LinkedIn Export Skill

LinkedIn导出数据处理技能

Parse LinkedIn GDPR data exports into structured JSON, then search messages, analyze connections, export to Markdown, and ingest into RLAMA for semantic search.

将LinkedIn GDPR数据导出文件解析为结构化JSON，随后可进行消息搜索、人脉分析、导出为Markdown格式，或导入至RLAMA进行语义搜索。

Prerequisites

前置要求

Python 3.10+ via
```
uv
```
LinkedIn GDPR export ZIP — Request at: LinkedIn → Settings → Data Privacy → Get a copy of your data
RLAMA + Ollama (optional, for semantic search ingestion)

Python 3.10+（通过
```
uv
```
安装）
LinkedIn GDPR导出ZIP文件 — 申请路径：LinkedIn → 设置 → 数据隐私 → 获取你的数据副本
RLAMA + Ollama（可选，用于语义搜索导入）

Quick Start

快速开始

bash

undefined

bash

undefined

1. Parse the export ZIP (run once)

1. 解析导出ZIP文件（仅需运行一次）

uv run ~/.claude/skills/linkedin-export/scripts/li_parse.py ~/Downloads/Basic_LinkedInDataExport_*.zip

2. Search, analyze, export, or ingest

2. 搜索、分析、导出或导入数据

uv run ~/.claude/skills/linkedin-export/scripts/li_search.py --list-partners uv run ~/.claude/skills/linkedin-export/scripts/li_network.py summary uv run ~/.claude/skills/linkedin-export/scripts/li_export.py all --output ~/linkedin-archive/ uv run ~/.claude/skills/linkedin-export/scripts/li_ingest.py


All scripts read from `~/.claude/skills/linkedin-export/data/parsed.json`. Parse once, query many times.

---

uv run ~/.claude/skills/linkedin-export/scripts/li_search.py --list-partners uv run ~/.claude/skills/linkedin-export/scripts/li_network.py summary uv run ~/.claude/skills/linkedin-export/scripts/li_export.py all --output ~/linkedin-archive/ uv run ~/.claude/skills/linkedin-export/scripts/li_ingest.py


所有脚本均读取`~/.claude/skills/linkedin-export/data/parsed.json`文件。只需解析一次，即可多次查询。

---

Parse —

li_parse.py

解析工具 —

li_parse.py

Unzip and parse all CSVs from the LinkedIn GDPR export into structured JSON.

bash

uv run ~/.claude/skills/linkedin-export/scripts/li_parse.py <linkedin-export.zip>
uv run ~/.claude/skills/linkedin-export/scripts/li_parse.py <zip> --output /custom/path.json

Output:

~/.claude/skills/linkedin-export/data/parsed.json

Parses: messages, connections, profile, positions, education, skills, endorsements, invitations, recommendations, shares, reactions, certifications.

Auto-detects CSV column names (case-insensitive) to handle LinkedIn format changes between exports.

将LinkedIn GDPR导出文件中的所有CSV解压并解析为结构化JSON格式。

bash

uv run ~/.claude/skills/linkedin-export/scripts/li_parse.py <linkedin-export.zip>
uv run ~/.claude/skills/linkedin-export/scripts/li_parse.py <zip> --output /custom/path.json

输出文件：

~/.claude/skills/linkedin-export/data/parsed.json

可解析内容：消息、人脉、个人资料、工作经历、教育背景、技能、技能认可、人脉邀请、推荐信、动态分享、互动反应、证书。

自动检测CSV列名（不区分大小写），以适配不同版本LinkedIn导出文件的格式变化。

Search Messages —

li_search.py

消息搜索工具 —

li_search.py

Search messages by person, keyword, date range, or combination.

bash

undefined

按联系人、关键词、日期范围或组合条件搜索消息。

bash

undefined

Search by person

按联系人搜索

uv run ~/.claude/skills/linkedin-export/scripts/li_search.py --person "Jane Doe"

