LinkedIn Comment Drafter
Paste a LinkedIn post URL and get 1-3 conversation-starting comment drafts in your voice, a suggested reaction, and one-click publishing after approval.
Marketing & SEOIntermediate★ 3,733⑂ 627AI score 9/10Last updated: Sep 29, 2026
What it does
- Parses a LinkedIn post URL, then fetches the post body plus up to 10 top comments (via Apify if
APIFY_TOKENis set; otherwise it asks you to paste the text). - Picks 2-3 of seven tested comment patterns (Missing-Piece, Answer-the-Closing-Question, Data-First, Counter-with-Concession, Quotable-Reframe, and more) and writes 200-350 character drafts.
- Attaches a suggested reaction type (
LIKE,PRAISE,INTEREST, ...) and a one-line rationale for why that pattern fits. - Runs a humanizer pass: strips AI-tell vocabulary, caps em dashes, adds an odd-precision number with a named referent.
- Reshare mode: checks
canShare, drafts a one- or two-sentence take, and reposts to your feed. - Shows an approval card and only publishes through Publora once you say "post".
Who it's for
- Founders and operators building a LinkedIn presence through commenting
- Marketers and sellers who want to be among the first commenters on viral posts
- Employee-advocacy leads resharing brand and colleague content
- Anyone tired of generic "Great post!" replies (this skill refuses them)
Examples
- "Comment on this: linkedin.com/posts/..." → detects the closing question → returns a T2 Answer-the-Closing-Question primary draft, T1 Missing-Piece backup,
INTERESTreaction. - Racing for an early comment slot on a viral post → Data-First template with a concrete stat and a date the old assumption broke.
- "Reshare this with my thoughts" → verifies resharing is enabled, drafts a one-line take, publishes and returns the new reshare URN.
· · · Install guide · · ·
Try it now, no install
Paste this into Claude to use the skill without installing anything.
Read the instructions in this file and follow them to help me: https://raw.githubusercontent.com/sergebulaev/linkedin-skills/HEAD/.codex-marketplace/linkedin-skills/skills/linkedin-comment-drafter/SKILL.md What I want: (describe your task here)
If Claude can't open the link, open it yourself and paste the contents instead.
↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.
Install in the Claude app (no terminal)
- Download the ZIP with the button below.
- In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
- Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
Install in Claude Code
Let Claude do it — paste this into Claude Code
Install the skill I found on Claude Skill Mart. Copy the .codex-marketplace/linkedin-skills/skills/linkedin-comment-drafter folder from the GitHub repo sergebulaev/linkedin-skills into my ~/.claude/skills/linkedin-comment-drafter/. When it's done, tell me in one line what this skill can do.
Install with a command instead
git clone https://github.com/sergebulaev/linkedin-skills.git && mkdir -p ~/.claude/skills && cp -r linkedin-skills/.codex-marketplace/linkedin-skills/skills/* ~/.claude/skills/⚠ This is a third-party skill. Check the source repository before installing.
- Open a terminal and clone the repo:
git clone https://github.com/sergebulaev/linkedin-skills.git - Create the skills directory:
mkdir -p ~/.claude/skills - This skill references shared
lib/helpers and../../references/files, so copy the whole skill bundle rather than one folder:cp -r linkedin-skills/.codex-marketplace/linkedin-skills/skills/* ~/.claude/skills/ - Also copy the bundle's top-level
references/directory (voice-profile, untrusted-content, voice-rules) so the relative paths resolve. - Optional: export
APIFY_TOKENto auto-fetch post bodies and comments (roughly $0.001-$0.006 per call). Without it, you paste the post text manually. - Optional: connect a Publora account for auto-publishing; otherwise the skill falls back to copy-paste instructions.
- Restart Claude Code and try: "Draft a comment on this LinkedIn post: <URL>".
View source on GitHub ↗License: MIT