linkedin

Create a LinkedIn post from any content source - blog posts, articles, PDFs, URLs, or plain text.

Usage: $ARGUMENTS

Optional custom file attachment:

# Auto-generate PDF from ALL blog diagrams (default)
/publisher:linkedin my-post

# Attach your own image or PDF
/publisher:linkedin my-post en path/to/image.png
/publisher:linkedin my-post en path/to/report.pdf

Media attachment (zero dependencies!):

• With Pillow: Generates PDF from all diagrams → single file
• Without Pillow: Uploads all diagrams as separate images → works everywhere!
• Custom file: Just provide the path → always works
• No install required for the fallback option!

CRITICAL: LinkedIn's "Little Text Format" requires escaping reserved characters even for REST API!

Reserved characters that MUST be escaped: \ | { } @ [ ] ( ) < > # * _ ~

DO NOT manually escape these in your commentary - Claude handles two-step escaping automatically:

1. LinkedIn Little Text Format escaping (parentheses, brackets, etc.)
2. JSON escaping (quotes, backslashes)

Pass raw text with parentheses, hashtags, etc. directly - the command handles all escaping.

Process:

1. Parse Input Arguments

   • Extract content input, optional language parameter, and optional custom file path
   • Examples:
     • 2025-10-06-my-post (slug only, default English)
     • 2025-10-06-my-post ja (slug with Japanese)
     • 2025-10-06-my-post en path/to/custom.png (with custom file)
     • path/to/article.md (file path)
     • https://myblog.com/post (URL)

2. Universal Input Detection

   If input looks like a file path (contains / or file extension):

   • Use Read tool to check if file exists
   • Detect format by extension:
     • .md / .mdx → Parse markdown with frontmatter (extract title, description, body, metadata)
     • .pdf → Inform user PDF parsing is limited, suggest converting to markdown first
     • .docx → Inform user DOCX parsing is limited, suggest converting to markdown first
     • .html → Read and extract main content, strip HTML tags
     • .txt → Read as plain text
     • .json → Parse JSON and extract relevant fields
   • Extract: title, description, body content, metadata

   If input looks like a URL (starts with http:// or https://):

   • Use WebFetch tool to retrieve the page
   • Prompt: "Extract the main article content, title, and description from this page"
   • Parse and clean the text

   If input is a slug (no / and no protocol):

   • Search codebase using Glob: **/*${input}*.md
   • Common patterns to check:
     • src/content/blog/posts/{en,ja}/*${input}*.md
     • content/blog/*${input}*.md
     • posts/*${input}*.md
     • blog/*${input}*.md
   • If language specified, prioritize matching language folder
   • Use Read tool to parse markdown file with frontmatter

3. Determine Language (default: English):

   • If user explicitly specifies "ja" → Japanese
   • If user explicitly specifies "en" → English
   • If file path contains /ja/ → Japanese
   • If content appears to be in Japanese → Japanese
   • Otherwise → English

4. Generate engaging LinkedIn commentary in the target language:

   • For English: Follow professional thought leadership voice (see examples below)
   • For Japanese: Use professional Japanese business tone (敬語), include article link
   • Use actual blog content and key points
   • Make it contextual and intelligent, not template-based
   • APPLY HUMANIZATION (see Humanization Guidelines below)

5. Handle file attachment:

   If custom file path provided (third argument):

   • Use the specified file path (e.g., path/to/image.png or path/to/report.pdf)
   • Verify file exists using Read tool
   • Supported formats: .png, .jpg, .jpeg, .pdf
   • Use this file for LinkedIn media upload

   If no custom file specified (default behavior):

   • Auto-detect blog diagrams:
     • English: public/diagrams/[SLUG]-0-en-light.png
     • Japanese: public/diagrams/[SLUG]-0-ja-light.png
   • Script will auto-generate PDF from diagrams if found
   • Commentary MUST include article URL when diagrams exist