Search by keyword

按关键词搜索

uv run ~/.claude/skills/linkedin-export/scripts/li_search.py --keyword "project proposal"

Date range

按日期范围搜索

uv run ~/.claude/skills/linkedin-export/scripts/li_search.py --after 2025-01-01 --before 2025-06-01

Combined filters

组合条件过滤

uv run ~/.claude/skills/linkedin-export/scripts/li_search.py --person "Jane" --keyword "meeting" --after 2025-06-01

Full conversation by ID

按会话ID查看完整对话

uv run ~/.claude/skills/linkedin-export/scripts/li_search.py --conversation "CONVERSATION_ID"

List all conversation partners (sorted by message count)

列出所有对话联系人（按消息数量排序）

uv run ~/.claude/skills/linkedin-export/scripts/li_search.py --list-partners

Show context around matches

显示匹配结果的上下文内容

uv run ~/.claude/skills/linkedin-export/scripts/li_search.py --keyword "AI" --context 3

Full message content + JSON output

显示完整消息内容并输出JSON格式

uv run ~/.claude/skills/linkedin-export/scripts/li_search.py --keyword "proposal" --full --json


**Flags**: `--person`, `--keyword`, `--after`, `--before`, `--conversation`, `--list-partners`, `--context N`, `--full`, `--limit N`, `--json`

---

uv run ~/.claude/skills/linkedin-export/scripts/li_search.py --keyword "proposal" --full --json


**可用参数**：`--person`, `--keyword`, `--after`, `--before`, `--conversation`, `--list-partners`, `--context N`, `--full`, `--limit N`, `--json`

---

Network Analysis —

li_network.py

人脉网络分析工具 —

li_network.py

Analyze the connection graph — companies, roles, timeline.

bash

undefined

分析人脉关系图谱——包括所属公司、职位、时间线等。

bash

undefined

Summary stats

查看汇总统计

uv run ~/.claude/skills/linkedin-export/scripts/li_network.py summary

Top companies by connection count

按人脉数量查看Top公司

uv run ~/.claude/skills/linkedin-export/scripts/li_network.py companies --top 20

Connection timeline

人脉增长时间线

uv run ~/.claude/skills/linkedin-export/scripts/li_network.py timeline --by year uv run ~/.claude/skills/linkedin-export/scripts/li_network.py timeline --by month

Role/title distribution

职位/头衔分布

uv run ~/.claude/skills/linkedin-export/scripts/li_network.py roles --top 20

Search connections

搜索人脉

uv run ~/.claude/skills/linkedin-export/scripts/li_network.py search "Anthropic"

Export connections to CSV or JSON

将人脉导出为CSV或JSON格式

uv run ~/.claude/skills/linkedin-export/scripts/li_network.py export --format csv uv run ~/.claude/skills/linkedin-export/scripts/li_network.py export --format json


**Subcommands**: `summary`, `companies`, `timeline`, `roles`, `search`, `export`

---

uv run ~/.claude/skills/linkedin-export/scripts/li_network.py export --format csv uv run ~/.claude/skills/linkedin-export/scripts/li_network.py export --format json


**可用子命令**：`summary`, `companies`, `timeline`, `roles`, `search`, `export`

---

Export to Markdown —

li_export.py

Markdown导出工具 —

li_export.py

Convert parsed data to clean Markdown files.

bash

undefined

将解析后的数据转换为整洁的Markdown文件。

bash

undefined

Export messages (one file per conversation)

导出消息（每个对话一个文件）

uv run ~/.claude/skills/linkedin-export/scripts/li_export.py messages --output ~/linkedin-archive/messages/

Export connections as Markdown table

将人脉导出为Markdown表格

uv run ~/.claude/skills/linkedin-export/scripts/li_export.py connections --output ~/linkedin-archive/connections.md

Export everything

导出所有数据

uv run ~/.claude/skills/linkedin-export/scripts/li_export.py all --output ~/linkedin-archive/

