agentleFS
ItamarZand88ItamarZand88/CLI-Anything-WEB/.claude/skills/linkedin-cli/SKILL.md

linkedin-cli

Skill215 starsChanged 3 months agoMITView on GitHub

Interacts with LinkedIn via the cli-web-linkedin command-line tool — search people/jobs/companies, view profiles and feed, create/edit/delete posts, react and comment, manage connections and invitations, read and send messages, view notifications, follow companies. Use when the user asks about LinkedIn or wants to search, post, network, or message on LinkedIn from the terminal. Prefer this CLI over fetching the LinkedIn website. Requires login.

  • Installs packages

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Every command accepts --json.

    line 50
  2. Very specific:

    Add sleep 3 between scripted invocations instead of tight loops — built-in inter-request delays only apply within a single process.

    line 68

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

cli-web-linkedin

Full LinkedIn client: search, profiles, feed, posting, reactions, comments, network, and messaging. All commands require auth login first. Install: pip install "cli-web-linkedin[browser]", then playwright install chromium.

Commands

GroupCommands
searchall|people|jobs|companies QUERY [--limit N] (default 10)
profileme, get USERNAME
feedfeed [--count N]
companycompany NAME (view page), company follow|unfollow COMPANY_URN
jobssearch QUERY [--limit N], get JOB_ID (full description)
postcreate TEXT, edit POST_URN TEXT, delete POST_URN, react POST_URN [--type LIKE|PRAISE|EMPATHY|INTEREST|APPRECIATION|ENTERTAINMENT], unreact POST_URN, comment POST_URN TEXT, edit-comment COMMENT_URN TEXT, delete-comment COMMENT_URN
notificationsnotifications [--limit N]
networkconnections [--limit N], invitations [--limit N], accept|decline INVITATION_URN, connect PROFILE_URN [-m MESSAGE]
messaginglist [--limit N], read CONVERSATION_URN [--limit N], send RECIPIENT TEXT (conversation or profile URN)
authlogin, status, logout

Examples

# Find people (returns name, headline, profile URL per result)
cli-web-linkedin search people "python developer" --limit 10 --json

# Job search, then full description
cli-web-linkedin jobs search "software engineer" --limit 5 --json
cli-web-linkedin jobs get 4388202530 --json

# Publish a post
cli-web-linkedin post create "Hello LinkedIn!" --json

# Pending invitations, then accept one (URN from the list)
cli-web-linkedin network invitations --json
cli-web-linkedin network accept "urn:li:invitation:123" --json

# Read recent messages
cli-web-linkedin messaging list --json
cli-web-linkedin messaging read "urn:li:msg_conversation:123" --json

JSON output

Every command accepts --json. Reads return the data object directly; writes return {"success": true, ...}. Errors return {"error": true, "code": "...", "message": "..."}.

Auth

cli-web-linkedin auth login      # browser-based LinkedIn login, stores li_at cookie
cli-web-linkedin auth status --json

Cookies live in ~/.config/cli-web-linkedin/auth.json; on 401/403 the CLI reloads them from disk, then refreshes via headless browser. For CI, set CLI_WEB_LINKEDIN_AUTH_JSON with the cookies JSON. Run doctor to diagnose auth problems.

Utilities

cli-web-linkedin doctor [--json] self-diagnoses the local setup (install, auth, dependencies). cli-web-linkedin mcp-serve serves the commands as MCP tools over stdio.

Agent tips

LinkedIn flags automated access aggressively; keep usage human-paced to protect the account:

  • Add sleep 3 between scripted invocations instead of tight loops — built-in inter-request delays only apply within a single process.
  • Stay under roughly 50 profile views and 150 searches per day.
  • URNs (post, comment, invitation, conversation) come from the JSON output of list/read commands — fetch them rather than constructing by hand.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.