Linkedin Article Publisher Skill
Claude Skill that publish on LinkedIn article
Install: /plugin marketplace add iamzifei/linkedin-article-publisher-skill
Works with Claude Code · 21 GitHub stars
Install
/plugin marketplace add iamzifei/linkedin-article-publisher-skillInstall command taken from the project's README or registry entry. Always review code before running it.
README excerpt
Read full README on GitHub →LinkedIn Article Publisher Skill
Publish Markdown articles to LinkedIn Articles with one command. Say goodbye to tedious rich text editing.
v1.0.0 — Block-index positioning for precise image placement
The Problem
If you're used to writing in Markdown, publishing to LinkedIn Articles is a painful process:
| Pain Point | Description |
|---|---|
| Format Loss | Copy from Markdown editor -> Paste to LinkedIn -> All formatting gone |
| Manual Formatting | Set each H2, bold, link manually — 15-20 min per article |
| Tedious Image Upload | Multiple clicks per image: Add media -> Select -> Wait |
| Position Errors | Hard to remember where each image should go |
Time Comparison
| Task | Manual | With This Skill |
|---|---|---|
| Format conversion | 15-20 min | 0 (automatic) |
| Cover image | 1-2 min | 10 sec |
| 5 content images | 5-10 min | 1 min |
| Total | 20-30 min | 2-3 min |
10x efficiency improvement
The Solution
This skill automates the entire publishing workflow:
Markdown File
| Python parsing
v
Structured Data (title, images with block_index, HTML)
| Playwright MCP
v
LinkedIn Articles Editor (browser automation)
|
v
Draft Saved (never auto-publishes)
Key Features
- Rich Text Paste: Convert Markdown to HTML, paste via clipboard — all formatting preserved
- Block-Index Positioning: Precise image placement using element indices, not text matching
- Reverse Insertion: Insert images from highest to lowest index to avoid position shifts
- Smart Wait Strategy: Conditions return immediately when met, no wasted wait time
- Safe by Design: Only saves as draft, never publishes automatically
Why Block-Index?
Previously, images were positioned by matching surrounding text — this failed when:
- Multiple paragraphs had similar content
- Text was too short to be unique
Now, each image has a block_index indicating exactly which block element it follows. This is deterministic and reliable.
Requirements
| Requirement | Details |
|---|---|
| Claude Code | claude.ai/code |
| Playwright MCP | Browser automation |
| LinkedIn Account | Free account works (no Premium required) |
| Python 3.9+ | With dependencies below |
| macOS | Currently macOS only |
pip install Pillow pyobjc-framework-Cocoa
Installation
Method 1: Git Clone (Recommended)
git clone https://github.com/iamzifei/linkedin-article-publisher-skill.git
cp -r linkedin-article-publisher-skill/skills/linkedin-article-publisher ~/.claude/skills/
Method 2: Plugin Marketplace
/plugin marketplace add iamzifei/linkedin-article-publisher-skill
/plugin install linkedin-article-publisher@iamzifei/linkedin-article-publisher-skill
Usage
Natural Language
Publish /path/to/article.md to LinkedIn
Help me post this article to LinkedIn: ~/Documents/my-post.md
Skill Command
/linkedin-article-publisher /path/to/article.md
Workflow Steps
[1/7] Parse Markdown...
-> Extract title, cover image, content images with block_index
-> Convert to HTML, count total blocks
[2/7] Open LinkedIn Articles editor...
-> Navigate to linkedin.com/article/new/
[3/7] Upload cover image...
-> First image becomes cover
Similar plugs
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local…
Why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
Production-grade engineering skills for AI coding agents.