Export RLAMA-optimized documents

导出适配RLAMA的优化文档

uv run ~/.claude/skills/linkedin-export/scripts/li_export.py rlama --output ~/linkedin-archive/rlama/


**Subcommands**: `messages`, `connections`, `all`, `rlama`

---

uv run ~/.claude/skills/linkedin-export/scripts/li_export.py rlama --output ~/linkedin-archive/rlama/


**可用子命令**：`messages`, `connections`, `all`, `rlama`

---

RLAMA Ingestion —

li_ingest.py

RLAMA导入工具 —

li_ingest.py

Prepare RLAMA-optimized documents and create a semantic search collection.

bash

undefined

生成适配RLAMA的优化文档并创建语义搜索集合。

bash

undefined

Full pipeline: prepare docs + create RLAMA collection

完整流程：生成文档 + 创建RLAMA集合

uv run ~/.claude/skills/linkedin-export/scripts/li_ingest.py

Prepare docs only (no RLAMA required)

仅生成文档（无需RLAMA）

uv run ~/.claude/skills/linkedin-export/scripts/li_ingest.py --prepare-only

Rebuild existing collection

重建现有集合

uv run ~/.claude/skills/linkedin-export/scripts/li_ingest.py --rebuild


**Collection**: `linkedin-tdimino` (fixed/600/100 chunking, BM25-heavy hybrid search)

**Query examples**:
```bash
rlama run linkedin-tdimino --query "What did I discuss with [person]?"
rlama run linkedin-tdimino --query "Who works at [company]?"
rlama run linkedin-tdimino --query "What are my top skills?"

RLAMA document structure:

messages-conversations-{a-f,g-l,m-r,s-z}.md

— Conversations grouped alphabetically

```
connections-companies.md
```
— Connections by company
```
connections-timeline.md
```
— Connections by year
```
profile-positions-education.md
```
— Resume data
```
endorsements-skills.md
```
— Skills and endorsements
```
shares-reactions.md
```
— Posts and activity
```
INDEX.md
```
— Collection metadata

uv run ~/.claude/skills/linkedin-export/scripts/li_ingest.py --rebuild


**集合名称**：`linkedin-tdimino`（固定600/100分块，侧重BM25的混合搜索）

**查询示例**：
```bash
rlama run linkedin-tdimino --query "我和[某人]讨论过什么内容？"
rlama run linkedin-tdimino --query "谁在[某公司]工作？"
rlama run linkedin-tdimino --query "我的核心技能有哪些？"

RLAMA文档结构：

messages-conversations-{a-f,g-l,m-r,s-z}.md

— 按字母分组的对话内容

```
connections-companies.md
```
— 按公司分类的人脉
```
connections-timeline.md
```
— 按年份分类的人脉
```
profile-positions-education.md
```
— 简历相关数据
```
endorsements-skills.md
```
— 技能与技能认可
```
shares-reactions.md
```
— 动态与互动
```
INDEX.md
```
— 集合元数据

Data Format Reference

数据格式参考

See

references/linkedin-export-format.md

for complete CSV column documentation.

Key files in the LinkedIn export ZIP:

CSV	Contents
`messages.csv`	All messages and InMail
`Connections.csv`	1st-degree connections
`Profile.csv`	Profile data
`Positions.csv`	Work history
`Education.csv`	Education
`Skills.csv`	Listed skills
`Endorsement_Received_Info.csv`	Endorsements
`Invitations.csv`	Connection requests
`Recommendations_Received.csv`	Recommendations
`Shares.csv`	Posts and shares
`Reactions.csv`	Post reactions
`Certifications.csv`	Certifications

