creator-insights

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Twitter Creator Insights

Twitter创作者洞察

This skill provides Twitter/X content creators with actionable intelligence about their account performance, trending topics in their niche, and competitive analysis. Includes account analytics, viral content discovery, thread/follower intelligence, and AI-powered content generation.

本技能为Twitter/X内容创作者提供关于账号表现、细分领域热门话题及竞品分析的实用情报，涵盖账号分析、爆款内容挖掘、推文线程/粉丝洞察，以及AI驱动的内容生成功能。

When to Use This Skill

何时使用本技能

Invoke this skill when:

A creator requests analysis of their Twitter account or another account
User asks about trending content or viral tweets in a specific niche
User wants to understand what content performs well in their space
User needs recommendations for improving their Twitter strategy
User asks about competitor or similar account activity
User wants to find influential accounts in a niche
User wants to identify VIP followers or "hidden gem" accounts (NEW)
User asks which threads attracted high-value engagement (NEW)
User needs help drafting tweets or analyzing viral patterns with AI (NEW)
User wants to optimize an existing tweet before posting (NEW)

在以下场景调用本技能：

创作者请求分析自己或他人的Twitter账号
用户询问特定细分领域的热门内容或爆款推文
用户希望了解自身领域内表现优异的内容类型
用户需要优化Twitter运营策略的建议
用户询问竞品或同类账号的动态
用户想要找到细分领域内的有影响力账号
用户希望识别VIP粉丝或「潜力账号」（新增功能）
用户询问哪些推文线程获得了高价值互动（新增功能）
用户需要AI辅助撰写推文或分析爆款规律（新增功能）
用户想要在发布前优化现有推文（新增功能）

Core Workflow

核心工作流程

The skill follows a fetch → analyze → score → recommend pipeline:

本技能遵循获取→分析→评分→推荐的流程：

1. Account Analysis Phase

1. 账号分析阶段

Objective: Deep-dive into a Twitter account's performance and content patterns.

Process:

Run

python scripts/twitter_analyzer.py --username [handle] --tweets 100

The system fetches:
- User profile (followers, bio, verification status)
- Recent tweets (up to 100)
- Engagement metrics (likes, RTs, replies, quotes, views)
Calculates:
- Engagement rate (weighted by follower count)
- Content patterns (hashtag usage, thread frequency, tweet types)
- Posting schedule optimization
- Viral content identification (outliers >2σ above mean)

Key Metrics:

Engagement Rate: (likes + RTs + replies) / followers × 100
Like/RT Ratio: Indicates passive vs. active engagement
Thread Performance: Threads vs. standalone tweet comparison
Viral Multiplier: How many times above average a tweet performed

Output Structure:

TWITTER ANALYSIS: @username
├── Profile metrics (followers, tweets, verification)
├── Engagement metrics (rates, averages, ratios)
├── Viral content (top 5 tweets with multiplier)
├── Thread analysis (performance comparison)
├── Hashtag performance (which hashtags drive engagement)
├── Posting schedule (best times based on data)
└── Recommendations (7 actionable insights)

目标：深入分析Twitter账号的表现及内容规律。

流程：

运行

python scripts/twitter_analyzer.py --username [handle] --tweets 100

系统获取以下信息：
- 用户资料（粉丝数、简介、认证状态）
- 近期推文（最多100条）
- 互动指标（点赞、转发、回复、引用、浏览量）
计算：
- 互动率（按粉丝数加权）
- 内容规律（话题标签使用频率、线程发布频率、推文类型）
- 发布时间优化建议
- 爆款内容识别（超出均值2σ的异常内容）

关键指标：

互动率：(点赞 + 转发 + 回复) / 粉丝数 × 100
点赞/转发比率：反映被动与主动互动的占比
线程表现：线程推文与单条推文的表现对比
爆款倍数：推文表现超出平均水平的倍数

输出结构：

TWITTER ANALYSIS: @username
├── 资料指标（粉丝数、推文数、认证状态）
├── 互动指标（互动率、平均值、比率）
├── 爆款内容（Top 5高倍数推文）
├── 线程分析（表现对比）
├── 话题标签表现（哪些标签能提升互动）
├── 发布时间建议（基于数据的最佳时段）
└── 优化建议（7条可执行洞察）

2. Niche Detection Phase

2. 细分领域识别阶段

Objective: Identify a creator's content niche and posting style.

Process:

Run

python scripts/profile_analyzer.py --profile @username

Analyzes last 30 tweets for:
- Keyword frequency across 14 predefined niches
- Content themes (most common topics)
- Tone analysis (professional, casual, educational, entertaining)
- Posting cadence and consistency

Niche Categories:

Tech, AI/ML, Crypto/Web3, Business, Marketing
Gaming, Fitness, Beauty, Food, Travel
Comedy, Education, Music, Art

Scoring Method:

python

niche_score = Σ(keyword_matches) for niche in all_niches
primary_niche = max(niche_scores)
secondary_niches = scores > (primary_score × 0.5)

目标：识别创作者的内容领域及发布风格。

流程：

运行

python scripts/profile_analyzer.py --profile @username

分析最近30条推文的：
- 14个预设领域的关键词频率
- 内容主题（最常见话题）
- 语气分析（专业、休闲、教育、娱乐）
- 发布频率与一致性

细分领域类别：

科技、AI/ML、加密货币/Web3、商业、营销
游戏、健身、美妆、美食、旅行
喜剧、教育、音乐、艺术

评分方法：

python

niche_score = Σ(keyword_matches) for niche in all_niches
primary_niche = max(niche_scores)
secondary_niches = scores > (primary_score × 0.5)

3. Trend Discovery Phase

3. 趋势挖掘阶段

Objective: Find viral content and trending topics in a specific niche.

Process:

Run

python scripts/trend_aggregator.py --niche "[topic]" --viral-examples --limit 10

Search for tweets matching:
```
"{niche}" min_faves:1000 -is:retweet
```

Rank by total engagement:

likes + (retweets × 2) + (replies × 1.5)

Analyze viral factors:
- Hashtag usage patterns
- Tweet length optimization
- Thread vs. single tweet
- Question-based engagement
- Quote tweet ratio (conversation starter indicator)

Viral Factor Detection:

python

if len(hashtags) > 0: "used {n} hashtags"
if '?' in text: "engaged audience with question"
if len(text) > 200: "detailed/thorough content"
elif len(text) < 100: "concise and punchy"
if quotes > retweets/2: "sparked conversation"

目标：找到特定细分领域的爆款内容及热门话题。

流程：

运行

python scripts/trend_aggregator.py --niche "[topic]" --viral-examples --limit 10

搜索符合条件的推文：
```
"{niche}" min_faves:1000 -is:retweet
```

按总互动量排序：

点赞 + (转发 × 2) + (回复 × 1.5)

分析爆款因素：
- 话题标签使用规律
- 推文长度优化
- 线程推文vs单条推文
- 提问式互动
- 引用推文比率（反映话题引发讨论的能力）

爆款因素检测：

python

if len(hashtags) > 0: "used {n} hashtags"
if '?' in text: "engaged audience with question"
if len(text) > 200: "detailed/thorough content"
elif len(text) < 100: "concise and punchy"
if quotes > retweets/2: "sparked conversation"

4. Competitive Intelligence Phase

4. 竞品情报阶段

Objective: Identify top performers and rising accounts in a niche.

Process:

Run

python scripts/trend_aggregator.py --niche "[topic]" --find-accounts --limit 10

Aggregate top 50 viral tweets in niche
Group by author and calculate:
- Total engagement across all tweets
- Average engagement per tweet
- Follower count
Sort by engagement/follower ratio (efficiency metric)

Account Scoring:

python

account_score = (total_engagement / follower_count) × tweet_frequency

目标：识别细分领域内的顶级创作者及潜力账号。

流程：

运行

python scripts/trend_aggregator.py --niche "[topic]" --find-accounts --limit 10

汇总细分领域内Top 50爆款推文
按作者分组并计算：
- 所有推文的总互动量
- 单条推文平均互动量
- 粉丝数
按「互动量/粉丝数」比率排序（效率指标）

账号评分：

python

account_score = (total_engagement / follower_count) × tweet_frequency

Identifies accounts that punch above their weight

识别粉丝规模不大但互动效率极高的账号

undefined

undefined

5. Thread Intelligence Phase NEW

5. 线程洞察阶段新增

Objective: Identify high-performing threads and track engagement from influential accounts.

Process:

Run

python scripts/thread_intelligence.py --username [handle] --tweets 50 --threshold 10000

Fetches user's timeline and identifies multi-tweet threads
For each thread:
- Gets full thread context
- Fetches all replies
- Identifies high-value repliers (accounts with >10K followers by default)
- Tracks engagement patterns
Ranks threads by number of high-value replies

Influence Threshold:

python

high_value_account = follower_count >= threshold  # Default: 10,000

目标：识别高表现推文线程，并追踪有影响力账号的互动情况。

流程：

运行

python scripts/thread_intelligence.py --username [handle] --tweets 50 --threshold 10000

获取用户时间线并识别多推文线程
对每个线程：
- 获取完整线程内容
- 获取所有回复
- 识别高价值回复者（默认粉丝数>10K的账号）
- 追踪互动规律
按高价值回复数量对线程排序

影响力阈值：

python

high_value_account = follower_count >= threshold  # 默认值：10,000

Configurable via --threshold parameter

可通过--threshold参数配置


**Output Structure**:

THREAD INTELLIGENCE: @username ├── Thread Statistics (total, high-value reply count, engagement rate) ├── Top Threads (ranked by high-value replies) │ ├── Thread text preview │ ├── Tweet count in thread │ ├── Total replies vs high-value replies │ └── Reply engagement score ├── Top Thread Details (deep-dive on #1 thread) │ ├── Full text preview │ ├── High-value repliers list │ └── Follower counts └── Most Engaged High-Value Accounts (across all threads) ├── Reply count per account └── Number of threads engaged with


**Comparison Mode**:
```bash
python scripts/thread_intelligence.py --username [handle] --compare --tweets 50

Compares thread performance vs standalone tweets to determine optimal content format.


**输出结构**：

THREAD INTELLIGENCE: @username ├── 线程统计（总数、高价值回复数、互动率） ├── Top线程（按高价值回复排序） │ ├── 线程内容预览 │ ├── 线程内推文数量 │ ├── 总回复数vs高价值回复数 │ └── 回复互动评分 ├── Top线程详情（对排名第1的线程深度分析） │ ├── 完整内容预览 │ ├── 高价值回复者列表 │ └── 粉丝数 └── 互动最活跃的高价值账号（所有线程） ├── 每个账号的回复数 └── 参与的线程数量


**对比模式**：
```bash
python scripts/thread_intelligence.py --username [handle] --compare --tweets 50

对比线程推文与单条推文的表现，确定最优内容格式。

6. Follower Intelligence Phase NEW

6. 粉丝洞察阶段新增

Objective: Discover VIP followers using combined influence scoring and engagement tracking.

Process:

Run

python scripts/follower_intelligence.py --username [handle] --tweets 20 --max-followers 500

Fetches user's followers (newest first, up to 500)
Tracks engagement across recent tweets:
- Who retweeted (via
```
get_tweet_retweeters
```
  endpoint)
- Who replied (via
```
get_tweet_replies
```
  endpoint)

Calculates influence score for each follower:

python

influence_score = (followers × 0.7) + (engagement_count × 1000 × 0.3)

Identifies special segments:
- VIP Followers: Top 50 by influence score
- Hidden Gems: <5K followers but ≥2 interactions
- Top Engagers: Most interactions regardless of follower count

Influence Score Formula:

python

undefined

目标：结合影响力评分与互动追踪，发现VIP粉丝。

流程：

运行

python scripts/follower_intelligence.py --username [handle] --tweets 20 --max-followers 500

获取用户粉丝（按最新排序，最多500个）
追踪近期推文的互动情况：
- 谁转发了推文（通过
```
get_tweet_retweeters
```
  接口）
- 谁回复了推文（通过
```
get_tweet_replies
```
  接口）

计算每个粉丝的影响力评分：

python

influence_score = (followers × 0.7) + (engagement_count × 1000 × 0.3)

识别特殊群体：
- VIP粉丝：影响力评分Top 50
- 潜力账号：粉丝数<5K且互动≥2次
- 顶级互动者：互动次数最多的粉丝（无论粉丝数多少）

影响力评分公式：

python

undefined

Balanced scoring: audience size (70%) + actual engagement (30%)

平衡评分：受众规模（70%）+ 实际互动（30%）

influence = (follower_count × 0.7) + (total_interactions × 1000 × 0.3)

Example:

示例：

Account A: 100K followers, 0 interactions = 70,000 influence

账号A：10万粉丝，0次互动 = 70,000影响力

Account B: 10K followers, 5 interactions = 8,500 influence

账号B：1万粉丝，5次互动 = 8,500影响力

Account C: 2K followers, 10 interactions = 4,400 influence (hidden gem!)

账号C：2千粉丝，10次互动 = 4,400影响力（潜力账号！）


**Output Structure**:

VIP FOLLOWERS: @username ├── Engagement Statistics │ ├── Total followers analyzed │ ├── Engaged followers (who interacted) │ └── Engagement rate % ├── Top VIP Followers (by influence score) │ ├── Username, follower count, verified status │ ├── Engagement breakdown (RTs, replies) │ └── Influence score ├── Hidden Gems (high engagement, low followers) │ └── Rising creators to nurture └── Top Engagers (most interactions) └── Your biggest supporters


**Growth Analysis Mode**:
```bash
python scripts/follower_intelligence.py --username [handle] --growth --max-followers 200

Analyzes follower quality distribution (micro, small, medium, large, mega).


**输出结构**：

VIP FOLLOWERS: @username ├── 互动统计 │ ├── 分析的粉丝总数 │ ├── 参与互动的粉丝数 │ └── 互动率% ├── Top VIP粉丝（按影响力评分） │ ├── 用户名、粉丝数、认证状态 │ ├── 互动明细（转发、回复） │ └── 影响力评分 ├── 潜力账号（高互动、低粉丝数） │ └── 需要培养的新晋创作者 └── 顶级互动者（互动次数最多） └── 你的核心支持者


**增长分析模式**：
```bash
python scripts/follower_intelligence.py --username [handle] --growth --max-followers 200

分析粉丝质量分布（微型、小型、中型、大型、超大型账号）。

7. AI Content Generation Phase NEW

7. AI内容生成阶段新增

Objective: Use AI to analyze viral patterns, draft tweets, and optimize content using Claude 3.5 Sonnet.

Three AI Actions:

目标：使用AI分析爆款规律、撰写推文，并通过Claude 3.5 Sonnet优化内容。

三种AI操作：

A. Viral Pattern Analysis

A. 爆款规律分析

bash

python scripts/content_generator.py --action analyze --username [top_creator] --tweets 50 --min-engagement 100

Process:

Fetches high-engagement tweets (>100 engagement by default)
Filters for viral content
Sends top 5 tweets to AI with prompt:
- "Analyze content themes that perform best"
- "Identify tweet structure patterns"
- "Determine optimal posting times"
- "Evaluate hashtag strategy"
- "Understand engagement patterns"

Output: AI-generated multi-section analysis with actionable insights.

bash

python scripts/content_generator.py --action analyze --username [top_creator] --tweets 50 --min-engagement 100

流程：

获取高互动推文（默认互动量>100）
筛选爆款内容
将Top 5推文发送给AI，并附带提示：
- "分析表现最佳的内容主题"
- "识别推文结构规律"
- "确定最优发布时间"
- "评估话题标签策略"
- "理解互动模式"

输出：AI生成的多板块分析报告，包含可执行洞察。

B. Tweet Drafting

B. 推文撰写

bash

python scripts/content_generator.py --action draft --topic "Your topic here" --username [style_reference] --variations 5

Process:

Optionally analyzes reference account's style (if --username provided)
Sends topic + style context to AI
AI generates 3-5 variations with:
- Different angles/hooks per variation
- Character count (ensures ≤280)
- Strategy explanation
- Predicted engagement level

Output: JSON array of tweet variations with metadata.

bash

python scripts/content_generator.py --action draft --topic "Your topic here" --username [style_reference] --variations 5

流程：

可选：分析参考账号的风格（若提供--username参数）
将主题+风格上下文发送给AI
AI生成3-5种变体，包含：
- 每种变体的不同角度/钩子
- 字符数（确保≤280）
- 策略说明
- 预测互动水平

输出：包含元数据的推文变体JSON数组。

C. Tweet Optimization

C. 推文优化

bash

python scripts/content_generator.py --action optimize --text "Your tweet draft" --goal engagement

