Best use case
linkedin-inbound-run is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Automatic inbound LinkedIn message processing
Teams using linkedin-inbound-run should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/linkedin-inbound-run/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How linkedin-inbound-run Compares
| Feature / Agent | linkedin-inbound-run | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Automatic inbound LinkedIn message processing
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# LinkedIn Inbound Run
> Runs the LinkedIn Inbound Agent to monitor incoming messages.
## When to use
- "check LinkedIn messages"
- "run LinkedIn inbound agent"
- "any new messages on LinkedIn?"
## How to execute
### Step 1: Check prerequisites
```bash
# Check that Chrome is running with debugging
lsof -i :9222
# Should show a Chrome process on port 9222
# If Chrome is not running:
$SCRIPTS_PATH/start_chrome_linkedin.sh
```
### Step 2: Run the agent
**Dry-run (no CRM writes, no notifications):**
```bash
cd $AGENTS_PATH/linkedin-inbound
python3 linkedin_inbound_agent.py --dry-run
```
**Full run:**
```bash
cd $AGENTS_PATH/linkedin-inbound
python3 linkedin_inbound_agent.py
```
**Notification test:**
```bash
python3 linkedin_inbound_agent.py --notify-test
```
### Step 3: Check results
```bash
# View summary
today=$(date +%Y-%m-%d)
cat $AGENTS_PATH/logs/linkedin-inbound-$today.md
# View error log
tail -20 $AGENTS_PATH/logs/linkedin_inbound_errors.log
# View agent log
cat $AGENTS_PATH/logs/linkedin_agent_log.json | jq '.[-5:]'
```
### Step 4: Notify the user
- How many messages were processed
- How many new contacts
- How many POSITIVE/QUESTION replies
- Whether manual review is needed
## Output
- **Telegram notification** in Saved Messages (if there are actionable items)
- **Summary log**: `agents/logs/linkedin-inbound-{date}.md`
- **CRM updates**: `sales/crm/activities.csv`, `sales/crm/relationships/leads.csv`
- **Staged contacts**: `sales/crm/staging/linkedin_inbound_new_contacts.csv`
## Errors
### CDP connection failed
```
ERROR: CDP connection failed: ...
```
**Resolution:**
1. Start Chrome with debugging:
```bash
$SCRIPTS_PATH/start_chrome_linkedin.sh
```
2. Open LinkedIn: https://www.linkedin.com/messaging/
3. Check login
### Classification failed
Agent automatically switches to fallback classification (rule-based).
Check if Claude CLI works:
```bash
echo "test" | claude -p --model haiku
```
### Telegram failed
Notification text is saved in the log file even if Telegram is not working.
```bash
tail -f /tmp/linkedin-inbound-agent.log
```
## Scheduled run
Agent runs automatically via launchd:
```bash
# Status
launchctl list | grep linkedin-inbound
# Stop
launchctl unload ~/Library/LaunchAgents/com.yourcompany.linkedin-inbound.plist
# Start
launchctl load ~/Library/LaunchAgents/com.yourcompany.linkedin-inbound.plist
# View logs
tail -f /tmp/linkedin-inbound-agent.log
tail -f /tmp/linkedin-inbound-agent-error.log
```
## Related skills
- `change-review` — if a PR with CRM changes is needed
- `add-lead` — add staged contacts to CRM
- `telegram-send` — manually send notificationRelated Skills
telegram-inbound-run
Automatic inbound Telegram message processing
linkedin-cdp
LinkedIn CDP: Input-only automation (mouse, keyboard, screenshots). Zero DOM access.
linkedin-automation
Automate LinkedIn tasks via Rube MCP (Composio): create posts, manage profile, company info, comments, and image uploads. Always search tools first for current schemas.
wemp-operator
> 微信公众号全功能运营——草稿/发布/评论/用户/素材/群发/统计/菜单/二维码 API 封装
zsxq-smart-publish
Publish and manage content on 知识星球 (zsxq.com). Supports talk posts, Q&A, long articles, file sharing, digest/bookmark, homework tasks, and tag management. Use when publishing content to 知识星球, creating/editing posts, uploading files/images/audio, managing digests, batch publishing, or formatting content for 知识星球.
zoom-automation
Automate Zoom meeting creation, management, recordings, webinars, and participant tracking via Rube MCP (Composio). Always search tools first for current schemas.
zoho-crm-automation
Automate Zoho CRM tasks via Rube MCP (Composio): create/update records, search contacts, manage leads, and convert leads. Always search tools first for current schemas.
ziliu-publisher
字流(Ziliu) - AI驱动的多平台内容分发工具。用于一次创作、智能适配排版、一键分发到16+平台(公众号/知乎/小红书/B站/抖音/微博/X等)。当用户需要多平台发布、内容排版、格式适配时使用。触发词:字流、ziliu、多平台发布、一键分发、内容分发、排版发布。
zhihu-post-skill
> 知乎文章发布——知乎平台内容创作与发布自动化
zendesk-automation
Automate Zendesk tasks via Rube MCP (Composio): tickets, users, organizations, replies. Always search tools first for current schemas.
youtube-knowledge-extractor
This skill performs deep analysis of YouTube videos through **both information channels** Multimodal YouTube video analysis through both audio (transcript) and visual (frame extraction + image analysis) channels. Especially powerful for HowTo videos, tutorials, demos, and explainer videos where what is SHOWN (screenshots, UI demos, diagrams, code, physical actions) is just as important as what is SAID. Use this skill whenever a user wants to analyze, summarize, or create step-by-step guides from YouTube videos, or when they share a YouTube URL and want to understand what happens in the video. Triggers on requests like "Analyze this YouTube video", "Create a step-by-step guide from this video", "What does this video show?", "Summarize this tutorial", or any YouTube URL shared with analysis intent.
youtube-factory
Generate complete YouTube videos from a single prompt - script, voiceover, stock footage, captions, thumbnail. Self-contained, no external modules. 100% free tools.