check-responses

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 **responses** agent:

- Navigate to LinkedIn messaging
- Review conversations since last run (up to 7 days back)
- Categorize each conversation (interested, not interested, question, meeting request, inbound, spam)
- Send responses where the category is clear
- When a sent response is synced as a dashboard message, use the canonical dashboard `lead_id` resolved from the matched lead (`id`, `_id.$oid`, then `original_id`), not a LinkedIn slug
- Flag ambiguous conversations for user review
- Update agent memory with conversation history
- Present summary: messages sent, messages skipped, needs user input

After completing this command, sync all data per `references/storage.md`.

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

More from Kasper-AI/gtm-kit-plugin