gmail-inbox-triage

$npx mdskill add openai/plugins/gmail-inbox-triage

Sort Gmail messages into priority buckets for quick action.

  • Helps rank unread mail by urgency and reply requirements.
  • Depends on Gmail search and batch reading APIs.
  • Classifies messages using urgency heuristics and thread context.
  • Outputs results in Urgent, Needs reply soon, Waiting, and FYI categories.

SKILL.md

.github/skills/gmail-inbox-triageView on GitHub ↗
---
name: gmail-inbox-triage
description: Triage a Gmail inbox into actionable buckets such as urgent, needs reply soon, waiting, and FYI using connected Gmail data. Use when the user asks to triage the inbox, rank what needs attention, find what still needs a reply, or separate important mail from noise.
---

# Gmail Inbox Triage

## Overview

Use this skill for direct inbox-triage requests. Build on the core Gmail skill at [../gmail/SKILL.md](../gmail/SKILL.md), especially its search and thread-reading guidance.

## Workflow

1. Default to `INBOX` and a clear timeframe unless the user asks for a broader audit.
2. Use `search_emails` to build a shortlist before reading bodies.
3. Exclude obvious noise early if newsletters, calendar churn, or automated alerts dominate the first pass.
4. Use `batch_read_email` only when snippets are not enough to classify urgency or reply-needed status.
5. Escalate to `read_email_thread` when a message appears to be part of an active conversation and the surrounding thread may change the classification. Be careful because low-signal notifications can turn into long threads; `read_email_thread` exposes `total_messages`, which helps detect that.
6. Return the result in explicit Inbox Zero-style buckets such as `Urgent`, `Needs reply soon`, `Waiting`, and `FYI`.

## Bucket Heuristics

- `Urgent`: direct asks with time pressure, blocking messages, decision requests with deadlines, or operational mail that can break if ignored.
- `Needs reply soon`: direct asks without same-day urgency, active conversations where the user is the next responder, or follow-ups that will go stale if ignored.
- `Waiting`: threads where the user already replied or the current blocker belongs to someone else.
- `FYI`: announcements, newsletters, calendar churn, and transactional mail that does not require action.

## Output

- Include sender, subject, why each item is in its bucket, and the likely next action.
- State timeframe, search scope, and confidence.
- Treat reply-needed as an inference, not a guaranteed state.
- Avoid claiming the inbox is fully triaged if you only checked a narrow slice.

More from openai/plugins

SkillDescription
accessibility-and-inclusive-visualizationMake data visualizations accessible and inclusive. Use when the user needs chart or diagram accessibility guidance, text alternatives for complex visuals, color and contrast review, keyboard support, reduced-motion behavior for animation or parallax, or an accessibility QA workflow for exported figures, UML-like diagrams, and dashboards.
agent-browserBrowser automation CLI for AI agents. Use when the user needs to interact with websites, verify dev server output, test web apps, navigate pages, fill forms, click buttons, take screenshots, extract data, or automate any browser task. Also triggers when a dev server starts so you can verify it visually.
agent-browser-verifyAutomated browser verification for dev servers. Triggers when a dev server starts to run a visual gut-check with agent-browser — verifies the page loads, checks for console errors, validates key UI elements, and reports pass/fail before continuing.
agents-sdkBuild AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, or chat applications. Covers Agent class, state management, callable RPC, Workflows integration, and React hooks. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
ai-elementsAI Elements component library guidance — pre-built React components for AI interfaces built on shadcn/ui. Use when building chat UIs, message displays, tool call rendering, streaming responses, reasoning panels, or any AI-native interface with the AI SDK.
ai-gatewayVercel AI Gateway expert guidance. Use when configuring model routing, provider failover, cost tracking, or managing multiple AI providers through a unified API.
ai-generation-persistenceAI generation persistence patterns — unique IDs, addressable URLs, database storage, and cost tracking for every LLM generation
ai-sdkVercel AI SDK expert guidance. Use when building AI-powered features — chat interfaces, text generation, structured output, tool calling, agents, MCP integration, streaming, embeddings, reranking, image generation, or working with any LLM provider.
aiq-deploy|
aiq-research|