完整CSV列说明请查看

references/linkedin-export-format.md

。

LinkedIn导出ZIP中的关键文件：

CSV文件	内容
`messages.csv`	所有消息和站内信
`Connections.csv`	一级人脉
`Profile.csv`	个人资料数据
`Positions.csv`	工作经历
`Education.csv`	教育背景
`Skills.csv`	已列出的技能
`Endorsement_Received_Info.csv`	获得的技能认可
`Invitations.csv`	人脉邀请
`Recommendations_Received.csv`	收到的推荐信
`Shares.csv`	动态与分享内容
`Reactions.csv`	动态互动反应
`Certifications.csv`	证书

Script Selection Guide

脚本选择指南

Task	Script	Example
First-time setup	`li_parse.py`	Parse the ZIP
Find a conversation	`li_search.py --person`	Search by person name
Find a topic	`li_search.py --keyword`	Search by keyword
Who do I talk to most?	`li_search.py --list-partners`	Sorted partner list
Company breakdown	`li_network.py companies`	Top companies
Network growth	`li_network.py timeline`	Connections over time
Archive messages	`li_export.py messages`	Markdown per conversation
Semantic search	`li_ingest.py`	RLAMA collection

任务	对应脚本	示例
首次配置	`li_parse.py`	解析ZIP文件
查找特定对话	`li_search.py --person`	按联系人姓名搜索
查找特定主题	`li_search.py --keyword`	按关键词搜索
查看对话最频繁的联系人	`li_search.py --list-partners`	按消息数排序的联系人列表
公司分布统计	`li_network.py companies`	查看Top公司
人脉增长趋势	`li_network.py timeline`	按时间查看人脉增长
归档消息	`li_export.py messages`	按对话导出为Markdown
语义搜索	`li_ingest.py`	创建RLAMA搜索集合

linkedin-export

Original

Translation

LinkedIn Export Skill

LinkedIn导出数据处理技能

Prerequisites

前置要求

Quick Start

快速开始

1. Parse the export ZIP (run once)

1. 解析导出ZIP文件（仅需运行一次）

2. Search, analyze, export, or ingest

2. 搜索、分析、导出或导入数据

Parse — li_parse.py

解析工具 — li_parse.py

Search Messages — li_search.py

消息搜索工具 — li_search.py

Search by person

按联系人搜索

Search by keyword

按关键词搜索

Date range

按日期范围搜索

Combined filters

组合条件过滤

Full conversation by ID

按会话ID查看完整对话

List all conversation partners (sorted by message count)

列出所有对话联系人（按消息数量排序）

Show context around matches

显示匹配结果的上下文内容

Full message content + JSON output

显示完整消息内容并输出JSON格式

Network Analysis — li_network.py

人脉网络分析工具 — li_network.py

Summary stats

查看汇总统计

Top companies by connection count

按人脉数量查看Top公司

Connection timeline

人脉增长时间线

Role/title distribution

职位/头衔分布

Search connections

搜索人脉

Export connections to CSV or JSON

将人脉导出为CSV或JSON格式

Export to Markdown — li_export.py

Markdown导出工具 — li_export.py

Export messages (one file per conversation)

导出消息（每个对话一个文件）

Export connections as Markdown table

将人脉导出为Markdown表格

Export everything

导出所有数据

Export RLAMA-optimized documents

导出适配RLAMA的优化文档

RLAMA Ingestion — li_ingest.py

RLAMA导入工具 — li_ingest.py

Full pipeline: prepare docs + create RLAMA collection

完整流程：生成文档 + 创建RLAMA集合

Prepare docs only (no RLAMA required)

仅生成文档（无需RLAMA）

Rebuild existing collection

重建现有集合

Data Format Reference

数据格式参考

Script Selection Guide

脚本选择指南

Parse —
`li_parse.py`

解析工具 —
`li_parse.py`

Search Messages —
`li_search.py`

消息搜索工具 —
`li_search.py`

Network Analysis —
`li_network.py`

人脉网络分析工具 —
`li_network.py`

Export to Markdown —
`li_export.py`

Markdown导出工具 —
`li_export.py`

RLAMA Ingestion —
`li_ingest.py`

RLAMA导入工具 —
`li_ingest.py`