Skip to content
SkillModel-led970 tokens in use

li-comment

Writes comments on other people's LinkedIn posts that read as a person with an opinion, from nine comment types, two options at a time.

3,760 stars on the repository MIT LicenseJakeschincariol/linkedin-agent-skill · skills/li-comment
/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-comment costs

66tokens idle
970tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. 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 →
Good
  • Frontmatter12/15
  • Structure11/25
  • Examples6/15
  • Output10/15
  • Size15/15
  • Resources10/15

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-comment drafts comments for posts you paste in. It picks from nine comment types by what the post is: add a datum, add the missing case, respectful disagreement, extend one line, ask the real question, the receipt, the correction, the reframe or the one-liner.

Each answer gives two options of different types and says which one to post. Comments run two to four sentences and never open with filler such as a generic compliment. A batch mode handles a round of five to ten posts.

What You Get

  • Two comment options of different types for each post, with a one-line reason for the one to post
  • A set of rules that cap comments at two to four sentences and ban empty openers and emoji openers
  • A batch mode that returns one comment per post for an engagement round of five to ten posts
  • A running note of who you commented on this week so the same few people do not get every comment

Common Use Cases

  • Commenting on a post from a person you want to be seen by
  • Disagreeing with a post without starting a fight
  • Running a daily twenty-minute engagement round across a list of posts
  • Correcting a factual error in a post politely and briefly

What Makes It Unique

It treats a comment as a choice among nine types and refuses to default to the first one. Every comment must say something specific enough that it could not sit under any other post on the topic. It never drives a browser, so it does not scrape the feed or publish on your behalf.

Under The Hood

The skill is instructions only, with no scripts. It works from post text you paste, and if you give a URL it cannot open it asks for the text. In batch mode it keeps a note of who you commented on by writing to a log file in your home folder under .claude/linkedin. It runs the options through the humanizer skill first. 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