Goals:

engagement

reach

replies

clarity

Process:

Sends original tweet + optimization goal to AI
AI provides:
- Optimized version
- 2-3 alternative approaches
- Explanation of improvements
- Posting strategy tips

Output: Enhanced tweet with detailed optimization rationale.

bash

python scripts/content_generator.py --action optimize --text "Your tweet draft" --goal engagement

优化目标：

engagement

（互动）、

reach

（曝光）、

replies

（回复）、

clarity

（清晰度）

流程：

将原始推文+优化目标发送给AI
AI提供：
- 优化后的版本
- 2-3种替代方案
- 改进说明
- 发布策略建议

输出：优化后的推文及详细的优化理由。

8. Enhanced Viral Analysis IMPROVED

8. 增强版爆款分析升级

The viral factor detection has been significantly enhanced with multi-dimensional pattern analysis:

Previous (Simple):

python

if len(hashtags) > 0: "used hashtags"
if '?' in text: "question"

New (Sophisticated):

python

undefined

爆款因素检测已通过多维模式分析显著增强：

旧版（基础）：

python

if len(hashtags) > 0: "used hashtags"
if '?' in text: "question"

新版（进阶）：

python

undefined

1. FORMAT DETECTION

1. 格式检测

Thread detection (🧵, "thread", "1/")
Question count (single vs multiple)
List/numbered format (1. 2. 3.)
Emotional hooks (amazing, shocking, breaking)
Call-to-action (let me know, check out, reply with)

线程识别（🧵、"thread"、"1/"）
提问数量（单个vs多个）
列表/编号格式（1. 2. 3.）
情感钩子（amazing、shocking、breaking）
行动号召（let me know、check out、reply with）

2. MEDIA DETECTION

2. 媒体检测

Visual content presence (images/videos)

视觉内容存在（图片/视频）

3. LENGTH OPTIMIZATION

3. 长度优化

Comprehensive (>240 chars)
Concise (<80 chars)
Optimal range (120-180 chars)

长篇内容（>240字符）
简短内容（<80字符）
最优范围（120-180字符）

4. HASHTAG STRATEGY

4. 话题标签策略

Strategic use (3+ hashtags)
Focused single hashtag

策略性使用（3个以上标签）
聚焦单个标签

5. ENGAGEMENT PATTERN ANALYSIS

5. 互动模式分析

High reply ratio (>25% = discussion starter)
High retweet ratio (>20% = shareable)
Viral coefficient (quotes+RTs >30%)

高回复比率（>25% = 话题发起者）
高转发比率（>20% = 易分享内容）
爆款系数（引用+转发>30%）

6. TEMPORAL ANALYSIS

6. 时间分析

Peak posting window (9-11 AM, 1-3 PM)
Low-competition hours (9 PM - 6 AM)
Weekend timing advantage

峰值发布窗口（9-11点、13-15点）
低竞争时段（21点-次日6点）
周末时间优势

7. ADVANCED PATTERNS

7. 进阶模式

Data-driven credibility (study, research, analysis)
Storytelling hooks (story, remember when)
Controversy/debate (unpopular opinion, hot take)


**Example Enhanced Output**:

🔥 Why viral: Question encouraging replies; emotional hook driving curiosity; comprehensive detail (long-form); highly shareable content


Returns top 4 most relevant factors for each viral tweet.

数据驱动可信度（study、research、analysis）
故事钩子（story、remember when）
争议/辩论点（unpopular opinion、hot take）


**增强版输出示例**：

🔥 爆款原因：提问引发回复；情感钩子激发好奇心；内容详尽（长篇）；高分享性


返回每条爆款推文的Top 4最相关因素。

Engagement Scoring Framework

互动评分框架

Following head-of-content methodology, we use weighted engagement metrics:

python

WEIGHTS = {
    'bookmarks': 4.0,  # Strongest intent signal
    'replies': 2.0,    # Direct conversation
    'retweets': 1.5,   # Amplification
    'quotes': 2.5,     # Conversation + amplification
    'likes': 1.0,      # Baseline engagement
    'views': 0.01      # Reach indicator
}

engagement_score = Σ(metric × weight)

Outlier Detection: Content scoring above

mean + (2.0 × standard_deviation)

is flagged as viral.

