linkedin-monitorBulletproof LinkedIn inbox monitoring with progressive autonomy. Monitors messages hourly, drafts replies in your voice, and alerts you to new conversations. Supports 4 autonomy levels from monitor-only to full autonomous.
Install via ClawdBot CLI:
clawdbot install linkedin-monitorReliable LinkedIn inbox monitoring for Clawdbot.
# 1. Setup (interactive)
linkedin-monitor setup
# 2. Verify health
linkedin-monitor health
# 3. Run manually (test)
linkedin-monitor check
# 4. Enable cron (hourly)
linkedin-monitor enable
| Level | Name | Behavior |
|-------|------|----------|
| 0 | Monitor Only | Alerts to new messages only |
| 1 | Draft + Approve | Drafts replies, waits for approval |
| 2 | Auto-Reply Simple | Auto-handles acknowledgments, scheduling |
| 3 | Full Autonomous | Replies as you, books meetings, networks |
Default: Level 1 ā Change with linkedin-monitor config autonomyLevel 2
linkedin-monitor setup # Interactive setup wizard
linkedin-monitor health # Check auth status
linkedin-monitor check # Run one check cycle
linkedin-monitor enable # Enable hourly cron
linkedin-monitor disable # Disable cron
linkedin-monitor status # Show current state
linkedin-monitor config # View/edit configuration
linkedin-monitor logs # View recent activity
linkedin-monitor reset # Clear state (start fresh)
Location: ~/.clawdbot/linkedin-monitor/config.json
{
"autonomyLevel": 1,
"alertChannel": "discord",
"alertChannelId": "YOUR_CHANNEL_ID",
"calendarLink": "cal.com/yourname",
"communicationStyleFile": "USER.md",
"timezone": "America/New_York",
"schedule": "0 * * * *",
"morningDigest": {
"enabled": true,
"hour": 9,
"timezone": "Asia/Bangkok"
},
"safetyLimits": {
"maxMessagesPerDay": 50,
"escalationKeywords": ["angry", "legal", "refund"],
"dailyDigest": true
}
}
1. Health Check
āāā Verify LinkedIn auth (lk CLI)
2. Fetch Messages
āāā lk message list --json
3. Compare State
āāā Filter: only messages not in state file
4. For Each New Message
āāā Level 0: Alert only
āāā Level 1: Draft reply ā Alert ā Wait for approval
āāā Level 2: Simple = auto-reply, Complex = draft
āāā Level 3: Full autonomous response
5. Update State
āāā Record message IDs (prevents duplicates)
State is managed by scripts, not the LLM. This guarantees:
State files: ~/.clawdbot/linkedin-monitor/state/
When at Level 1, approve drafts with:
send [name] # Send draft to [name]
send all # Send all pending drafts
edit [name] [text] # Edit draft before sending
skip [name] # Discard draft
lk auth login
linkedin-monitor health
linkedin-monitor check --debug
linkedin-monitor reset # Clear state
linkedin-monitor check # Fresh start
lk CLI (LinkedIn CLI) ā npm install -g lkjq (JSON processor) ā brew install jq~/.clawdbot/linkedin-monitor/
āāā config.json # Your configuration
āāā state/
ā āāā messages.json # Seen message IDs
ā āāā lastrun.txt # Last check timestamp
ā āāā drafts.json # Pending drafts
āāā logs/
āāā activity.log # Activity history
Generated Mar 1, 2026
A recruitment agency uses LinkedIn Monitor to automate initial contact with potential candidates. At autonomy level 1, it drafts personalized replies based on candidate profiles and waits for recruiter approval before sending, ensuring quality control while saving time on routine messages.
A freelance consultant employs the skill to monitor LinkedIn messages for new project inquiries. With autonomy level 2, it automatically handles simple scheduling requests and acknowledgments, allowing the freelancer to focus on complex negotiations while maintaining prompt communication.
A startup founder utilizes LinkedIn Monitor to manage incoming connection requests and messages from investors or partners. At autonomy level 0, it alerts the founder to new conversations, ensuring no opportunity is missed while maintaining a hands-on approach to relationship building.
A sales team implements the skill to track responses from LinkedIn outreach campaigns. Using autonomy level 3, it autonomously replies to qualified leads, books meetings via integrated calendars, and escalates complex queries, streamlining the sales pipeline efficiently.
Offer LinkedIn Monitor as a monthly subscription for professionals, with tiers based on autonomy levels and message volume limits. Revenue comes from recurring fees, targeting individuals and small teams who value time-saving automation in networking.
License the skill to large corporations for their sales or HR departments, with custom configurations and premium support. Revenue is generated through annual contracts, focusing on organizations needing scalable LinkedIn monitoring across multiple users.
Provide a free version with basic monitoring (autonomy level 0) and charge for advanced features like higher autonomy levels, detailed analytics, or integration with other tools. Revenue streams from upgrades and add-ons for power users.
š¬ Integration Tip
Ensure the lk CLI is properly authenticated and jq is installed for JSON processing; test the skill in monitor-only mode first to verify setup before increasing autonomy levels.
Automatically update Clawdbot and all installed skills once daily. Runs via cron, checks for updates, applies them, and messages the user with a summary of what changed.
Full desktop computer use for headless Linux servers. Xvfb + XFCE virtual desktop with xdotool automation. 17 actions (click, type, scroll, screenshot, drag,...
Essential Docker commands and workflows for container management, image operations, and debugging.
Tool discovery and shell one-liner reference for sysadmin, DevOps, and security tasks. AUTO-CONSULT this skill when the user is: troubleshooting network issues, debugging processes, analyzing logs, working with SSL/TLS, managing DNS, testing HTTP endpoints, auditing security, working with containers, writing shell scripts, or asks 'what tool should I use for X'. Source: github.com/trimstray/the-book-of-secret-knowledge
Deploy applications and manage projects with complete CLI reference. Commands for deployments, projects, domains, environment variables, and live documentation access.
Monitor topics of interest and proactively alert when important developments occur. Use when user wants automated monitoring of specific subjects (e.g., product releases, price changes, news topics, technology updates). Supports scheduled web searches, AI-powered importance scoring, smart alerts vs weekly digests, and memory-aware contextual summaries.