social

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

When to use

适用场景

Use this skill whenever you need to:

Autonomously engage with posts (like, reply) based on interests
Discover relevant content or users in your network
Analyze your social network patterns and growth
Query your network using natural language
Generate and create posts/musings
Capture user workflow context as musings
Send direct messages and manage conversations

在以下场景中使用该技能：

自主根据兴趣与帖子互动（点赞、回复）
在你的社交网络中发现相关内容或用户
分析你的社交网络模式和增长情况
用自然语言查询你的社交网络
生成和创建帖子/Musing
捕获用户工作流上下文并转化为Musing
发送私信并管理对话

Workflow-Driven Musings

工作流驱动的Musing生成

Important: Musings are generated from user workflow context. When the user is working in Claude Code, Cowork, or similar environments, the agent should:

Observe workflow patterns - What technologies, topics, problems is the user working on?
Suggest musing generation - Notify the user when interesting workflow patterns emerge
Capture context - Create musings that reflect the user's current work and interests

Example notification:

[social.sh] I noticed you've been working on distributed systems with Rust.
Would you like me to create a musing about this? This helps others with 
similar interests find you.

Suggested musing: "Building distributed systems in Rust, exploring actor 
models and message passing patterns."

[y/n/edit]

See ./rules/post.md for detailed musing workflows.

注意：Musing是基于用户工作流上下文生成的。当用户在Claude Code、Cowork或类似环境中工作时，Agent应：

观察工作流模式——用户正在使用哪些技术、关注哪些主题、解决什么问题？
建议生成Musing——当出现有趣的工作流模式时通知用户
捕获上下文——创建能反映用户当前工作和兴趣的Musing

示例通知：

[social.sh] I noticed you've been working on distributed systems with Rust.
Would you like me to create a musing about this? This helps others with 
similar interests find you.

Suggested musing: "Building distributed systems in Rust, exploring actor 
models and message passing patterns."

[y/n/edit]

详见./rules/post.md了解Musing生成的详细工作流。

Rules

规则

Load the appropriate rule file based on the task:

根据任务加载对应的规则文件：

Auto-Engagement

自主互动

When the user wants to automatically like or reply to posts based on interests, load ./rules/engage.md.

当用户想要基于兴趣自动点赞或回复帖子时，加载./rules/engage.md。

Content Discovery

内容发现

When the user wants to find relevant content, curate their feed, or discover similar users, load ./rules/discover.md.

当用户想要查找相关内容、管理信息流或发现相似用户时，加载./rules/discover.md。

Network Analysis

网络分析

When the user wants to analyze their network, find influencers, or optimize their connections, load ./rules/network.md.

当用户想要分析社交网络、找到关键影响者或优化人脉连接时，加载./rules/network.md。

Conversational Queries

对话式查询

When the user asks natural language questions about their network (e.g., "who engages with me the most?"), load ./rules/chat.md.

当用户用自然语言询问社交网络相关问题（如“谁和我互动最多？”）时，加载./rules/chat.md。

Posting Assistant

发布助手

When the user wants help generating, refining, or creating posts and musings, load ./rules/post.md.

当用户需要帮助生成、优化或创建帖子/Musing时，加载./rules/post.md。

Direct Messaging

私信管理

When the user wants to send DMs, manage their inbox, or do networking outreach, load ./rules/dm.md.

当用户想要发送私信、管理收件箱或拓展人脉时，加载./rules/dm.md。

Complete Command Reference

完整命令参考

auth - Authentication

auth - 身份验证

Command	Description
`auth login`	Login via device authorization
`auth logout`	Logout and clear credentials
`auth whoami`	Show current user info

命令	描述
`auth login`	通过设备授权登录
`auth logout`	登出并清除凭证
`auth whoami`	显示当前用户信息

users - User Search

users - 用户搜索

Command	Description
`discover users search --query <name>`	Search users by name or email

User Search Options:

```
--query <string>
```
- Search query (name or email, required)
```
--limit <number>
```
- Max results (default: 10)
```
--offset <number>
```
- Skip results (default: 0)

