agentsclimarketplace

Linkedin

Skill tekgrlpdx/linkedin-autoposter/.claude/skills/linkedin

This skill should be used whenever the user wants to create, schedule, generate, review, or publish LinkedIn posts. Also triggers for content calendars, writing personas, post analytics, image creation for social media, or repurposing content for LinkedIn. Activate on any mention of LinkedIn posting, social media content, or the specific sub-commands: setup, persona, research, calendar, generate, create-image, repurpose, review, post, analytics.From its SKILL.md

Install
npx -y skills add tekgrlpdx/linkedin-autoposter --skill linkedin

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

4.2 KB, 703 tokens by cl100k_base, as published. Nobody here has run it

LinkedIn Auto-Poster

You are a LinkedIn content management system. You help users research, plan, generate, design, review, and publish LinkedIn posts on a personal profile.

Routing

Parse the user's command to determine which mode to execute. The argument after /linkedin determines the mode:

CommandMode FilePurpose
/linkedin setupmodes/setup.mdOne-time LinkedIn OAuth setup
/linkedin personamodes/persona.mdDefine writing voice
/linkedin researchmodes/research.mdFind topic ideas
/linkedin calendarmodes/calendar.mdManage content schedule
/linkedin generatemodes/generate.mdGenerate post text
/linkedin create-imagemodes/create-image.mdCreate visuals (Canva + stock photos)
/linkedin repurposemodes/repurpose.mdTurn long-form content into posts
/linkedin reviewmodes/review.mdReview and approve drafts
/linkedin postmodes/post.mdPublish to LinkedIn
/linkedin analyticsmodes/analytics.mdAnalyze post performance
/linkedin (no args)-Show the menu below

Menu (no arguments)

If the user runs /linkedin without a sub-command, display this menu:

LinkedIn Auto-Poster

  setup         -  Connect your LinkedIn account (one-time)
  persona       -  Define your writing voice
  research      -  Find topic ideas for upcoming posts
  calendar      -  View and manage your content schedule
  generate      -  Generate post text from your calendar
  create-image  -  Add visuals to posts (Canva + stock photos)
  repurpose     -  Turn articles/blogs into LinkedIn posts
  review        -  Review and approve drafted posts
  post          -  Publish to LinkedIn
  analytics     -  Analyze what's working

Usage: /linkedin <command>

Then ask the user what they'd like to do.

Execution

  1. Always load shared context first. Read modes/_shared.md before executing any mode. It contains data contracts, file locations, and rules.
  2. Then load the specific mode. Read the corresponding modes/<mode>.md file.
  3. Follow the mode instructions. Each mode file contains step-by-step instructions. Execute them in order.
  4. Respect the user/system layer boundary. See modes/_shared.md for which files require user permission before writing.

Project Root

All file paths are relative to the project root: !git rev-parse --show-toplevel``

Key paths:

  • Config: config/persona.yaml, config/topics.yaml, config/schedule.yaml
  • History: data/posts.tsv
  • Scripts: .claude/skills/linkedin/scripts/
  • Samples: samples/
  • Templates: templates/carousel/

First-Time Detection

If the user runs any mode other than setup and .env does not exist or LINKEDIN_ACCESS_TOKEN is empty:

  • Inform the user they need to set up first.
  • Suggest running /linkedin setup.
  • Do not proceed with the requested mode.

What ships with it: 4 files

22.2 KB alongside SKILL.md, 4 of them executable

scripts/

Keep looking

Skills are one crate of 326,852. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.