categorizing-bsky-accounts

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Categorizing Bluesky Accounts

Bluesky账号分类

Fetch Bluesky account data and extract keywords for Claude to categorize by topic. The script compresses account context (bio + posts) into bio + keywords, then Claude performs intelligent categorization.

获取Bluesky账号数据并提取关键词，供Claude按主题分类。该脚本将账号上下文（简介+帖子）压缩为简介+关键词格式，随后由Claude执行智能分类。

Prerequisites

依赖条件

Requires: extracting-keywords skill (provides YAKE venv + domain stopwords)

The analyzer delegates keyword extraction to the extracting-keywords skill, which provides:

Optimized YAKE installation with minimal dependencies
Domain-specific stopwords: English (574), AI/ML (1357), Life Sciences (1293)
Support for 34 languages

需要： extracting-keywords skill（提供YAKE venv + 领域停用词）

分析器将关键词提取任务委托给extracting-keywords skill，该技能提供：

优化后的YAKE安装包，依赖项极少
领域专属停用词：英文（574个）、AI/ML（1357个）、生命科学（1293个）
支持34种语言

Core Workflow

核心工作流程

When users request Bluesky account analysis:

Ensure keyword extraction is set up - Invoke the extracting-keywords skill using the Skill tool to ensure YAKE venv exists (skip if already invoked in this session)
Determine input mode based on user's request:
- Following list → use
```
--following handle
```
- Followers → use
```
--followers handle
```
- List of handles → use
```
--handles "h1,h2,h3"
```
- File provided → use
```
--file accounts.txt
```
Configure parameters:
- ```
--accounts N
```
  - Number to analyze (default: 100, max: 100)
- ```
--posts N
```
  - Posts per account (default: 20, max: 100)
- ```
--stopwords [en|ai|ls]
```
  - Choose domain-specific stopwords:
  - ```
  en
```
  : English (general purpose)
- ```
ai
```
    : AI/ML domain (recommended for tech accounts)
  - ```
  ls
```
  : Life Sciences (for biomedical/research accounts)
- ```
--exclude "pattern1,pattern2"
```
  - Skip spam/bot accounts

Run script - Outputs simple text format to stdout:

@handle1.bsky.social (Display Name)
Bio text here
Keywords: keyword1, keyword2, keyword3

@handle2.bsky.social (Another Name)
Bio text here
Keywords: keyword4, keyword5, keyword6

Categorize accounts - Claude analyzes bio + keywords to categorize by topic

当用户请求Bluesky账号分析时：

确保关键词提取已配置完成 - 使用Skill工具调用extracting-keywords skill，确保YAKE虚拟环境已存在（若本次会话中已调用过则可跳过）
根据用户请求确定输入模式：
- 关注列表 → 使用
```
--following handle
```
- 粉丝列表 → 使用
```
--followers handle
```
- 账号句柄列表 → 使用
```
--handles "h1,h2,h3"
```
- 提供文件 → 使用
```
--file accounts.txt
```
配置参数：
- ```
--accounts N
```
  - 要分析的账号数量（默认值：100，最大值：100）
- ```
--posts N
```
  - 每个账号提取的帖子数量（默认值：20，最大值：100）
- ```
--stopwords [en|ai|ls]
```
  - 选择领域专属停用词：
  - ```
  en
```
  : 英文（通用场景）
- ```
ai
```
    : AI/ML领域（推荐用于科技类账号）
  - ```
  ls
```
  : 生命科学（用于生物医学/研究类账号）
- ```
--exclude "pattern1,pattern2"
```
  - 跳过垃圾/机器人账号

运行脚本 - 将纯文本格式结果输出到标准输出：

@handle1.bsky.social (Display Name)
Bio text here
Keywords: keyword1, keyword2, keyword3

@handle2.bsky.social (Another Name)
Bio text here
Keywords: keyword4, keyword5, keyword6

