LinkedIn Inbox Manager
Scanned@dylanbaker24
npx machina-cli add skill @dylanbaker24/linkedin-inbox --openclawLinkedIn Inbox Manager
Automated LinkedIn inbox monitoring with human-in-the-loop approval for responses. Uses Peekaboo for UI automation (no API rate limits, works with any LinkedIn account).
Requirements
- macOS with Peekaboo CLI installed (
brew install steipete/tap/peekaboo) - Screen Recording + Accessibility permissions granted
- LinkedIn logged in via browser (Chrome recommended)
- Clawdbot with browser capability
Quick Start
1. One-time Setup
# Grant Peekaboo permissions
peekaboo permissions
# Verify LinkedIn is accessible
peekaboo app launch "Google Chrome"
peekaboo see --app "Google Chrome" --annotate --path /tmp/linkedin-check.png
2. Configure User Style
Create linkedin-inbox-config.json in your workspace:
{
"scan": {
"intervalMinutes": 60,
"activeHours": { "start": 9, "end": 18, "timezone": "America/Los_Angeles" },
"skipWeekends": true
},
"drafting": {
"styleProfile": "USER.md",
"templates": {
"decline": "Thanks for reaching out. Not a fit for us right now, but best of luck.",
"interested": "This looks interesting. Happy to chat more. What's your availability?",
"referral": "I might know someone. Let me check and get back to you."
}
},
"notifications": {
"channel": "discord",
"target": "#linkedin"
}
}
3. Start Monitoring
Tell your agent: "Start LinkedIn inbox monitoring" or add to HEARTBEAT.md:
- Check LinkedIn inbox if last scan >1 hour ago
Core Workflow
Scan Inbox
# Navigate to LinkedIn messaging
peekaboo app launch "Google Chrome"
peekaboo menu click --app "Google Chrome" --item "New Tab"
peekaboo type "https://www.linkedin.com/messaging/" --return
sleep 3
# Capture inbox state
peekaboo see --app "Google Chrome" --window-title "Messaging" --annotate --path /tmp/linkedin-inbox.png
The agent reads the annotated screenshot to identify:
- Unread messages (bold names, blue dots)
- Message previews
- Sender names and titles
Draft Responses
For each unread message:
- Agent reads the conversation
- Classifies intent (pitch, networking, job inquiry, spam)
- Drafts response matching user's communication style
- Posts draft to notification channel for approval
Example notification:
š¼ LinkedIn: New message from **Alex M.** (Founder @ SomeCompany)
Preview: "Hi, I noticed you're growing and wondered if..."
**My read:** Services pitch. Doesn't fit current needs.
**Draft reply:**
> Thanks for reaching out. We're set on that side for now, but I'll keep you in mind if that changes.
React ā
to send, ā to skip, or reply with edits.
Send Approved Messages
On approval:
# Click into conversation
peekaboo click --on [message-element-id] --app "Google Chrome"
sleep 1
# Type response
peekaboo type "Your approved message here" --app "Google Chrome"
# Send (Enter or click Send button)
peekaboo press return --app "Google Chrome"
Communication Style Matching
The skill reads USER.md (or configured style file) to match the user's tone:
Extract these signals:
- Formality level (casual vs professional)
- Typical greeting style
- Sign-off patterns
- Sentence length preference
- Banned words/phrases
- Response length norms
Apply to drafts:
- Mirror detected patterns
- Use user's vocabulary
- Match their directness level
- Respect their guardrails (no "excited", no hype, etc.)
See references/style-extraction.md for detailed guidance.
Morning Ping Integration
Add LinkedIn summary to your morning ping:
š£ The Morning Ping ā Monday, Jan 27
**LinkedIn:**
⢠š Sarah Chen replied ā "That sounds great, let's do Thursday" ā Draft ready
⢠š Mike R. replied ā "Not interested right now" ā No action needed
⢠š© 3 new connection requests (2 sales pitches, 1 relevant)
⢠š© 1 unread message from Alex (job inquiry) ā Draft ready
Reply "send sarah" to approve, "skip mike" to archive.
Approval Commands
Users can respond with:
send [name]- Send the drafted replysend all- Send all pending draftsskip [name]- Archive without replyingedit [name]: [new message]- Replace draft and sendshow [name]- Show full conversation
Scheduled Scanning
Via Cron (Recommended)
{
"schedule": "0 */2 9-18 * * 1-5",
"text": "Scan LinkedIn inbox and post any new messages to #linkedin with draft replies"
}
Via Heartbeat
In HEARTBEAT.md:
- If 9am-6pm PT and last LinkedIn scan >60min: scan inbox, draft replies, post to #linkedin
Safety Rules
- Never send without explicit approval - Always wait for user confirmation
- Rate limit actions - Max 20 LinkedIn actions per hour
- Respect quiet hours - Don't scan outside configured activeHours
- Log everything - Record all actions in daily memory file
- Preserve originals - Never delete messages, only archive
Troubleshooting
"Can't find messaging UI"
- Ensure Chrome is open with LinkedIn logged in
- Check window title matches (may vary by language)
- Use
peekaboo list windows --app "Google Chrome" --jsonto debug
"Session expired"
- LinkedIn sessions expire periodically
- Re-authenticate manually in browser
- Skill will detect login page and notify user
"Peekaboo permissions denied"
peekaboo permissions # Check status
# Grant via System Preferences > Privacy & Security > Screen Recording + Accessibility
Files
scripts/scan_inbox.sh- Peekaboo commands for inbox capturescripts/send_message.sh- Peekaboo commands for sendingreferences/style-extraction.md- Guide for communication style matching
Overview
LinkedIn Inbox Manager automates monitoring of LinkedIn messages with human-in-the-loop approval. It leverages UI automation via Peekaboo to read conversations, draft replies in your own style, and route them for review. It supports scheduled scans, off-hours inbox management, and morning activity summaries to keep you responsive.
How This Skill Works
The tool uses Peekaboo to navigate LinkedIn messaging and capture the inbox state (unread indicators, previews, senders). For each unread message it classifies intent, generates a draft that matches your STYLE from USER.md, and posts the draft to a designated channel for approval. Once approved, it simulates the necessary clicks and typing in the browser to send the reply.
When to Use It
- Monitoring LinkedIn messages for new inquiries or leads
- Drafting replies in your communication style when time is limited
- Managing inbox during evenings, weekends, or off-hours
- Setting up morning ping summaries of LinkedIn activity
- Requiring human approval before sending outreach messages
Quick Start
- Step 1: Install Peekaboo permissions and ensure LinkedIn is accessible in Chrome
- Step 2: Create linkedin-inbox-config.json with scan interval, activeHours, and templates
- Step 3: Start monitoring by telling your agent: "Start LinkedIn inbox monitoring"
Best Practices
- Maintain a current USER.md style profile to ensure tone consistency
- Regularly review and update templates (decline, interested, referral)
- Verify activeHours and timezone to avoid misaligned scans
- Keep drafts concise and aligned with your usual response length
- Use the approval channel to review and edit drafts before sending
Example Use Cases
- Lead inquiry from Alex M. about a partnership; draft mirrors user voice, approved, and sent
- Networking outreach from a peer requesting a chat; draft with scheduling prompt; approved
- Job inquiry received; draft response offering next steps and timeline; approved
- Referral message routed for confirmation; draft prepared and approved
- Morning LinkedIn activity summary posted to Discord for team awareness