LinkedIn Marketing Skills Bundle
Eleven focused skills to plan, draft, audit, and publish LinkedIn posts and comments with a draft → approve → publish flow.
Marketing & SEOIntermediate★ 3,453⑂ 581AI score 9/10Last updated: Sep 23, 2026
What it does
- Routes your request to one of 11 single-purpose skills: viral post writing, comment drafting, thread reply sweeps, weekly content planning, hook extraction, profile optimization, engager analytics, repurposing, and more.
linkedin-humanizerstrips AI tells before you publish: emoji-density scoring, banned AI vocabulary, and parallel runs across five AI detectors.- Bakes in concrete 2026 algorithm heuristics: hook inside the first 210 characters, 900–1,300 char posts, 200–350 char comments, em-dash budget of ~1 per 100 words, numbers over adjectives.
- Handles the messy plumbing: parsing LinkedIn URLs into activity/share/ugcPost URNs, decoding commentUrn fragments, and LinkedIn's 2-level thread flattening.
- Every action skill follows the same pattern: draft, wait for your explicit approval, then publish.
Who it's for
- B2B marketers and content operators who treat LinkedIn as a primary channel.
- Founders building trust with investors, hires, and design partners (a dedicated Founders edition supplies 10 content angles).
- Teams running employee advocacy programs or managing multiple posting accounts.
Example uses
- "Turn this tweet thread into a native LinkedIn post" →
linkedin-repurposerrewrites it for the platform. - Paste a post URL and say "draft a comment" → the skill reads the post, writes a 200–350 char comment, and publishes once approved.
- "Audit this draft before I post" → checks AI vocabulary, emoji density, and hook length, then returns a cleaned rewrite.
Note: auto-publishing needs a Publora API key; reading posts/comments needs an Apify token. Without keys it still returns copy-paste-ready drafts.
· · · 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 Claude 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 && cp -r linkedin-skills/.codex-marketplace/linkedin-skills ~/.claude/skills/linkedin-skills⚠ This is a third-party skill. Check the source repository before installing.
- Open a terminal and make sure the skills directory exists:
mkdir -p ~/.claude/skills - Clone the repository:
git clone https://github.com/sergebulaev/linkedin-skills.git - Copy the bundle in:
cp -r linkedin-skills/.codex-marketplace/linkedin-skills ~/.claude/skills/linkedin-skills - (Optional) Install Python deps from the skill folder:
pip install -r requirements.txt - (Optional, for auto-publishing) Sign up free at https://app.publora.com/signup, connect your LinkedIn channel, then add to
.env:PUBLORA_API_KEY=sk_...andLINKEDIN_PLATFORM_ID=linkedin-... - (Optional, for reading posts/comments) Get a token at https://console.apify.com/sign-up and add
APIFY_TOKEN=apify_api_...to.env. - Restart Claude Code and try "write me a LinkedIn post about X". With no keys configured you'll get drafts to paste manually — that path is fully supported.
View source on GitHub ↗License: MIT