Skip to content
SkillModel-led1,017 tokens in use

li-post

Turns one raw idea into a LinkedIn post in your voice: three hook options from 21 formulas, one full draft, humanized and ready to paste.

3,760 stars on the repository MIT LicenseJakeschincariol/linkedin-agent-skill · skills/li-post
/plugin marketplace add Jakeschincariol/linkedin-agent-skill /plugin install linkedin-agent
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing li-post costs

96tokens idle
1,017tokens in use
3,439tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter12/15
  • Structure19/25
  • Examples12/15
  • Output10/15
  • Size15/15
  • Resources15/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Needs attention
  • Development activity28
  • Maintenance4
  • Community52
  • Maturity16
  • Momentum40

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.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers