himself65/finance-skills / plugins/social-readers/skills/linkedin-reader
linkedin-reader
UnverifiedRead LinkedIn for financial research through opencli: the user's feed, and job search with location, seniority, job type, remote, company, and date filters. Use this skill whenever the user wants to check their LinkedIn feed, see what professionals or analysts are posting about a company, market, or earnings, gauge professional sentiment, or search finance and trading jobs on LinkedIn. Read-only: it cannot post, like, comment, connect, message, or apply.
LinkedIn Skill (Read-Only)
If your host has not already executed the shell probes below (for example, in Codex), run the commands inside the ! wrappers with its shell tool before choosing a setup path. Use the actual output; if shell access is unavailable, report that limitation.
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.
Step 1: Ensure opencli Is Installed and Ready
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:
# Install opencli globally
npm install -g @jackwener/opencli
If SETUP_NEEDED, guide the user through setup:
Setup
opencli requires Node.js >= 20 and a Chrome browser with the Browser Bridge extension:
- Install the Browser Bridge extension:
- Download the latest
opencli-extension-v{version}.zipfrom the GitHub Releases page - Unzip it, open
chrome://extensionsin Chrome, and enable Developer mode - Click Load unpacked and select the unzipped folder
- Download the latest
- Login to linkedin.com in Chrome — opencli reuses your existing browser session
- Verify connectivity:
opencli doctor
This auto-starts the daemon, verifies the extension is connected, and checks session health.
Common setup issues
| Symptom | Fix |
|---|---|
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 |
Step 2: Identify What the User Needs
Match the user's request to one of the read commands below, then use the corresponding command from references/commands.md.
| User Request | Command | Key Flags |
|---|---|---|
| Setup check | opencli doctor | — |
| Home feed / posts | opencli linkedin timeline | --limit N (default 20, max 100) |
| Search for jobs | opencli linkedin search "QUERY" | --location, --limit N (default 10, max 100), --details |
| Finance job search | opencli linkedin search "QUERY" | --experience-level, --job-type, --remote, --company, --date-posted, --start |
Step 3: Execute the Command
General pattern
# Read LinkedIn feed posts
opencli linkedin timeline --limit 20 -f json
# 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
# Detailed job listings with descriptions
opencli linkedin search "financial analyst" --details --limit 10 -f json
Key rules
- Check setup first — run
opencli doctorbefore any other command if unsure about connectivity - Use
-f jsonor-f yamlfor structured output when processing data programmatically - Use
-f csvwhen the user wants spreadsheet-compatible output - Use
--limit Nto control result count — start with 10-20 unless the user asks for more - For job search, use filters —
--location,--experience-level,--job-type,--remote,--date-postedto narrow results - Read-only — don't post, like, comment, connect, message, or apply to jobs
Output format flag (-f)
| Format | Flag | Best 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 |
Output columns
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.
Step 4: Present the Results
Lead with what matters for the user's research question rather than a raw dump. For feed posts, attribute each one (author, headline, text, reactions and comments, URL), highlight market commentary, analyst takes, and earnings reactions, and note the bullish or bearish lean and where views are consensus or contrarian. For job results, give title, company, location, salary when available, posting date, and the listing URL. Keep browser session details private.
Step 5: Diagnostics
If something isn't working, run:
opencli doctor
This checks daemon status, extension connectivity, and browser session health.
Error Reference
| Error | Cause | Fix |
|---|---|---|
Extension not connected | Browser Bridge not installed/enabled | Install extension and enable it in Chrome |
No session | Not logged into linkedin.com | Login to linkedin.com in Chrome |
AuthRequiredError | LinkedIn login wall detected | Refresh linkedin.com and log in again |
EmptyResultError | No results found for query | Broaden search terms or check feed has content |
| Rate limited | Too many requests | Wait a few minutes, then retry |
Reference Files
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.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 463k | Updated | Claude CodeCodex | Verified | Install |
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 463k | Updated | Claude CodeCodex | Verified | Install |
| discernment-nudgeanthropics/skillsAfter you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format. | Stars: 195k | Updated | Claude CodeCodex | Verified | Install |
| internal-commsanthropics/skillsA set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.). | Stars: 195k | Updated | Claude CodeCodex | Verified | Install |