gmail-multi-inbox
Gmail Multi-Inbox Setup & Maintenance
Overview
Gmail's Multiple Inboxes displays up to 5 custom sections alongside the main inbox. Each section shows emails matching a search query. This skill uses a label + filter approach: label-based sections get Gmail filters that auto-label incoming mail by sender domain. The output is always a Google Apps Script the user pastes into script.google.com.
The generated script is idempotent — safe to re-run after adding or removing senders. When senders are removed from the lists, setupAll() automatically deletes the corresponding Gmail filters.
Prerequisites
This skill requires a Gmail MCP connector (e.g. search_gmail_messages) to scan the user's inbox. Gmail does not have an official MCP server — the user must have a third-party Gmail connector configured. If no Gmail connector is available, the skill can still work in a limited way: skip the scanning steps and let the user provide sender domains manually, or import from an existing script.
Configuration
The skill stores its current configuration in assets/config.json inside this skill's directory. This file tracks:
- The section definitions (name, query, label)
- The sender domains assigned to each label
- Timestamp of last scan
More from apocohq/skills
things-morning-organizer
Morning review and prioritization of Things todos. Use this skill every morning, or whenever the user asks to review, triage, categorize, or prioritize their Things tasks. Also trigger when the user says things like 'what should I work on today', 'organize my todos', 'morning routine', or 'daily review'.
28align-repo
|
17ralph-it
Pick and implement the next user story from a PRD GitHub issue. Analyzes merged PRs for prior work and findings, proposes a plan, implements it, and creates a PR linking back to the PRD. Use when user says "ralph it", "ralph-it", or wants to work through PRD user stories.
16grill-me
|
14write-a-prd
>
13skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
11