Skip to content
SkillModel-led688 tokens in use

li-reply

Handles the comment thread under your own LinkedIn post: sorts every comment by value and drafts the replies, from leads to critics.

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

72tokens idle
688tokens 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
  • Structure17/25
  • Examples9/15
  • 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-reply works on the comments under your own LinkedIn posts. You paste the thread and it sorts each comment into lead, substance, peer, support or noise, states the counts and writes replies in that order, stopping when the value stops.

Replies answer the question asked, use the person’s name once, match their length and handle critics by conceding the true part first. Nothing is posted until you say yes and paste the replies yourself.

What You Get

  • A count of comments per bucket: lead, substance, peer, support and noise
  • Public replies to leads that answer fully and end with one sentence offering help
  • Longer replies to substantive comments and critics, and short replies of 3 to 8 words to support comments
  • A note on which noise comments to skip, such as pitches in your comments

Common Use Cases

  • Answering twenty comments in the first hour after a post goes live
  • Replying to a critic without getting defensive
  • Turning a comment from a prospect into a useful public answer
  • Deciding which comments deserve more than a like

What Makes It Unique

The reply effort follows value: leads and substance get the longest answers, support gets a like and a few words, and pitches get nothing. It gives specific rules for critics, leads and spam in your comments, and keeps every answer in public, so the next person sees the value and contacts you.

Under The Hood

The skill is instructions only, with no scripts. It works from the comments you paste, including screenshots, and avoids scraping the thread with a browser tool. It passes the replies through the humanizer skill. It does not fetch web pages, call APIs, write files 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