账号分类 - Claude根据简介+关键词执行主题分类

Quick Start

快速开始

Analyze following list with AI/ML stopwords:

bash

python scripts/bluesky_analyzer.py --following austegard.com --stopwords ai

Analyze followers:

bash

python scripts/bluesky_analyzer.py --followers austegard.com

Analyze specific handles:

bash

python scripts/bluesky_analyzer.py --handles "user1.bsky.social,user2.bsky.social,user3.bsky.social"

From file:

bash

python scripts/bluesky_analyzer.py --file accounts.txt --stopwords ai

Filter out bot accounts:

bash

python scripts/bluesky_analyzer.py --following handle --exclude "bot,spam,promo" --stopwords ai

使用AI/ML停用词分析关注列表：

bash

python scripts/bluesky_analyzer.py --following austegard.com --stopwords ai

分析粉丝列表：

bash

python scripts/bluesky_analyzer.py --followers austegard.com

分析指定账号句柄：

bash

python scripts/bluesky_analyzer.py --handles "user1.bsky.social,user2.bsky.social,user3.bsky.social"

从文件导入账号：

bash

python scripts/bluesky_analyzer.py --file accounts.txt --stopwords ai

过滤机器人账号：

bash

python scripts/bluesky_analyzer.py --following handle --exclude "bot,spam,promo" --stopwords ai

Parameters

参数说明

Input Modes (choose one)

输入模式（选择其一）

--handles "h1,h2,h3" Comma-separated list of Bluesky handles

--following HANDLE Analyze accounts followed by HANDLE

--followers HANDLE Analyze accounts following HANDLE

--file PATH Read handles from file (one per line)

--handles "h1,h2,h3" 逗号分隔的Bluesky账号句柄列表

--following HANDLE 分析指定账号关注的所有账号

--followers HANDLE 分析关注指定账号的所有账号

--file PATH 从文件读取账号句柄（每行一个）

Analysis Options

分析选项

--accounts N Number of accounts to analyze (1-100, default: 100)

--posts N Posts to fetch per account (1-100, default: 20)

--stopwords [en|ai|ls] Stopwords to use for keyword extraction (default: en)

```
en
```
: English stopwords (574 terms) - general purpose
```
ai
```
: AI/ML domain stopwords (1357 terms) - tech-focused accounts
```
ls
```
: Life Sciences stopwords (1293 terms) - biomedical/research accounts

--exclude "word1,word2" Skip accounts with these keywords in bio/posts

--accounts N 要分析的账号数量（1-100，默认值：100）

--posts N 每个账号获取的帖子数量（1-100，默认值：20）

--stopwords [en|ai|ls] 关键词提取使用的停用词（默认值：en）

```
en
```
: 英文停用词（574个）- 通用场景
```
ai
```
: AI/ML领域停用词（1357个）- 科技类账号专用
```
ls
```
: 生命科学停用词（1293个）- 生物医学/研究类账号专用

--exclude "word1,word2" 跳过简介/帖子中包含这些关键词的账号

Output Format

输出格式

The script outputs simple text format for Claude to process:

@alice.bsky.social (Alice Smith)
AI researcher working on LLM alignment and safety
Keywords: alignment, safety research, interpretability, llm evaluation

@bob.bsky.social (Bob Johnson)
Full-stack developer building web applications
Keywords: react, typescript, node.js, api design, postgresql

@carol.bsky.social (Carol Williams)
Biotech researcher studying CRISPR applications
Keywords: crispr, gene editing, therapeutics, clinical trials

Claude then categorizes accounts based on bio + keywords without hardcoded rules.

