linkedin-poster
Skill1 starsChanged 37 days agoMITView on GitHub
Automatically post business content to LinkedIn for sales generation and professional presence. Creates post drafts with approval workflow, scheduling support, and engagement tracking. Use when you need to maintain LinkedIn presence, share business updates, or generate leads through social media. All posts require human approval before publishing.
- Reads credentials
- Installs packages
We split this skill into the rules it gives an agent
14 rules. 0 are common, 12 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
12
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 35
Posts to LinkedIn: after approval
- Distinctive: line 44
Create LinkedIn App at LinkedIn Developers
- Very specific: line 47
Add to .env file
- Very specific: line 73
Create templates in AI_Employee_Vault/Templates/:
- Distinctive: line 227
Use official API when possible
- Distinctive: line 228
Avoid spam or excessive posting
- Distinctive: line 230
Don't automate comments/likes
- Distinctive: line 236
All posts (no auto-posting)
- Distinctive: line 248
All posts reviewed by human
- Distinctive: line 250
No political or controversial content
- Distinctive: line 293
Wait 24 hours before retry
- Distinctive: line 296
Check if post is in draft mode
- Distinctive: line 297
Verify approval was processed
- Distinctive: line 298
Check LinkedIn for errors
“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
LinkedIn Poster
Automatically post business content to LinkedIn to generate sales leads and maintain professional presence.
Overview
This skill enables automated posting to LinkedIn for business development, thought leadership, and sales generation. All posts require human approval before publishing to ensure quality and brand alignment.
Usage
# Create a post draft
claude /post-linkedin --content "Your post content here"
# Schedule a post
claude /post-linkedin --content "Post content" --schedule "2026-03-13 09:00"
# Post with approval
claude /post-linkedin --content "Post content" --require-approvalWhat It Does
- Creates post drafts in
/Plans/POST_*.md - Requests approval via
/Pending_Approval/ - Posts to LinkedIn after approval
- Tracks engagement and logs results
- Schedules posts for optimal timing
Prerequisites
LinkedIn API Access
Option 1: LinkedIn API (Recommended for Production)
- Create LinkedIn App at LinkedIn Developers
- Request API access (requires company page)
- Get OAuth2 credentials
- Add to
.envfile
Option 2: Playwright Automation (Development)
- Install Playwright:
pip install playwright - Run setup:
python scripts/linkedin_poster.py --setup - Login manually (session saved)
Configuration
Environment Variables
# .env file
LINKEDIN_CLIENT_ID=your_client_id
LINKEDIN_CLIENT_SECRET=your_client_secret
LINKEDIN_ACCESS_TOKEN=your_token
LINKEDIN_COMPANY_ID=your_company_id # Optional
# Or for Playwright automation
LINKEDIN_SESSION_PATH=./linkedin_session
LINKEDIN_EMAIL=your@email.com
LINKEDIN_PASSWORD=your_password # Use with cautionPost Templates
Create templates in AI_Employee_Vault/Templates/:
# templates/linkedin_business_update.md
---
type: linkedin_post
category: business_update
---
🚀 Exciting update from [Company Name]!
[Main content here]
What are your thoughts? Drop a comment below! 👇
#Business #Innovation #YourIndustryPost Workflow
Content Idea → Draft Created → /Pending_Approval/POST_*.md
↓
Human reviews & edits
↓
Moves to /Approved/
↓
LinkedIn Poster publishes
↓
Logs engagement → /Done/Action File Format
Draft Post (Pending Approval)
---
type: linkedin_post
status: pending_approval
created: 2026-03-12T20:28:00Z
scheduled_for: 2026-03-13T09:00:00Z
category: business_update
---
# LinkedIn Post Draft
## Post Content
🚀 Exciting news! We've just launched our new AI Employee automation system.
Key benefits:
✅ 24/7 autonomous operation
✅ 85% cost reduction
✅ Instant scalability
Interested in learning more? Let's connect!
#AI #Automation #BusinessInnovation
## Hashtags
#AI #Automation #BusinessInnovation #DigitalTransformation
## Target Audience
- Business owners
- CTOs and tech leaders
- Entrepreneurs
## Expected Engagement
- Reach: 500-1000
- Engagement rate: 3-5%
## To Approve
Move this file to `/Approved/` folder to publish.
