Skip to main content
skill CX Codex

li-reply — Claude Code skill: LinkedIn comment replies

The li-reply skill sorts comments on your LinkedIn posts and drafts replies in priority order. You review and post the final text yourself.

MIT ★ 3,812 updated 2026-09-17

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add Jakeschincariol/linkedin-agent-skill
/plugin install linkedin-agent@linkedin-agent-skill
Open on GitHub

What li-reply does

li-reply works with comments from the user’s own LinkedIn post. Paste the thread with names and roles when available; screenshots are also accepted. The skill first places each comment into one of five groups: lead, substance, peer, support, or noise. It gives the count for each group before drafting.

The response style depends on the group. Questions get a direct public answer, critics get an acknowledgment of the valid point before the disagreement, and a lead gets a useful reply with a soft offer at the end. Short praise receives a short response, while a substantive comment gets more detail. Pitches and bad-faith messages can be skipped.

The skill does not scrape the thread with a browser tool. It prepares copy-ready replies, but posting stays behind a user confirmation gate. Nothing is posted until the user approves the drafts and pastes them.

What it helps with

  • sort comments under a LinkedIn post
  • separate leads from praise and spam
  • draft a measured reply to a critic
  • prioritize substantive comments
  • decide which pitches to ignore

Example prompts for the agent

  • Sort these comments from my LinkedIn post, count each group, and draft replies in priority order.
  • Write public replies for the lead and the substantive comments, then keep support replies short.
  • Use these screenshots to prepare copy-ready replies, but wait for my approval before anything is posted.

How to install li-reply

1Plugin marketplace

/plugin marketplace add Jakeschincariol/linkedin-agent-skill
/plugin install linkedin-agent@linkedin-agent-skill

This installs the whole linkedin-agent plugin with all its skills

2Skills CLI (Vercel)

npx skills add Jakeschincariol/linkedin-agent-skill --skill li-reply -a claude-code

3Manually: put the files in place

~/.claude/skills/li-reply/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/li-reply/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about li-reply

How do I install li-reply in Claude Code?

Add the marketplace with /plugin marketplace add Jakeschincariol/linkedin-agent-skill, then install the plugin with /plugin install linkedin-agent@linkedin-agent-skill.

What does li-reply do?

It classifies comments under your LinkedIn post and drafts a response for each relevant group. It can also mark pitches, spam, and bad-faith comments for skipping.

Can li-reply work from screenshots?

Yes. You can provide screenshots of the comments, but the skill does not collect the thread through a browser tool.

Source text

SKILL.md · MIT
---
name: li-reply
description: >-
  Handle the replies under the user's own LinkedIn posts - draft answers to
  every comment, sorted by which ones are worth answering. Use when the user
  pastes the comments on their post, says "reply to these", "handle my
  comments", "someone said X on my post", or is dealing with a critic or a
  lead in the comments.
---

# li-reply

The reply thread under your own post is where reach is actually decided. Every
reply is a second engagement event on the post, and the first hour of replies
does most of the work. But the value is not equal across comments, so this
skill sorts before it writes.

## Input

The user pastes the comments, ideally with names and roles. Screenshots are
fine. Do not scrape the thread with a browser tool.

## Triage first

Sort every comment into one of five buckets and say the count out loud:

| bucket | what it is | what it gets |
| --- | --- | --- |
| **LEAD** | someone describing the problem you solve | a real answer + a soft open door |
| **SUBSTANCE** | adds data, disagrees, extends | the longest reply on the thread |
| **PEER** | a name worth being seen next to | a reply that gives them something |
| **SUPPORT** | "great post", 🔥, a tag | a like, and a 3-8 word reply at most |
| **NOISE** | pitch, spam, bad faith | nothing, or one line and out |

Then write in that order, and stop writing when the value stops.

## How to reply

- **Answer the actual question.** If someone asks how, tell them how, in the
  reply. Do not send them to a DM to hear the answer they could have had.
- **Use their name once**, at the start, and never with an exclamation mark.
- **Match their length.** A two-line comment does not get a six-line reply.
- **To a critic:** concede the true part first, in their words, then hold the
  line on the part you believe. Never delete, never get defensive, never reply
  twice on the same thread.
- **To a lead:** answer fully in public. The open door is one sentence at the
  end, and it is an offer of help, not a pitch. Public value is what makes the
  next person DM you.
- **To a pitch in your comments:** ignore it. Replying gives it reach.

## Output

One block, grouped by bucket, each reply copy-ready and already humanized:

```
REPLIES  ·  17 comments  ·  1 LEAD, 3 SUBSTANCE, 4 PEER, 8 SUPPORT, 1 NOISE

LEAD
@Sarah Chen - "we have the same problem with proposals"
> The part that fixed it for us was pulling the pricing table out of the doc
> entirely and sending it as its own page. Cut a whole review round. Happy to
> send you the template if it is useful.

SUBSTANCE
@Marcus Webb - disagrees on cadence
> Fair, and 4x a week only worked because I had 8 months of posts behind it.
> From a standing start I would do what you said.

SUPPORT  (like these, reply to the first three)
@... "This is great" -> Thanks Dan.
...

NOISE  (1)
Skipped: an agency pitch. Replying gives it reach.
```

Then the gate: **nothing is posted until the user says yes.** They paste the
replies themselves.

© Jake Schincariol · MIT · Jakeschincariol/linkedin-agent-skill

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set12

The whole set →

Project sponsors

Companies that keep this analytics open