linkedin-reader

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

LinkedIn Skill (Read-Only)

LinkedIn技能(只读模式)

Reads LinkedIn for financial research using opencli, a universal CLI tool that bridges web services to the terminal via browser session reuse.
This skill is read-only. It is designed for financial research: reading professional commentary on markets, monitoring analyst posts, searching finance/trading jobs, and tracking professional sentiment. It does NOT support posting, liking, commenting, connecting, messaging, or any write operations.
Important: opencli reuses your existing Chrome login session — no API keys or cookie extraction needed. Just be logged into linkedin.com in Chrome and have the Browser Bridge extension installed.

使用opencli读取LinkedIn内容用于金融研究,opencli是一款通用CLI工具,通过复用浏览器会话将Web服务对接至终端。
此技能为只读模式,专为金融研究设计:可读取市场相关的专业评论、监控分析师帖子、搜索金融/交易类岗位、追踪行业专业情绪。它不支持发布、点赞、评论、添加好友、发消息或任何写入操作。
注意事项:opencli会复用你现有的Chrome登录会话——无需API密钥或提取Cookie。你只需在Chrome中登录linkedin.com,并安装Browser Bridge扩展即可。

Step 1: Ensure opencli Is Installed and Ready

步骤1:确保opencli已安装且可用

Current environment status:
!`(command -v opencli && opencli doctor 2>&1 | head -5 && echo "READY" || echo "SETUP_NEEDED") 2>/dev/null || echo "NOT_INSTALLED"`
If the status above shows
READY
, skip to Step 2. If
NOT_INSTALLED
, install first:
bash
undefined
当前环境状态:
!`(command -v opencli && opencli doctor 2>&1 | head -5 && echo "READY" || echo "SETUP_NEEDED") 2>/dev/null || echo "NOT_INSTALLED"`
如果上方状态显示
READY
,请跳至步骤2。如果显示
NOT_INSTALLED
,请先安装:
bash
undefined

Install opencli globally

Install opencli globally

npm install -g @jackwener/opencli

If `SETUP_NEEDED`, guide the user through setup:
npm install -g @jackwener/opencli

如果显示`SETUP_NEEDED`,请引导用户完成以下设置:

Setup

设置

opencli requires a Chrome browser with the Browser Bridge extension:
  1. Install the Browser Bridge extension — follow the instructions from
    opencli doctor
    output
  2. Login to linkedin.com in Chrome — opencli reuses your existing browser session
  3. Verify connectivity:
bash
opencli doctor
This auto-starts the daemon, verifies the extension is connected, and checks session health.
opencli需要安装了Browser Bridge扩展的Chrome浏览器:
  1. 安装Browser Bridge扩展——按照
    opencli doctor
    输出的说明操作
  2. 在Chrome中登录linkedin.com——opencli会复用你现有的浏览器会话
  3. 验证连通性:
bash
opencli doctor
该命令会自动启动守护进程,验证扩展是否已连接,并检查会话健康状态。

Common setup issues

常见设置问题

SymptomFix
Extension not connected
Install Browser Bridge extension in Chrome and ensure it's enabled
Daemon not running
Run
opencli doctor
— it auto-starts the daemon
No session for linkedin.com
Login to linkedin.com in Chrome, then retry
AuthRequiredError
LinkedIn session expired — refresh linkedin.com in Chrome and log in again

现象修复方案
Extension not connected
在Chrome中安装Browser Bridge扩展并确保已启用
Daemon not running
运行
opencli doctor
——它会自动启动守护进程
No session for linkedin.com
在Chrome中登录linkedin.com后重试
AuthRequiredError
LinkedIn会话已过期——在Chrome中刷新linkedin.com并重新登录

Step 2: Identify What the User Needs

步骤2:识别用户需求

Match the user's request to one of the read commands below, then use the corresponding command from
references/commands.md
.
User RequestCommandKey Flags
Setup check
opencli doctor
Home feed / posts
opencli linkedin timeline
--limit N
Search for jobs
opencli linkedin search "QUERY"
--location
,
--limit N
,
--details
Finance job search
opencli linkedin search "QUERY"
--experience-level
,
--job-type
,
--remote

将用户请求匹配到下方的读取命令,然后使用
references/commands.md
中对应的命令。
用户请求命令核心参数
检查设置
opencli doctor
首页动态/帖子
opencli linkedin timeline
--limit N
搜索岗位
opencli linkedin search "QUERY"
--location
,
--limit N
,
--details
金融类岗位搜索
opencli linkedin search "QUERY"
--experience-level
,
--job-type
,
--remote

Step 3: Execute the Command

步骤3:执行命令

General pattern

通用使用示例

bash
undefined
bash
undefined

Read LinkedIn feed posts

Read LinkedIn feed posts

opencli linkedin timeline --limit 20 -f json
opencli linkedin timeline --limit 20 -f json

Search for finance/trading jobs

Search for finance/trading jobs

opencli linkedin search "quantitative analyst" --limit 10 -f json opencli linkedin search "portfolio manager" --location "New York" --limit 15 -f json
opencli linkedin search "quantitative analyst" --limit 10 -f json opencli linkedin search "portfolio manager" --location "New York" --limit 15 -f json

Detailed job listings with descriptions

Detailed job listings with descriptions

opencli linkedin search "financial analyst" --details --limit 10 -f json
undefined
opencli linkedin search "financial analyst" --details --limit 10 -f json
undefined

