gmail-inbox-zero

33
3
Source

Gmail Inbox Zero Triage - Interactive inbox management using gog CLI with Telegram buttons. Use when the user wants to achieve inbox zero, triage their Gmail inbox interactively, process ALL inbox messages (read and unread) with AI summaries and batch actions (archive, filter, unsubscribe). OAuth-based, no passwords needed.

Install

mkdir -p .claude/skills/gmail-inbox-zero && curl -L -o skill.zip "https://mcp.directory/api/skills/download/2800" && unzip -o skill.zip -d .claude/skills/gmail-inbox-zero && rm skill.zip

Installs to .claude/skills/gmail-inbox-zero

About this skill

Gmail Inbox Zero Triage

Achieve inbox zero with AI-powered email triage! Process ALL Gmail inbox messages interactively with summaries and batch actions using OAuth (no passwords needed).

Features

OAuth-based - No passwords, secure authentication via gog
AI summaries - Quick 1-line summary of each email
Batch processing - Queue actions instantly, execute at the end
Telegram buttons - Archive, Filter, Unsubscribe, View
Inbox zero focus - Process ALL inbox messages (read + unread)
Fast workflow - No waiting between actions

Workflow

  1. User triggers: "Triage my emails" or "Process my inbox"
  2. Fetch ALL inbox messages from Gmail (up to 20 at a time)
  3. Display all emails at once with:
    • Subject and sender
    • AI-generated summary (1 line)
    • Telegram inline buttons for actions
  4. User clicks actions for each email (queued instantly, no API calls yet)
  5. User clicks "Done" button to execute all queued actions in batch
  6. Repeat until inbox zero! 🎯

Prerequisites

Requires: gog CLI with authenticated Gmail account.

Check if already set up:

gog auth list

If not set up, user needs to run gog auth add (see gog skill for OAuth setup).

Set environment variable for keyring password:

export GOG_KEYRING_PASSWORD="your-password"

Telegram Button Layout

Each email displays with 4 action buttons:

[📥 Archive] [🔍 Filter]
[🚫 Unsub]   [📧 View]
  • 📥 Archive - Remove from inbox, mark as read
  • 🔍 Filter - Create filter to auto-archive future emails from sender
  • 🚫 Unsubscribe - Find and open unsubscribe link
  • 📧 View - Show full email content
  • No click = Skip (leave in inbox)

At the end:

[✅ Done - Execute All Actions]

Action Queue System

Actions are queued using short callback codes to avoid Telegram's 64-char limit:

  • q:a:0 = queue archive, message index 0
  • q:f:0 = queue filter, message index 0
  • q:u:0 = queue unsubscribe, message index 0
  • q:v:0 = view full email, message index 0 (executes immediately)
  • q:done = execute all queued actions

Queue is managed via scripts/queue_manager.py and stored in action_queue.json.

Scripts

gog_processor.py

Main processor for Gmail operations via gog CLI.

List inbox messages:

python3 scripts/gog_processor.py list <account> [limit]

Archive a message:

python3 scripts/gog_processor.py archive <account> <msg_id>

Find unsubscribe link:

python3 scripts/gog_processor.py unsubscribe <account> <msg_id>

Create filter:

python3 scripts/gog_processor.py filter <account> "<from_header>"

Get message body:

python3 scripts/gog_processor.py body <account> <msg_id>

queue_manager.py

Manages action queue for batch execution.

Add action to queue:

python3 scripts/queue_manager.py add <action> <msg_id> [from_header]

Get queue:

python3 scripts/queue_manager.py get

Clear queue:

python3 scripts/queue_manager.py clear

execute_queue.py

Executes all queued actions in batch.

python3 scripts/execute_queue.py <account>

Returns JSON with results of all executed actions.

Implementation Steps

  1. Load current batch: Fetch inbox messages and save to current_batch.json
  2. Display all emails: Show each with summary and buttons
  3. Handle button callbacks:
    • Archive/Filter/Unsub: Add to queue via queue_manager.py
    • View: Fetch and display full email immediately
    • Done: Execute queue via execute_queue.py
  4. Show results: Report archived count and remaining inbox count
  5. Repeat if needed: Fetch next batch or celebrate inbox zero

AI Summary Guidelines

Generate concise 1-line summaries:

  • Receipts/Invoices: "Payment receipt for $X. Financial record."
  • Security alerts: "Security notification about [action]. [Important/Standard] alert."
  • Newsletters: "Newsletter about [topic]. No action required."
  • Calendar: "Calendar [event type] for [date/time]."
  • Legal: "Legal [document type]. [Brief context]."

Keep it simple, factual, and action-oriented.