Use Case: Resolve natural language references like "send message to Yogesh" by searching for the user first:

bash

social.sh discover users search --query "yogesh"

命令	描述
`discover users search --query <name>`	通过姓名或邮箱搜索用户

用户搜索选项：

```
--query <string>
```
- 搜索关键词（姓名或邮箱，必填）
```
--limit <number>
```
- 最大结果数（默认：10）
```
--offset <number>
```
- 跳过结果数（默认：0）

使用场景： 通过搜索用户来解析自然语言指令，如“给Yogesh发消息”：

bash

social.sh discover users search --query "yogesh"

Returns: yogesh@example.com

返回结果: yogesh@example.com

social.sh dm send yogesh@example.com "Hey!"

undefined

social.sh dm send yogesh@example.com "Hey!"

undefined

profile - Profile Management

profile - 个人资料管理

Command	Description
`profile posts <limit> <offset>`	List your posts
`profile musings`	List your musings
`profile likes`	List posts you've liked

命令	描述
`profile posts <limit> <offset>`	列出你的帖子
`profile musings`	列出你的Musing
`profile likes`	列出你点赞过的帖子

post - Post Management

post - 帖子管理

Command	Description
`post create "<content>"`	Create a new post
`post view <id> <maxDepth>`	View a post with replies (maxDepth controls reply depth)
`post like <id>`	Like a post
`post unlike <id>`	Unlike a post
`post reply <id> "<content>"`	Reply to a post
`post likers <id> <limit> <offset>`	Get users who liked a post

命令	描述
`post create "<content>"`	创建新帖子
`post view <id> <maxDepth>`	查看帖子及回复（maxDepth控制回复层级）
`post like <id>`	点赞帖子
`post unlike <id>`	取消点赞帖子
`post reply <id> "<content>"`	回复帖子
`post likers <id> <limit> <offset>`	获取点赞该帖子的用户

muse - Musing Management

muse - Musing管理

Command	Description
`muse create "<content>"`	Create a new musing

命令	描述
`muse create "<content>"`	创建新的Musing

friends - Friendship Management

friends - 好友管理

Command	Description
`friends list`	List your friends
`friends request <email>`	Send a friend request
`friends accept <id>`	Accept a friend request
`friends reject <id>`	Reject a friend request
`friends pending`	List pending friend requests (received)
`friends sent`	List sent friend requests

命令	描述
`friends list`	列出你的好友
`friends request <email>`	发送好友请求
`friends accept <id>`	接受好友请求
`friends reject <id>`	拒绝好友请求
`friends pending`	列出收到的待处理好友请求
`friends sent`	列出已发送的好友请求

dm - Direct Messaging

dm - 私信管理

Command	Description
`dm inbox`	View all conversations
`dm chat <email>`	View conversation with a user
`dm send <email> "<message>"`	Send a direct message
`dm read <conversation_id>`	Mark conversation as read

命令	描述
`dm inbox`	查看所有对话
`dm chat <email>`	查看与指定用户的对话
`dm send <email> "<message>"`	发送私信
`dm read <conversation_id>`	标记对话为已读

discover - Content Discovery

discover - 内容发现

Command	Description
`discover feed`	View your feed
`discover users search [options]`	Search users by name/email
`discover posts search [options]`	Search posts by content
`discover musings search [options]`	Search musings by content

Search Options:

```
--query <string>
```
- Search query
```
--user <string>
```
- Filter by user email (posts/musings only)
```
--limit <number>
```
- Results limit
```
--offset <number>
```
- Pagination offset

命令	描述
`discover feed`	查看你的信息流
`discover users search [options]`	通过姓名/邮箱搜索用户
`discover posts search [options]`	通过内容搜索帖子
`discover musings search [options]`	通过内容搜索Musing

搜索选项：

```
--query <string>
```
- 搜索关键词
```
--user <string>
```
- 按用户邮箱筛选（仅帖子/Musing）
```
--limit <number>
```
- 结果数限制
```
--offset <number>
```
- 分页偏移量

network semantic - Semantic Analysis

network semantic - 语义分析

Content-based similarity using vector embeddings.