遵循内容负责人方法论，我们使用加权互动指标：

python

WEIGHTS = {
    'bookmarks': 4.0,  # 最强的意向信号
    'replies': 2.0,    # 直接对话
    'retweets': 1.5,   # 传播放大
    'quotes': 2.5,     # 对话+传播放大
    'likes': 1.0,      # 基础互动
    'views': 0.01      # 曝光指标
}

engagement_score = Σ(metric × weight)

异常值检测：评分超过

均值 + (2.0 × 标准差)

的内容被标记为爆款。

Output Formats

输出格式

Text Output (default)

文本输出（默认）

Human-readable reports with:

Section headers and dividers
Bullet points for key insights
Numerical rankings
Actionable recommendations

人类可读的报告，包含：

章节标题与分隔线
关键洞察的项目符号
数字排名
可执行建议

JSON Output

JSON输出

Machine-readable data for:

Integration with other tools
Historical tracking
Custom dashboard creation
Multi-account comparison

Example:

bash

python scripts/twitter_analyzer.py --username handle --output json > analysis.json

机器可读数据，适用于：

与其他工具集成
历史追踪
自定义仪表盘创建
多账号对比

示例：

bash

python scripts/twitter_analyzer.py --username handle --output json > analysis.json

Configuration

配置

Config File (

config.yaml

- optional):

yaml

undefined

配置文件 (

config.yaml

- 可选)：

yaml

undefined

AI content generation settings

AI内容生成设置

openrouter: default_model: "anthropic/claude-3.5-sonnet" temperature: 0.7 max_tokens: 2000

Influence scoring for follower/thread intelligence

粉丝/线程洞察的影响力评分

influence: follower_weight: 0.7 # 70% weight on follower count engagement_weight: 0.3 # 30% weight on engagement high_value_threshold: 10000 # 10K+ followers = high-value hidden_gem_threshold: 5000 # <5K followers = potential gem min_engagement_interactions: 2 # Minimum interactions to count

influence: follower_weight: 0.7 # 粉丝数权重70% engagement_weight: 0.3 # 互动权重30% high_value_threshold: 10000 # 粉丝数≥10K = 高价值账号 hidden_gem_threshold: 5000 # 粉丝数<5K = 潜力账号 min_engagement_interactions: 2 # 计入统计的最低互动次数

Viral analysis thresholds

爆款分析阈值

viral: min_engagement: 100 # Minimum total engagement min_likes: 500 # For trending searches high_reply_ratio: 0.25 # >25% replies = discussion high_retweet_ratio: 0.20 # >20% RTs = shareable viral_coefficient: 0.30 # >30% quotes+RTs = viral

viral: min_engagement: 100 # 最低总互动量 min_likes: 500 # 趋势搜索的最低点赞数 high_reply_ratio: 0.25 # >25%回复率 = 话题性内容 high_retweet_ratio: 0.20 # >20%转发率 = 易分享内容 viral_coefficient: 0.30 # >30%引用+转发 = 爆款

Tweet generation defaults

推文生成默认设置

generation: num_variations: 5 # Default tweet variations max_length: 280 # Twitter character limit style_sample_size: 10 # Tweets to analyze for style

settings: rate_limit: 100 # Requests per minute default_timeframe: "30d" # Analytics window cache_duration: 15 # Minutes to cache trends

undefined

generation: num_variations: 5 # 默认推文变体数量 max_length: 280 # Twitter字符限制 style_sample_size: 10 # 用于风格分析的推文数量

settings: rate_limit: 100 # 每分钟请求数 default_timeframe: "30d" # 分析时间窗口 cache_duration: 15 # 趋势缓存时长（分钟）

undefined

Error Handling

错误处理

Rate Limiting:

Automatic backoff when hitting API limits
60-second cooldown before retry
Progress maintained across retries

Authentication Failures:

If authentication errors occur, check platform configuration

Network Timeouts:

10-second timeout per request
Automatic retry with exponential backoff
Graceful degradation (returns partial results)

Invalid Usernames:

Could not fetch info for @username

→ Verify account exists and is not suspended

速率限制：

触发API限制时自动退避
重试前冷却60秒
重试时保留进度

认证失败：

若出现认证错误，请检查平台配置

网络超时：

每个请求超时10秒
自动指数退避重试
优雅降级（返回部分结果）

无效用户名：

Could not fetch info for @username

→ 验证账号是否存在且未被封禁

Advanced Usage

进阶用法

Batch Analysis

批量分析

Analyze multiple accounts:

bash

for account in account1 account2 account3; do
    python scripts/twitter_analyzer.py --username $account --output json > ${account}_analysis.json
done

分析多个账号：

bash

for account in account1 account2 account3; do
    python scripts/twitter_analyzer.py --username $account --output json > ${account}_analysis.json
done

Automated Monitoring

自动化监控

Daily trend tracking:

bash

undefined

每日趋势追踪：

bash

undefined

Add to crontab

添加到crontab

0 9 * * * cd /path/to/skill && python scripts/trend_aggregator.py --niche "AI" --viral-examples --limit 10 >> daily_trends.log

undefined

0 9 * * * cd /path/to/skill && python scripts/trend_aggregator.py --niche "AI" --viral-examples --limit 10 >> daily_trends.log

undefined

Comparative Analysis

对比分析

Compare two accounts:

bash

python scripts/twitter_analyzer.py --username account1 --output json > a1.json
python scripts/twitter_analyzer.py --username account2 --output json > a2.json

对比两个账号：

bash

python scripts/twitter_analyzer.py --username account1 --output json > a1.json
python scripts/twitter_analyzer.py --username account2 --output json > a2.json

Then compare engagement_rate, viral_multiplier, etc.

然后对比engagement_rate、viral_multiplier等指标

undefined

undefined

Related Scripts

Integration with Other Skills

与其他技能集成

This skill complements:

Content planning skills: Use viral patterns to inform content strategy
Copywriting skills: Analyze successful tweet structures
Marketing skills: Understand audience engagement patterns

本技能可与以下技能互补：

内容规划技能：利用爆款规律制定内容策略
文案撰写技能：分析成功推文的结构
营销技能：理解受众互动模式

Metrics Glossary

指标术语表

Engagement Rate: % of followers who interact with content
Viral Multiplier: How many standard deviations above average
Like/RT Ratio: Passive (likes) vs. active (RTs) engagement
Thread Performance: Avg engagement on threaded vs. single tweets
Consistency Score: Regularity of posting (0-10 scale)
Quote Rate: Replies with quotes (conversation quality indicator)

互动率：与内容互动的粉丝占比
爆款倍数：超出平均水平的标准差倍数
点赞/转发比率：被动（点赞）vs主动（转发）互动
线程表现：线程推文与单条推文的平均互动对比
一致性评分：发布规律性（0-10分）
引用率：带引用的回复占比（反映对话质量）

Best Practices

最佳实践

Run weekly analysis on your account to track trends
Compare to competitors in your niche for benchmarking
Act on viral patterns - replicate what works
Monitor recommended posting times based on your data
Track hashtag performance and iterate
Experiment with threads if data shows they outperform
Focus on engagement rate over vanity metrics

每周分析一次账号，追踪趋势变化
与竞品对比，进行基准测试
复制爆款规律 - 复用有效的内容模式
遵循推荐的发布时间，基于你的数据
追踪话题标签表现，持续优化
尝试线程推文，如果数据显示其表现更优
关注互动率而非虚荣指标

Troubleshooting

故障排除

"Rate limit exceeded" → Wait 60 seconds and retry

"Request timed out" → Reduce

--tweets

parameter or try again (network issue)

Empty results → Try broader niche keywords or lower

min_faves

threshold

Proxy connection issues → Check that sc-proxy is running and configured correctly in Star Child

"Rate limit exceeded" → 等待60秒后重试

"Request timed out" → 减少

--tweets

参数或稍后重试（网络问题）

空结果 → 尝试更宽泛的领域关键词或降低

min_faves

阈值

代理连接问题 → 检查sc-proxy是否在Star Child中正常运行并配置正确

What's New in v2.0:

v2.0新增功能：

Thread Intelligence: Identify high-value engagement in threads (10K+ followers)
Follower Intelligence: VIP follower discovery with influence score algorithm
AI Content Generation: OpenRouter integration for viral analysis & tweet drafting
Enhanced Viral Analysis: 7-category sophisticated pattern detection
API Expansion: 10+ new TwitterAPI.io endpoints (followers, retweeters, replies, threads)
ASCII Dashboards: Beautiful terminal visualizations with progress bars
Comprehensive Config: Documented settings for all thresholds and parameters

线程洞察：识别线程中的高价值互动（粉丝数≥10K）
粉丝洞察：通过影响力评分算法发现VIP粉丝
AI内容生成：集成OpenRouter进行爆款分析与推文撰写
增强版爆款分析：7类进阶模式检测
API扩展：新增10+ TwitterAPI.io接口（粉丝、转发者、回复、线程）
ASCII仪表盘：美观的终端可视化，含进度条
全面配置：所有阈值与参数的文档化设置

Module Summary:

模块总结：

```
twitter_analyzer.py
```
- Account analytics (v1.0 feature)
```
profile_analyzer.py
```
- Niche detection (v1.0 feature)
```
trend_aggregator.py
```
- Viral discovery (enhanced in v2.0)
```
thread_intelligence.py
```
- Thread analysis (NEW in v2.0)
```
follower_intelligence.py
```
- VIP follower tracking (NEW in v2.0)
```
content_generator.py
```
- AI-powered content (NEW in v2.0)

```
twitter_analyzer.py
```
- 账号分析（v1.0功能）
```
profile_analyzer.py
```
- 细分领域识别（v1.0功能）
```
trend_aggregator.py
```
- 爆款挖掘（v2.0增强）
```
thread_intelligence.py
```
- 线程分析（v2.0新增）
```
follower_intelligence.py
```
- VIP粉丝追踪（v2.0新增）
```
content_generator.py
```
- AI驱动内容（v2.0新增）

creator-insights

Original

Translation

Twitter Creator Insights

Twitter创作者洞察

When to Use This Skill

何时使用本技能

Core Workflow

核心工作流程

1. Account Analysis Phase

1. 账号分析阶段

2. Niche Detection Phase

2. 细分领域识别阶段

3. Trend Discovery Phase

3. 趋势挖掘阶段

4. Competitive Intelligence Phase

4. 竞品情报阶段

Identifies accounts that punch above their weight

识别粉丝规模不大但互动效率极高的账号

5. Thread Intelligence Phase NEW

5. 线程洞察阶段 新增

Configurable via --threshold parameter

可通过--threshold参数配置

6. Follower Intelligence Phase NEW

6. 粉丝洞察阶段 新增

Balanced scoring: audience size (70%) + actual engagement (30%)

平衡评分：受众规模（70%）+ 实际互动（30%）

Example:

示例：

Account A: 100K followers, 0 interactions = 70,000 influence

账号A：10万粉丝，0次互动 = 70,000影响力

Account B: 10K followers, 5 interactions = 8,500 influence

账号B：1万粉丝，5次互动 = 8,500影响力

Account C: 2K followers, 10 interactions = 4,400 influence (hidden gem!)

账号C：2千粉丝，10次互动 = 4,400影响力（潜力账号！）

7. AI Content Generation Phase NEW

7. AI内容生成阶段 新增

A. Viral Pattern Analysis

A. 爆款规律分析

B. Tweet Drafting

B. 推文撰写

C. Tweet Optimization

C. 推文优化

8. Enhanced Viral Analysis IMPROVED

8. 增强版爆款分析 升级

1. FORMAT DETECTION

1. 格式检测

2. MEDIA DETECTION

2. 媒体检测

3. LENGTH OPTIMIZATION

3. 长度优化

4. HASHTAG STRATEGY

4. 话题标签策略

5. ENGAGEMENT PATTERN ANALYSIS

5. 互动模式分析

6. TEMPORAL ANALYSIS

6. 时间分析

7. ADVANCED PATTERNS

7. 进阶模式

Engagement Scoring Framework

互动评分框架

Output Formats

输出格式

Text Output (default)

文本输出（默认）

JSON Output

JSON输出

Configuration

配置

AI content generation settings

AI内容生成设置

Influence scoring for follower/thread intelligence

粉丝/线程洞察的影响力评分

Viral analysis thresholds

爆款分析阈值

Tweet generation defaults

推文生成默认设置

Error Handling

错误处理

Advanced Usage

5. 线程洞察阶段新增

6. 粉丝洞察阶段新增

7. AI内容生成阶段新增

8. 增强版爆款分析升级