Security Notes

  • OAuth-based authentication - No passwords needed, uses gog's OAuth tokens
  • Tokens stored securely by gog CLI in system keychain
  • Read/modify permissions - gog only gets access to what user grants
  • Queue stored locally - Action queue is temporary, cleared after execution

Error Handling

Common issues:

  • gog not authenticated: Run gog auth add <account>
  • Account not found: Check gog auth list for available accounts
  • No inbox messages: Success state - inbox zero achieved!
  • Permission denied: User may need to re-authenticate with gog
  • Keyring password: Set GOG_KEYRING_PASSWORD environment variable

Dependencies

  • gog CLI - Must be installed and authenticated (see gog skill)
  • Python 3 - Standard library only (subprocess, json, re, pathlib)

No additional pip packages needed.

Tips for Best Experience

  • Process regularly: Triage inbox daily to maintain inbox zero
  • Use filters liberally: Auto-archive recurring newsletters and notifications
  • Archive aggressively: If you don't need it now, archive it (searchable in All Mail)
  • Batch mode is fast: Process 10-20 emails in under a minute
  • Trust the summaries: AI summaries are accurate for quick decisions

a-stock-analysis

openclaw

A股实时行情与分时量能分析。获取沪深股票实时价格、涨跌、成交量,分析分时量能分布(早盘/尾盘放量)、主力动向(抢筹/出货信号)、涨停封单。支持持仓管理和盈亏分析。Use when: (1) 查询A股实时行情, (2) 分析主力资金动向, (3) 查看分时成交量分布, (4) 管理股票持仓, (5) 分析持仓盈亏。

754288

fivem

openclaw

Fix, create, or validate FiveM server resources for QBCore/ESX (config.lua, fxmanifest.lua, items, housing/furniture, scripts, MLOs). Use when asked to debug resource errors, convert ESX↔QB, update fxmanifest versions, add items, or source scripts from GitHub. Also use for SSH key generation for SFTP access.

408258

research-paper-writer

openclaw

Creates formal academic research papers following IEEE/ACM formatting standards with proper structure, citations, and scholarly writing style. Use when the user asks to write a research paper, academic paper, or conference paper on any topic.

81168

keyword-research

openclaw

Discovers high-value keywords with search intent analysis, difficulty assessment, and content opportunity mapping. Essential for starting any SEO or GEO content strategy.

439107

html-to-ppt

openclaw

Convert HTML/Markdown to PowerPoint presentations using Marp

33389

weread

openclaw

WeChat Reading (微信读书) CLI tool for fetching notes and highlights. Use when: (1) user asks about weread/微信读书 notes or highlights, (2) fetching today's or recent reading notes, (3) exporting book highlights, (4) managing reading bookshelf, (5) any task involving reading notes from WeChat Reading.

11285

You might also like

ui-ux-pro-max

nextlevelbuilder

"UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient."

2,8642,517

pdf-to-markdown

aliceisjustplaying

Convert entire PDF documents to clean, structured Markdown for full context loading. Use this skill when the user wants to extract ALL text from a PDF into context (not grep/search), when discussing or analyzing PDF content in full, when the user mentions "load the whole PDF", "bring the PDF into context", "read the entire PDF", or when partial extraction/grepping would miss important context. This is the preferred method for PDF text extraction over page-by-page or grep approaches.

3,7841,648

flutter-development

aj-geddes

Build beautiful cross-platform mobile apps with Flutter and Dart. Covers widgets, state management with Provider/BLoC, navigation, API integration, and material design.

2,1471,638

drawio-diagrams-enhanced

jgtolentino

Create professional draw.io (diagrams.net) diagrams in XML format (.drawio files) with integrated PMP/PMBOK methodologies, extensive visual asset libraries, and industry-standard professional templates. Use this skill when users ask to create flowcharts, swimlane diagrams, cross-functional flowcharts, org charts, network diagrams, UML diagrams, BPMN, project management diagrams (WBS, Gantt, PERT, RACI), risk matrices, stakeholder maps, or any other visual diagram in draw.io format. This skill includes access to custom shape libraries for icons, clipart, and professional symbols.

2,2621,465

godot

bfollington

This skill should be used when working on Godot Engine projects. It provides specialized knowledge of Godot's file formats (.gd, .tscn, .tres), architecture patterns (component-based, signal-driven, resource-based), common pitfalls, validation tools, code templates, and CLI workflows. The `godot` command is available for running the game, validating scripts, importing resources, and exporting builds. Use this skill for tasks involving Godot game development, debugging scene/resource files, implementing game systems, or creating new Godot components.

2,4591,222

nano-banana-pro

garg-aayush

Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.

1,952967