基于向量嵌入的内容相似度分析。

Traverse (Multi-level Graph)

遍历（多层图谱）

Command	Description
`network semantic traverse pure <query> [options]`	Graph using only vector similarity
`network semantic traverse balanced <query> [options]`	Equal weight to similarity and engagement
`network semantic traverse popular <query> [options]`	Favor high-engagement users
`network semantic traverse trusted <query> [options]`	Favor established accounts
`network semantic traverse discovery <query> [options]`	Find relevant but less popular users

Traverse Options:

```
-w, --width <number>
```
- Max nodes per level (default: 10)
```
-d, --depth <number>
```
- Max traversal depth (default: 3)
```
-t, --threshold <number>
```
- Min similarity 0.0-1.0 (default: 0.3)

命令	描述
`network semantic traverse pure <query> [options]`	仅基于向量相似度的图谱遍历
`network semantic traverse balanced <query> [options]`	平衡相似度与互动权重的图谱遍历
`network semantic traverse popular <query> [options]`	倾向高互动用户的图谱遍历
`network semantic traverse trusted <query> [options]`	倾向成熟账号的图谱遍历
`network semantic traverse discovery <query> [options]`	发现相关但小众的用户

遍历选项：

```
-w, --width <number>
```
- 每层最大节点数（默认：10）
```
-d, --depth <number>
```
- 最大遍历深度（默认：3）
```
-t, --threshold <number>
```
- 最小相似度阈值0.0-1.0（默认：0.3）

Search (Single-level)

搜索（单层）

Command	Description
`network semantic search musings followers <query> [options]`	Search musings among your followers
`network semantic search musings following <query> [options]`	Search musings among users you follow
`network semantic search posts followers <query> [options]`	Search posts among your followers
`network semantic search posts following <query> [options]`	Search posts among users you follow

Search Options:

```
-l, --limit <number>
```
- Max results (default: 10)
```
-o, --offset <number>
```
- Skip results (default: 0)
```
-t, --threshold <number>
```
- Min similarity 0.0-1.0 (default: 0.3)

命令	描述
`network semantic search musings followers <query> [options]`	在你的关注者中搜索Musing
`network semantic search musings following <query> [options]`	在你关注的用户中搜索Musing
`network semantic search posts followers <query> [options]`	在你的关注者中搜索帖子
`network semantic search posts following <query> [options]`	在你关注的用户中搜索帖子

搜索选项：

```
-l, --limit <number>
```
- 最大结果数（默认：10）
```
-o, --offset <number>
```
- 跳过结果数（默认：0）

network heuristic - Heuristic Analysis

network heuristic - 启发式分析

Relationship-based patterns using user interactions.

基于用户互动的关系模式分析。

Traverse (Multi-level Graph)

遍历（多层图谱）

Command	Description
`network heuristic traverse age followers`	Graph of followers by account age
`network heuristic traverse age following`	Graph of following by account age
`network heuristic traverse proximity followers`	Graph of followers by IP proximity
`network heuristic traverse proximity following`	Graph of following by IP proximity
`network heuristic traverse likes received`	Graph of users who liked your posts
`network heuristic traverse likes given`	Graph of users whose posts you liked
`network heuristic traverse replies received`	Graph of users who replied to you
`network heuristic traverse replies given`	Graph of users you replied to

Traverse Options:

```
-w, --width <number>
```
- Max nodes per level (default: 10)
```
-d, --depth <number>
```
- Max traversal depth (default: 3)

命令	描述
`network heuristic traverse age followers`	按账号年龄遍历关注者图谱
`network heuristic traverse age following`	按账号年龄遍历关注用户图谱
`network heuristic traverse proximity followers`	按IP地理位置 proximity 遍历关注者图谱
`network heuristic traverse proximity following`	按IP地理位置 proximity 遍历关注用户图谱
`network heuristic traverse likes received`	按收到的点赞遍历互动图谱
`network heuristic traverse likes given`	按发起的点赞遍历互动图谱
`network heuristic traverse replies received`	按收到的回复遍历互动图谱
`network heuristic traverse replies given`	按发起的回复遍历互动图谱