## To Reject
Move this file to `/Rejected/` folder or edit and re-submit.Features
Content Generation
# Generate post from business update
claude /post-linkedin --generate \
--topic "New product launch" \
--tone "professional" \
--length "medium"Scheduling
# Schedule for optimal time
claude /post-linkedin --content "..." --schedule "next-business-day 09:00"
# Schedule multiple posts
claude /post-linkedin --batch posts.jsonEngagement Tracking
- Tracks likes, comments, shares
- Logs to
/Accounting/linkedin_engagement.json - Weekly engagement reports
- ROI analysis
A/B Testing
# Create variants for testing
claude /post-linkedin --content "Version A" --variant-of "post_123"
claude /post-linkedin --content "Version B" --variant-of "post_123"Best Practices
Posting Frequency
- Minimum: 2-3 posts per week
- Optimal: 1 post per day
- Maximum: 2 posts per day
Optimal Posting Times
- Tuesday-Thursday: 9 AM - 11 AM
- Wednesday: Best engagement day
- Avoid: Weekends, early mornings, late evenings
Content Mix
- 40% Educational/Thought leadership
- 30% Company updates/News
- 20% Industry insights
- 10% Promotional
Hashtag Strategy
- Use 3-5 relevant hashtags
- Mix popular and niche tags
- Create branded hashtag
- Research trending tags
Security & Compliance
LinkedIn Terms of Service
⚠️ Important: Automated posting must comply with LinkedIn's terms:
- Use official API when possible
- Avoid spam or excessive posting
- Maintain authentic engagement
- Don't automate comments/likes
- Respect rate limits
Approval Workflow
Always require approval for:
- All posts (no auto-posting)
- Company announcements
- Client mentions
- Controversial topics
Auto-approve (with caution):
- Scheduled educational content
- Pre-approved templates
- Automated reports (with review)
Brand Safety
- All posts reviewed by human
- Tone and style guidelines enforced
- No political or controversial content
- Professional language only
- Fact-checking required
Monitoring
Check Status
# View pending posts
ls -lt AI_Employee_Vault/Pending_Approval/POST_*.md
# View published posts
ls -lt AI_Employee_Vault/Done/POST_*.md
# Check engagement
cat AI_Employee_Vault/Accounting/linkedin_engagement.json | jq .Engagement Reports
# Generate weekly report
claude /linkedin-report --period "last-week"
# View top performing posts
claude /linkedin-report --top 10Troubleshooting
"Authentication failed" error
# Re-authenticate
python scripts/linkedin_poster.py --setup
# Or refresh token
python scripts/linkedin_poster.py --refresh-token"Rate limit exceeded" error
- LinkedIn limits: 100 posts per day
- Reduce posting frequency
- Wait 24 hours before retry
Post not appearing
- Check if post is in draft mode
- Verify approval was processed
- Check LinkedIn for errors
- Review logs for API errors
Low engagement
- Review posting times
- Improve content quality
- Use better hashtags
- Engage with comments
Advanced Usage
Content Calendar
# Create monthly content calendar
claude /linkedin-calendar --month "April 2026"
# Auto-schedule from calendar
claude /linkedin-schedule --calendar "april_2026.json"AI-Generated Content
# Generate post from topic
claude /post-linkedin --generate \
--topic "AI automation benefits" \
--style "thought-leadership" \
--include-stats
# Generate from company news
claude /post-linkedin --generate \
--source "AI_Employee_Vault/Company_News.md"Integration with Sales
# Track leads from LinkedIn
claude /linkedin-leads --export "leads.csv"
# Connect with CRM
claude /linkedin-sync --crm "odoo"Performance Metrics
Track These KPIs
- Impressions: Total views
- Engagement Rate: (Likes + Comments + Shares) / Impressions
- Click-through Rate: Link clicks / Impressions
- Follower Growth: New followers per week
- Lead Generation: Inquiries from posts
Target Benchmarks
- Engagement rate: 2-5%
- CTR: 0.5-2%
- Follower growth: 5-10% monthly
- Lead conversion: 1-3%
Dependencies
# For API approach
requests==2.31.0
python-linkedin-v2==0.9.0
# For Playwright approach
playwright==1.41.0Alternative: LinkedIn Official API
For production use:
- LinkedIn Marketing API
- Official API with full features
- Requires company page
- Better rate limits
- Compliance-friendly
See Also
/process-vault-tasks- Process post drafts/update-dashboard- Track engagement metricsCompany_Handbook.md- Social media guidelinesorchestrator.py- Automated scheduling
Other versions6 projects use a version of this.
Word for word · 1
- muhammad-anas35/Nexus-ai-employee★ 1100% same
Edited · 0
None found.
Wrote their own version · 5
- amigoscode/skills★ 1same name
- muhammadwaheedairi/Personal-AI-Employee★ 1same name
- omerfarooq223/personal-ai-employee★ 1same name
- CodeWithSuleman/Personal-AI-Employee-FTE-★ 0same name
- syeda-hoorain-ali/personal-ai-employee-hackathon★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository8 other files it gives its agents.
- odoo-integrationSkill
- browsing-with-playwrightSkill
- send-emailSkill
- gmail-watcherSkill
- process-vault-tasksSkill
- facebook-posterSkill
- update-dashboardSkill
- whatsapp-watcherSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