脚本输出纯文本格式供Claude处理：

@alice.bsky.social (Alice Smith)
AI researcher working on LLM alignment and safety
Keywords: alignment, safety research, interpretability, llm evaluation

@bob.bsky.social (Bob Johnson)
Full-stack developer building web applications
Keywords: react, typescript, node.js, api design, postgresql

@carol.bsky.social (Carol Williams)
Biotech researcher studying CRISPR applications
Keywords: crispr, gene editing, therapeutics, clinical trials

随后Claude会根据简介+关键词进行分类，无需硬编码规则。

Common Workflows

常见工作流

Audit Your Following List

审计你的关注列表

bash

python scripts/bluesky_analyzer.py --following your-handle.bsky.social --stopwords ai

Claude will categorize accounts by topic and identify patterns in who you follow.

bash

python scripts/bluesky_analyzer.py --following your-handle.bsky.social --stopwords ai

Claude会按主题分类账号，并识别你关注账号的模式。

Find Experts in a Topic

寻找特定主题的专家

bash

python scripts/bluesky_analyzer.py --following alice.bsky.social --stopwords ai

Ask Claude: "Which of these accounts are ML researchers?" or "Who focuses on climate tech?"

bash

python scripts/bluesky_analyzer.py --following alice.bsky.social --stopwords ai

你可以询问Claude：“这些账号中哪些是ML研究者？”或“谁专注于气候科技？”

Analyze a Curated List

分析整理好的账号列表

bash

cat > accounts.txt << 'EOF'
expert1.bsky.social
expert2.bsky.social
expert3.bsky.social
EOF

python scripts/bluesky_analyzer.py --file accounts.txt --stopwords ls

bash

cat > accounts.txt << 'EOF'
expert1.bsky.social
expert2.bsky.social
expert3.bsky.social
EOF

python scripts/bluesky_analyzer.py --file accounts.txt --stopwords ls

Filter Out Bot Accounts

过滤机器人账号

bash

python scripts/bluesky_analyzer.py --following handle --exclude "bot,spam,promo,follow back" --stopwords ai

bash

python scripts/bluesky_analyzer.py --following handle --exclude "bot,spam,promo,follow back" --stopwords ai

Technical Details

技术细节

Keyword Extraction

关键词提取

Delegates to extracting-keywords skill using YAKE venv:

Stopwords options (--stopwords):
- ```
en
```
  : English (574 terms) - general purpose
- ```
ai
```
  : AI/ML domain (1357 terms) - filters technical noise, ML boilerplate
- ```
ls
```
  : Life Sciences (1293 terms) - filters research methodology, clinical terms
N-grams: 1-3 words
Deduplication: 0.9 threshold
Top keywords: 10 per account
Performance: ~5% overhead with domain stopwords vs English

委托给extracting-keywords skill使用YAKE虚拟环境：

停用词选项（--stopwords）：
- ```
en
```
  : 英文（574个）- 通用场景
- ```
ai
```
  : AI/ML领域（1357个）- 过滤技术噪声、ML模板内容
- ```
ls
```
  : 生命科学（1293个）- 过滤研究方法、临床术语
N-grams：1-3个词
去重阈值：0.9
每个账号提取的顶部关键词数量：10个
性能：使用领域停用词比通用英文停用词仅增加约5%的开销

API Rate Limits

API速率限制

Bluesky API limits:

3000 requests per 5 minutes
5000 requests per hour

The analyzer respects these limits with built-in delays.

Bluesky API限制：

5分钟内最多3000次请求
1小时内最多5000次请求

分析器内置延迟机制，严格遵守这些限制。

Categorization Algorithm

分类算法

Script's role:

Fetch account data (bio + posts)
Extract keywords to compress context
Output bio + keywords in simple format

Claude's role:

Read bio + keywords for each account
Intelligently categorize by topic (no hardcoded rules)
Group accounts, identify patterns, answer user questions

This agentic pattern is more flexible than hardcoded keyword matching.

