connect-requests

Files (1)

• SKILL.md

SKILL.md (first lines)

## Browser Preflight (MANDATORY — do this FIRST)

Before delegating to any agent, attach the Claude Chrome extension to this session:

1. Tell the user in chat:
   > "I need browser access to LinkedIn. You may see a permission prompt — please approve it. I'll wait."
2. Navigate to `https://www.linkedin.com/feed/` using the Browser tool. This triggers Claude's permission system and attaches the Chrome extension to the session.
3. Confirm the LinkedIn feed page loaded (content visible, not an error/login wall). If it fails, tell the user the extension isn't connected and stop — do NOT delegate to the agent.

If LinkedIn already loaded earlier in this session, this step passes instantly.

Delegate to the **outreach** agent in **connect-request mode**:

- Read qualified/approved leads from pipeline data
- For each lead, visit their LinkedIn profile and draft a personalized connection note (~300 char limit)
- Present each note or a clearly enumerated batch and wait for explicit user approval before sending
- Log the connection request message with the canonical dashboard `lead_id` resolved from the matched lead (`id`, `_id.$oid`, then `original_id`), not a LinkedIn slug
- If a lead does not have a dashboard ID yet, sync/fetch the lead first, then write or sync the message
- Batch in groups of 10-15 with a 30-60 second pause between each
- Update each lead's stage to "connected" after sending
- If LinkedIn shows "Weekly invitation limit reached" — stop immediately and report progress
- Max 20-25 connection requests per session

## Connection Note Structure

1. **Hook (~120 chars):** Specific reference to what they're building or their background
2. **Bridge (~130-160 chars):** Light product mention + invitation

## After Completion

Report summary: sent count, skipped count (with reasons), and remaining leads.

If this skill was triggered as part of `/run-all`, proceed to the next non-sending step after the approved batch completes.

From Kasper-AI/gtm-kit-plugin, MIT.

More from Kasper-AI/gtm-kit-plugin