe_data = sanitize_output(raw_data)

undefined

Common Patterns

通用模式

Chain Multiple Skills

串联多个技能

python

undefined

python

undefined

Example: SEO → Content → Quality Gate → Publish

示例: SEO → 内容生成 → 质量审核 → 发布

from content_attack_brief import SEOBrief from expert_panel import ExpertPanel

1. Get SEO brief

1. 获取SEO简报

brief = SEOBrief().generate_brief(keyword='ai marketing automation')

2. Generate content

2. 生成内容

content = generate_from_brief(brief) # Your content generation

content = generate_from_brief(brief) # 您的内容生成逻辑

3. Score with expert panel

3. 专家评审评分

panel = ExpertPanel() scores = panel.score_content(content, min_score=90)

4. Publish if passed

4. 评分达标则发布

if scores['average'] >= 90: publish_to_cms(content)

undefined

if scores['average'] >= 90: publish_to_cms(content)

undefined

Telemetry (Opt-In)

遥测（可选启用）

bash

undefined

bash

undefined

View local usage stats

查看本地使用统计

python3 telemetry/telemetry_report.py

Check for updates

检查更新

python3 telemetry/version_check.py

Opt out of remote telemetry (local logging still works)

退出远程遥测（本地日志仍保留）

export AI_MARKETING_SKILLS_TELEMETRY=false

undefined

export AI_MARKETING_SKILLS_TELEMETRY=false

undefined

Project Structure

项目结构

ai-marketing-skills/
├── growth-engine/          # Experiments, pacing, scorecards
├── sales-pipeline/         # RB2B, deal resurrector, ICP learner
├── content-ops/            # Expert panel, quality gates
├── outbound-engine/        # Cold email automation
├── seo-ops/                # Content gaps, GSC analysis
├── finance-ops/            # CFO briefings, cost analysis
├── revenue-intelligence/   # Gong insights, attribution
├── conversion-ops/         # CRO audits, lead magnets
├── podcast-ops/            # Episode → content pipeline
├── sales-playbook/         # Value pricing frameworks
├── autoresearch/           # Evolutionary content optimization
├── deck-generator/         # AI slide decks
├── yt-competitive-analysis/ # YouTube outlier detection
└── x-longform-post/        # Human-sounding X posts

Each category contains:

```
SKILL.md
```
— Category-specific skill documentation
```
scripts/
```
— Python automation scripts
```
requirements.txt
```
— Dependencies
```
.env.example
```
— Configuration template
```
README.md
```
— Category guide

ai-marketing-skills/
├── growth-engine/          # 实验、投放节奏、评分卡
├── sales-pipeline/         # RB2B、沉睡线索激活、ICP学习工具
├── content-ops/            # 专家评审、质量审核
├── outbound-engine/        # 冷邮件自动化
├── seo-ops/                # 内容差距分析、GSC分析
├── finance-ops/            # CFO简报、成本分析
├── revenue-intelligence/   # Gong洞察、归因分析
├── conversion-ops/         # CRO审计、引流磁铁
├── podcast-ops/            # 播客剧集→内容转化管道
├── sales-playbook/         # 价值定价框架
├── autoresearch/           # 进化式内容优化
├── deck-generator/         # AI幻灯片生成
├── yt-competitive-analysis/ # YouTube异常检测
└── x-longform-post/        # 类人风格的X长文

每个分类包含：

```
SKILL.md
```
— 分类专属技能文档
```
scripts/
```
— Python自动化脚本
```
requirements.txt
```
— 依赖列表
```
.env.example
```
— 配置模板
```
README.md
```
— 分类使用指南

ai-marketing-skills-automation

Original

Translation

AI Marketing Skills Automation

AI营销技能自动化

What It Does

功能介绍

Installation

安装步骤

Clone the repository

克隆仓库

Navigate to a specific skill category

进入特定技能分类目录

Install dependencies for that category

安装该分类的依赖

Set up environment variables

设置环境变量

Configuration

配置说明

Common environment variables across skills

各技能通用环境变量

Growth Engine specific

Growth Engine专属配置

Sales Pipeline specific

Sales Pipeline专属配置

SEO Ops specific

SEO Ops专属配置

Revenue Intelligence specific

Revenue Intelligence专属配置

Growth Engine

Growth Engine

Experiment Engine

实验引擎

Initialize the engine

初始化引擎

Create an experiment

创建实验

Run the experiment

运行实验

Get statistical significance

获取统计显著性

Pacing Alerts

投放节奏预警

Check daily pacing

检查每日投放节奏

CLI Usage

CLI使用方式

Create experiment

创建实验

Check pacing

检查投放节奏

Generate weekly scorecard

生成每周评分卡

Sales Pipeline

Sales Pipeline

RB2B Router

RB2B路由工具

Fetch website visitors from RB2B

从RB2B获取网站访客数据

Route to Instantly campaigns

将访客导入Instantly营销活动

Deal Resurrector

沉睡线索激活工具

Find stale deals with departed champions

查找关键联系人已离职的沉睡线索

Track champions to new companies

追踪关键联系人的新任职公司

ICP Learner

理想客户画像（ICP）学习工具

Analyze win/loss patterns

分析赢单/丢单模式

Update ICP definition

更新ICP定义

Content Ops

Content Ops

Expert Panel

专家评审机制

Load expert personas

加载专家角色

Score content