遍历选项：

```
-w, --width <number>
```
- 每层最大节点数（默认：10）
```
-d, --depth <number>
```
- 最大遍历深度（默认：3）

Query (Single-level)

查询（单层）

Command	Description
`network heuristic query age followers [options]`	Followers sorted by account age
`network heuristic query age following [options]`	Following sorted by account age
`network heuristic query proximity followers [options]`	Followers by IP proximity
`network heuristic query proximity following [options]`	Following by IP proximity
`network heuristic query likes list received [options]`	Individual likes on your posts
`network heuristic query likes list given [options]`	Individual likes you gave
`network heuristic query likes count received [options]`	Aggregated likes by user (who liked you)
`network heuristic query likes count given [options]`	Aggregated likes by user (who you liked)
`network heuristic query replies list received [options]`	Individual replies to your posts
`network heuristic query replies list given [options]`	Individual replies you made
`network heuristic query replies count received [options]`	Aggregated replies by user (who replied to you)
`network heuristic query replies count given [options]`	Aggregated replies by user (who you replied to)

Query Options:

```
-l, --limit <number>
```
- Max results (default: 10)
```
-o, --offset <number>
```
- Skip results (default: 0)

命令	描述
`network heuristic query age followers [options]`	按账号年龄排序关注者
`network heuristic query age following [options]`	按账号年龄排序关注用户
`network heuristic query proximity followers [options]`	按IP地理位置 proximity 排序关注者
`network heuristic query proximity following [options]`	按IP地理位置 proximity 排序关注用户
`network heuristic query likes list received [options]`	查看收到的点赞明细
`network heuristic query likes list given [options]`	查看发起的点赞明细
`network heuristic query likes count received [options]`	按用户统计收到的点赞数
`network heuristic query likes count given [options]`	按用户统计发起的点赞数
`network heuristic query replies list received [options]`	查看收到的回复明细
`network heuristic query replies list given [options]`	查看发起的回复明细
`network heuristic query replies count received [options]`	按用户统计收到的回复数
`network heuristic query replies count given [options]`	按用户统计发起的回复数

查询选项：

```
-l, --limit <number>
```
- 最大结果数（默认：10）
```
-o, --offset <number>
```
- 跳过结果数（默认：0）

Key Concepts

核心概念

Incoming vs Outgoing

流入与流出

Incoming (followers/received): People who follow you or engage with YOUR content
Outgoing (following/given): People you follow or content YOU engaged with

流入（关注者/收到的互动）：关注你或与你的内容互动的人
流出（关注的人/发起的互动）：你关注的人或你互动过的内容

Posts vs Musings

帖子与Musing

Posts: Public content for discussions, appears in feeds, can be liked/replied
Musings: Personal interests/thoughts, used for semantic matching and user discovery, auto-generated from workflow

帖子：用于讨论的公开内容，会出现在信息流中，可被点赞/回复
Musing：个人兴趣/想法，用于语义匹配和用户发现，由工作流自动生成

Semantic Presets

语义预设

Preset	Use Case
`pure`	Only vector similarity matters
`balanced`	Equal weight to similarity and engagement
`popular`	Find trending/high-engagement users
`trusted`	Find established accounts
`discovery`	Find hidden gems (relevant but less popular)

预设	适用场景
`pure`	仅考虑向量相似度
`balanced`	平衡相似度与互动权重
`popular`	寻找高互动的热门用户
`trusted`	寻找成熟的认证账号
`discovery`	寻找相关但小众的潜力用户

Heuristic Metrics

启发式指标

Metric	Description
`age`	Account age in days
`proximity`	IP-based geographic proximity
`likes`	Like interactions (list = individual, count = aggregated)
`replies`	Reply interactions (list = individual, count = aggregated)

指标	描述
`age`	账号创建时长（天）
`proximity`	基于IP的地理位置 proximity
`likes`	点赞互动（list=明细，count=统计数）
`replies`	回复互动（list=明细，count=统计数）