Key rules

核心规则

  1. Check setup first — run
    opencli doctor
    before any other command if unsure about connectivity
  2. Use
    -f json
    or
    -f yaml
    for structured output when processing data programmatically
  3. Use
    -f csv
    when the user wants spreadsheet-compatible output
  4. Use
    --limit N
    to control result count — start with 10-20 unless the user asks for more
  5. For job search, use filters
    --location
    ,
    --experience-level
    ,
    --job-type
    ,
    --remote
    ,
    --date-posted
    to narrow results
  6. NEVER execute write operations — this skill is read-only; do not post, like, comment, connect, message, or apply to jobs
  1. 优先检查设置——如果不确定连通性,在执行其他命令前先运行
    opencli doctor
  2. 使用
    -f json
    -f yaml
    ——当需要程序化处理数据时,使用该参数获取结构化输出
  3. 使用
    -f csv
    ——当用户需要可导入电子表格的输出时使用
  4. 使用
    --limit N
    ——控制返回结果数量,默认返回10-20条,除非用户要求更多
  5. 搜索岗位时使用过滤参数——
    --location
    (地点)、
    --experience-level
    (经验等级)、
    --job-type
    (工作类型)、
    --remote
    (远程)、
    --date-posted
    (发布日期)来缩小结果范围
  6. 绝对不要执行写入操作——此技能为只读模式,不要发布内容、点赞、评论、添加好友、发消息或申请岗位

Output format flag (
-f
)

输出格式参数(
-f

FormatFlagBest for
Table
-f table
(default)
Human-readable terminal output
JSON
-f json
Programmatic processing, LLM context
YAML
-f yaml
Structured output, readable
Markdown
-f md
Documentation, reports
CSV
-f csv
Spreadsheet export
格式参数适用场景
表格
-f table
(默认)
人类可读的终端输出
JSON
-f json
程序化处理、LLM上下文输入
YAML
-f yaml
结构化输出,可读性高
Markdown
-f md
文档、报告输出
CSV
-f csv
电子表格导出

Output columns

输出字段

Timeline posts include:
rank
,
author
,
author_url
,
headline
,
text
,
posted_at
,
reactions
,
comments
,
url
.
Job search results include:
rank
,
title
,
company
,
location
,
listed
,
salary
,
url
. With
--details
: also
description
,
apply_url
.

动态帖子包含字段:
rank
(排名)、
author
(作者)、
author_url
(作者主页链接)、
headline
(作者简介)、
text
(正文)、
posted_at
(发布时间)、
reactions
(互动数)、
comments
(评论数)、
url
(帖子链接)。
岗位搜索结果包含字段:
rank
(排名)、
title
(岗位名称)、
company
(公司)、
location
(地点)、
listed
(发布时间)、
salary
(薪资)、
url
(岗位链接)。添加
--details
参数时还会返回
description
(岗位描述)、
apply_url
(申请链接)。

Step 4: Present the Results

步骤4:展示结果

After fetching data, present it clearly for financial research:
  1. Summarize key content — highlight the most relevant posts or jobs for the user's research
  2. Include attribution — show author name, headline, post text, and engagement (reactions, comments)
  3. Provide URLs when the user might want to read the full post or job listing
  4. For feed posts, highlight market commentary, analyst takes, earnings reactions, and professional sentiment
  5. For job search results, present title, company, location, salary (when available), and posting date
  6. Flag sentiment — note bullish/bearish professional sentiment, consensus vs contrarian views
  7. Treat sessions as private — never expose browser session details

获取数据后,清晰展示内容以适配金融研究场景:
  1. 总结核心内容——高亮展示与用户研究最相关的帖子或岗位
  2. 包含来源信息——展示作者姓名、简介、帖子正文和互动数据(点赞、评论数)
  3. 提供链接——当用户可能需要阅读完整帖子或岗位详情时附上链接
  4. 针对动态帖子,高亮展示市场评论、分析师观点、盈利相关反馈和行业专业情绪
  5. 针对岗位搜索结果,展示岗位名称、公司、地点、薪资(如有)和发布日期
  6. 标记情绪倾向——标注看涨/看跌的行业专业情绪,共识观点与反向观点
  7. 会话隐私保护——永远不要泄露浏览器会话详情

Step 5: Diagnostics

步骤5:问题排查

If something isn't working, run:
bash
opencli doctor
This checks daemon status, extension connectivity, and browser session health.

如果运行出错,请执行:
bash
opencli doctor
该命令会检查守护进程状态、扩展连通性和浏览器会话健康状态。

Error Reference

错误参考

ErrorCauseFix
Extension not connected
Browser Bridge not installed/enabledInstall extension and enable it in Chrome
No session
Not logged into linkedin.comLogin to linkedin.com in Chrome
AuthRequiredError
LinkedIn login wall detectedRefresh linkedin.com and log in again
EmptyResultError
No results found for queryBroaden search terms or check feed has content
Rate limitedToo many requestsWait a few minutes, then retry

错误原因修复方案
Extension not connected
未安装/启用Browser Bridge扩展在Chrome中安装扩展并启用
No session
未登录linkedin.com在Chrome中登录linkedin.com
AuthRequiredError
检测到LinkedIn登录拦截刷新linkedin.com并重新登录
EmptyResultError
未搜索到对应结果扩大搜索关键词范围,或检查动态是否有内容
速率限制请求次数过多等待几分钟后重试

Reference Files

参考文件

  • references/commands.md
    — Complete read command reference with all flags, research workflows, and usage examples
Read the reference file when you need exact command syntax, research workflow patterns, or output details.
  • references/commands.md
    ——完整的读取命令参考,包含所有参数、研究工作流和使用示例
需要查询准确的命令语法、研究工作流模式或输出详情时,请阅读参考文件。