X Voice Match
Analyze Twitter/X accounts to extract posting patterns and generate authentic content that matches the account owner's unique voice.
Quick Start
Step 1: Analyze the account
CODEBLOCK0
Step 2: Generate posts
CODEBLOCK1
Or use the all-in-one approach:
CODEBLOCK2
What It Analyzes
The skill extracts:
- - Length patterns: Tweet character counts, thread usage, one-liner vs paragraph style
- Tone markers: Humor style, sarcasm, self-deprecation, edginess level
- Topics: Crypto, AI, tech, memes, personal life, current events
- Engagement patterns: QT vs original, reaction tweets, conversation starters
- Language patterns: Specific phrases, slang, emoji usage, punctuation style
- Content types: Observations, hot takes, memes, threads, questions, personal stories
Output Format
Voice Profile (JSON)
CODEBLOCK3
Generated Posts
Returns 1-N posts with confidence scores and reasoning.
Integration with Existing Tools
Works with Bird CLI (/data/workspace/bird.sh):
CODEBLOCK4
Post Type Templates
See references/post-types.md for common X post frameworks:
- - Observations
- Hot takes
- Self-deprecating humor
- Crypto commentary
- Reaction posts
- Questions
Advanced Usage
Update Voice Profile
Re-analyze periodically to capture style evolution:
CODEBLOCK5
Generate by Post Type
CODEBLOCK6
Batch Generation
CODEBLOCK7
Workflow
- 1. First time: Run full analysis on 30-50 tweets
- Generate posts: Provide topic, get 3-5 style-matched options
- User picks: Select best option or iterate with feedback
- Periodic updates: Re-analyze monthly or after major voice shifts
Tips
- - Minimum tweets: 30 tweets for basic analysis, 50+ for accuracy
- Recency matters: Recent tweets reflect current style better than old ones
- Topic relevance: Generated posts work best on topics the account normally covers
- Confidence scores: <70% = may not sound authentic, revise or regenerate
X Voice Match
分析Twitter/X账户,提取发帖模式,生成与账户所有者独特声音相匹配的真实内容。
快速开始
步骤1:分析账户
bash
cd /data/workspace/skills/x-voice-match
python3 scripts/analyze_voice.py @用户名 [--tweets 50] [--output profile.json]
步骤2:生成帖子
bash
python3 scripts/generate_post.py --profile profile.json --topic 你的主题 [--count 3]
或使用一站式方法:
bash
python3 scripts/generate_post.py --account @用户名 --topic AI代理接管一切 --count 5
分析内容
该技能提取:
- - 长度模式:推文字符数、线程使用情况、单行与段落风格
- 语气标记:幽默风格、讽刺、自嘲、尖锐程度
- 主题:加密货币、AI、科技、迷因、个人生活、时事
- 互动模式:引用推文与原创、反应型推文、话题发起
- 语言模式:特定短语、俚语、表情符号使用、标点风格
- 内容类型:观察、犀利观点、迷因、线程、问题、个人故事
输出格式
声音档案(JSON)
json
{
account: @gravyxbt_,
analyzed_tweets: 50,
patterns: {
avg_length: 85,
length_distribution: {short: 0.6, medium: 0.3, long: 0.1},
uses_threads: false,
humor_style: 自嘲、讽刺,
topics: [加密货币, AI代理, 迷因, 时事],
engagement_type: 反应型引用推文为主,
signature_phrases: [笑死, 真的, 认同],
emoji_usage: 最少、策略性使用,
punctuation: 小写、随意
}
}
生成的帖子
返回1-N条帖子,附带置信度分数和推理说明。
与现有工具集成
与Bird CLI(/data/workspace/bird.sh)配合使用:
bash
获取最新推文用于分析
./bird.sh user-tweets @gravyxbt
-n 50 > recenttweets.txt
python3 scripts/analyze
voice.py --input recenttweets.txt
帖子类型模板
参见references/post-types.md了解常见X帖子框架:
- - 观察
- 犀利观点
- 自嘲幽默
- 加密货币评论
- 反应型帖子
- 问题
高级用法
更新声音档案
定期重新分析以捕捉风格演变:
bash
python3 scripts/analyze_voice.py @用户名 --update profile.json
按帖子类型生成
bash
python3 scripts/generate_post.py --profile profile.json --type 犀利观点 --topic 加密货币
批量生成
bash
python3 scripts/generate_post.py --profile profile.json --batch topics.txt --output posts.json
工作流程
- 1. 首次使用:对30-50条推文进行完整分析
- 生成帖子:提供主题,获取3-5个风格匹配的选项
- 用户选择:选择最佳选项或根据反馈迭代
- 定期更新:每月或在重大风格转变后重新分析
提示
- - 最少推文数:基本分析需30条推文,50条以上更准确
- 时效性重要:近期推文比旧推文更能反映当前风格
- 主题相关性:生成帖子在账户常涉及的主题上效果最佳
- 置信度分数:<70% = 可能不够真实,需修改或重新生成