脚本的作用：

获取账号数据（简介+帖子）
提取关键词以压缩上下文
输出简介+关键词的纯文本格式

Claude的作用：

读取每个账号的简介+关键词
智能按主题分类（无硬编码规则）
分组账号、识别模式、回答用户问题

这种智能代理模式比硬编码关键词匹配更灵活。

Troubleshooting

故障排除

"No accounts to analyze"

Verify handle format (include domain: handle.bsky.social)
Check if account exists and has public following/followers

"Insufficient content for keyword extraction"

Account has few posts (<5)
Posts are very short
Try increasing
```
--posts
```
parameter

Rate limit errors

Reduce
```
--accounts
```
parameter
Add delays between batches
Check Bluesky API status

Import errors

Verify extracting-keywords skill is available

Check YAKE venv exists:

/home/claude/yake-venv/bin/python -c "import yake"

Verify Python 3.8+:
```
python3 --version
```

“No accounts to analyze”（无账号可分析）

验证账号句柄格式（需包含域名：handle.bsky.social）
检查账号是否存在且关注/粉丝列表为公开状态

“Insufficient content for keyword extraction”（关键词提取内容不足）

账号帖子数量过少（<5条）
帖子内容过短
尝试增加
```
--posts
```
参数的值

速率限制错误

减少
```
--accounts
```
参数的值
在批次之间增加延迟
检查Bluesky API状态

导入错误

确认extracting-keywords skill可用

检查YAKE虚拟环境是否存在：

/home/claude/yake-venv/bin/python -c "import yake"

确认Python版本为3.8+：
```
python3 --version
```

Integration with Other Skills

与其他技能的集成

Built-in integration:

extracting-keywords: Automatically delegates keyword extraction to this skill's optimized YAKE venv with domain-specific stopwords

内置集成：

extracting-keywords：自动将关键词提取任务委托给该技能的优化YAKE虚拟环境，支持领域专属停用词

Example Sessions

会话示例

User: "Can you analyze the accounts I follow on Bluesky and tell me what topics they focus on?"

Claude:

bash

python scripts/bluesky_analyzer.py --following user-handle.bsky.social --stopwords ai

Based on the output, I can see you follow:

AI/ML researchers (15 accounts): Focus on LLM safety, alignment, interpretability
Software engineers (20 accounts): Web development, React, TypeScript, DevOps
Writers (8 accounts): Tech journalism, newsletters, long-form content
Scientists (7 accounts): Climate science, biotech, physics

User: "Find ML researchers in @alice's network"

Claude:

bash

python scripts/bluesky_analyzer.py --following alice.bsky.social --stopwords ai

I found 23 ML researchers in Alice's network:

8 working on LLM alignment and safety
6 focused on model evaluation and benchmarks
5 in ML infrastructure and MLOps
4 in computer vision and multimodal models

User: "Here's a list of 30 accounts, categorize them"

Claude:

bash

python scripts/bluesky_analyzer.py --file accounts.txt --stopwords ai

Categorized into:

Climate Tech (8 accounts)
Biotech (6 accounts)
Fintech (5 accounts)
AI/ML (7 accounts)
Other (4 accounts)

用户：“你能分析我在Bluesky上关注的账号，告诉我他们关注的主题是什么吗？”

Claude：

bash

python scripts/bluesky_analyzer.py --following user-handle.bsky.social --stopwords ai

根据输出结果，我可以看到你关注的账号分为：

AI/ML研究者（15个账号）：专注于LLM安全、对齐、可解释性
软件工程师（20个账号）：Web开发、React、TypeScript、DevOps
作者（8个账号）：科技新闻、通讯稿、长内容创作
科学家（7个账号）：气候科学、生物技术、物理学

用户：“在@alice的社交网络中寻找ML研究者”

Claude：

bash

python scripts/bluesky_analyzer.py --following alice.bsky.social --stopwords ai

我在Alice的社交网络中找到了23位ML研究者：

8位专注于LLM对齐与安全
6位专注于模型评估与基准测试
5位专注于ML基础设施与MLOps
4位专注于计算机视觉与多模态模型

用户：“这是30个账号的列表，帮我分类”

Claude：

bash

python scripts/bluesky_analyzer.py --file accounts.txt --stopwords ai

分类结果：

气候科技（8个账号）
生物技术（6个账号）
金融科技（5个账号）
AI/ML（7个账号）
其他（4个账号）