li-post writes a LinkedIn post from a raw idea. It reads your voice profile (or builds one from three of your past posts), picks three hooks from a file of 21 formulas, drafts the post on the strongest one and runs it through the humanizer before you see it.
The result is a copy-ready block with the hook used, the length, the humanizer result and a suggested posting time. It never publishes. On your yes, it logs the post so the audit skill has a history.
What You Get
- Three hook options from different formulas, with one recommended and a reason
- One full draft in your voice, humanized before it is shown
- A copy-ready block with hook number, length, humanizer result and a posting time from your plan
- An entry in your post log on approval, recording the date, hook and first line
Common Use Cases
- Writing a post from a client result or a mistake you made
- Picking between hook formulas for the same idea
- Putting a link in the first comment and keeping the body clean
- Building a voice profile from three of your own posts
What Makes It Unique
It is built around a hooks file of 21 formulas, each with a template, a filled example, its use and the usual way it gets ruined. It insists on a number for every claim and leaves a placeholder when you have not given one, so it never invents metrics. Every draft passes through the humanizer, and nothing is published without your explicit yes.
Under The Hood
The skill reads your voice profile at ~/.claude/linkedin/voice.md and the hooks.json file in its folder. If the voice file is missing it asks for three past posts and writes the file, and on your approval it appends to ~/.claude/linkedin/log.md, so it writes local files. It calls the humanizer skill, which runs Python scripts on your machine. It does not fetch web pages, call APIs or post to LinkedIn.