Linkedin Post Generator

Turns meeting transcripts, Slack threads, and random notes into LinkedIn posts that sound like you actually wrote them. The setup is thoughtful: you feed it three posts in your style, it analyzes your tone and structure, then generates options from whatever source material you dump in. It pulls from Fireflies, Slack, and Google Drive automatically if you want, and has built-in confidentiality filters to strip financials and client names. The whole thing runs locally with your style profile stored in your config directory. It's basically ghostwriting yourself, which feels strange but honestly saves the friction of staring at a blank LinkedIn composer.

skills.sh installs: 304
GitHub stars: 15
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add casper-studios/casper-marketplace --skill linkedin-post-generator --agent claude-code

Installs into .claude/skills of the current project.

Files

LinkedIn Post Generator

Generate LinkedIn posts from shared source material, written in each user's personal style.

How It Works

Personal style profile — stored locally at ~/.config/casper/linkedin-style.md (never committed)
Source config — stored locally at ~/.config/casper/linkedin-sources.md (never committed)
Shared source material — meeting transcripts, Slack dumps, docs in source-material/
Prompt template — extraction rules, voice guidelines, few-shot examples in references/prompt-template.md