LinkedIn Marketing Skills
A 12-skill bundle that plans, drafts, audits, and (after your approval) publishes LinkedIn posts and comments.
Marketing & SEOIntermediate★ 5,763⑂ 935AI score 9/10Last updated: Nov 3, 2026
What it does
- Bundles 12 single-purpose skills for LinkedIn content ops: viral post writing (
linkedin-post-writer), comment and reply drafting (linkedin-comment-drafter,linkedin-reply-handler), AI-tell removal plus a pre-publish audit (linkedin-humanizer), hook-formula extraction, weekly content planning, profile optimization, thread monitoring, engager analytics, employee advocacy, and cross-platform repurposing. - Every action skill follows a strict draft → explicit approval → publish pattern; nothing goes out before you say "post".
- Ten baked-in voice rules: em-dash budget, banned AI vocabulary (leverage, delve, unlock…), specific numbers over adjectives, hook inside the first 210 chars, 900–1,300 char posts, 200–350 char comments.
- Parses LinkedIn URLs into all three URN types (activity/share/ugcPost) and extracts comment IDs, with documented workarounds for thread flattening and the
INSIGHTFULreaction bug. - Three setup tiers: Tier 0 needs nothing and returns copy-paste blocks, Tier 1 auto-publishes via the Publora API, Tier 2 lets you wire your own poster. Read-side fetching requires an Apify token or MCP connector.
Who it's for
- B2B marketers, founders, and personal-brand creators who treat LinkedIn as a primary channel
- Writers whose drafts keep reading as obviously AI-generated
- Teams standardizing commenting, replying, and employee advocacy workflows
Example uses
- "Plan my LinkedIn week" → picks a founder or general pillar set and builds a content calendar
- Paste a post URL and ask for a comment → the skill reads the post, drafts a 200–350 char comment, publishes on approval
- Paste your own draft and ask for a pre-publish audit → emoji density score, AI-vocabulary flags, hook rewrite
· · · 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/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 AI Skill Mart. Copy the .codex-marketplace/linkedin-skills folder from the GitHub repo sergebulaev/linkedin-skills into my ~/.claude/skills/linkedin-marketing/. 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 /tmp/linkedin-skills && mkdir -p ~/.claude/skills && cp -r /tmp/linkedin-skills/.codex-marketplace/linkedin-skills ~/.claude/skills/⚠ This is a third-party skill. Check the source repository before installing.
- Open a terminal.
- Clone the repo:
git clone https://github.com/sergebulaev/linkedin-skills.git /tmp/linkedin-skills - Copy the skill into place:
mkdir -p ~/.claude/skills && cp -r /tmp/linkedin-skills/.codex-marketplace/linkedin-skills ~/.claude/skills/ - (Optional) Install Python deps: from the skill folder run
pip install -r requirements.txt - (Optional, for auto-publishing) Sign up for Publora's free tier, connect LinkedIn, copy the API key, and add
PUBLORA_API_KEY=...andLINKEDIN_PLATFORM_ID=...to a.envfile in the skill folder. - (Optional, to read other people's posts/comments) Create an Apify account, generate a token, and add
APIFY_TOKEN=...to.env. - Restart Claude Code and try "draft a LinkedIn post about X". With zero configuration you still get copy-paste-ready drafts.
View source on GitHub ↗License: MIT