email-read

Read inbox and sent via Gmail API

33 stars

Best use case

email-read is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Read inbox and sent via Gmail API

Teams using email-read should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/email-read/SKILL.md --create-dirs "https://raw.githubusercontent.com/aAAaqwq/AGI-Super-Team/main/skills/email-read/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/email-read/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How email-read Compares

Feature / Agentemail-readStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Read inbox and sent via Gmail API

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Email Read

> Read emails from Gmail inbox, sent folder, or any label via Gmail API

## When to use

- "check my email"
- "what's in my inbox"
- "read emails"
- "any new messages?"
- "check sent emails" / "did I send that email?"
- "verify email was sent"
- Morning briefing

## Paths

| What | Path |
|------|------|
| Script | `$GOOGLE_TOOLS_PATH/read_emails.py` |
| Token | `$GOOGLE_TOOLS_PATH/token.json` |

## How to run

```bash
cd $GOOGLE_TOOLS_PATH

# Last 10 unread emails (default)
.venv/bin/python3 read_emails.py

# Last N unread emails
.venv/bin/python3 read_emails.py 20

# All emails (read + unread)
.venv/bin/python3 read_emails.py 10 all

# Custom query
.venv/bin/python3 read_emails.py 5 "from:client@example.com"
.venv/bin/python3 read_emails.py 10 "is:unread subject:invoice"
.venv/bin/python3 read_emails.py 5 "after:2026/02/01"

# SENT emails
.venv/bin/python3 read_emails.py 5 "in:sent"
.venv/bin/python3 read_emails.py 3 "in:sent to:alice@clientc.example.com"
.venv/bin/python3 read_emails.py 5 "in:sent after:2026/02/20"
.venv/bin/python3 read_emails.py 5 "in:sent subject:invoice"
```

## Query examples

| Query | Description |
|-------|-------------|
| `is:unread` | Only unread (default) |
| `all` | All messages |
| `from:team@yourcompany.com` | From specific person |
| `subject:invoice` | By subject |
| `after:2026/02/01` | After date |
| `is:starred` | Starred messages |
| `has:attachment` | With attachments |
| `label:important` | By label |
| `in:sent` | Sent emails |
| `in:sent to:user@example.com` | Sent to specific person |
| `in:sent after:2026/02/20` | Recently sent |
| `in:drafts` | Draft emails |

**Important:** When using `in:sent`, `in:drafts`, or `label:` queries, the script automatically removes the INBOX filter so results from other folders are returned correctly.

## Full thread rule

**IMPORTANT:** When checking email about a specific person, company, or topic -- ALWAYS read the full thread (both inbox and sent). Otherwise you only see half the conversation.

```bash
# CORRECT: full thread with a person
.venv/bin/python3 read_emails.py 10 "from:client@example.com after:2026/02/01"
.venv/bin/python3 read_emails.py 10 "in:sent to:client@example.com after:2026/02/01"

# OR in one query (both sides):
.venv/bin/python3 read_emails.py 20 "{from:client@example.com OR to:client@example.com} after:2026/02/01"
```

**When to apply:**
- "any updates from X?" -- read both sides
- "did they reply to the invoice?" -- read both sent and inbox
- Follow-up checks -- always full thread
- If you only see inbox -- you don't know what we already sent

**When NOT needed:**
- "show inbox" / "check email" -- just inbox
- Morning briefing -- only new incoming

## Output format

```
=== INBOX (N messages) ===        # or === SENT (N messages) ===

1. [NEW] Subject line
   From: Sender Name <email@example.com>
   Date: 2026-02-05 10:30
   Preview: First 100 chars of message...

2. Subject line (no [NEW] = already read)
   ...
```

## OAuth scopes

Uses `gmail.readonly` scope from existing token.json.

## Troubleshooting

| Problem | Solution |
|---------|----------|
| 401 Unauthorized | Refresh token: `google-auth` skill |
| No messages | Check query syntax |
| Token expired | Token auto-refreshes, but if fails run google-auth flow |

## Related skills

- `email-send-direct` - Send single email
- `email-send-bulk` - Mass email sending
- `daily-briefing` - Morning summary including inbox
- `google-auth` - Auth troubleshooting

Related Skills

vp-cpo-readiness-advisor

33
from aAAaqwq/AGI-Super-Team

Coaches Directors and executives through the transition to VP or CPO across four situations: preparing, interviewing, newly landed, or recalibrating at executive level.

sergei-mikhailov-tg-channel-reader

33
from aAAaqwq/AGI-Super-Team

Read posts and comments from Telegram channels via MTProto (Pyrogram or Telethon). Fetch recent messages and discussion replies from public or private channels by time window.

qq-email-operator

33
from aAAaqwq/AGI-Super-Team

QQ邮箱操作技能。支持通过 IMAP/SMTP 读取邮件、搜索邮件、回复邮件、发送邮件。凭据通过 pass 安全存储。

outbound-email-strategy

33
from aAAaqwq/AGI-Super-Team

Comprehensive outbound email strategy skill for cold outreach, email sequences, and multi-channel campaigns. Use when writing cold emails, creating outreach sequences, optimizing response rates, designing follow-up cadences, or building outbound campaigns. Covers prospecting, personalization frameworks, sequence design, subject lines, response handling, compliance, email design, HTML email templates, email layout, email marketing, newsletter design, drip campaigns, email subject lines, email headers, and cold email templates for discovery calls and SDR workflows.

email-outreach-run

33
from aAAaqwq/AGI-Super-Team

Automatic email outreach agent run

email-monitor

33
from aAAaqwq/AGI-Super-Team

AI inbox classification + Telegram notification

email-marketing

33
from aAAaqwq/AGI-Super-Team

Email marketing automation - campaign creation, sequence building, A/B testing, deliverability optimization, and analytics

email-manager

33
from aAAaqwq/AGI-Super-Team

多邮箱统一管理与智能助手。支持 Gmail、QQ邮箱等 IMAP 邮箱,定时查看邮件,AI 生成摘要和回复草稿,发送前需用户确认。

email-automation

33
from aAAaqwq/AGI-Super-Team

邮箱自动化:读取、搜索、草拟和发送邮件,支持 Gmail API 以及通用 IMAP/SMTP 流程。

cold-email-sequence-generator

33
from aAAaqwq/AGI-Super-Team

Generate personalized cold email sequences (7-14 emails) with A/B test subject lines, follow-up timing recommendations, and integrated social proof. Creates multi-touch campaigns optimized for response rates. Use when users need outbound email campaigns, sales sequences, or lead generation emails.

wemp-operator

33
from aAAaqwq/AGI-Super-Team

> 微信公众号全功能运营——草稿/发布/评论/用户/素材/群发/统计/菜单/二维码 API 封装

Content & Documentation

zsxq-smart-publish

33
from aAAaqwq/AGI-Super-Team

Publish and manage content on 知识星球 (zsxq.com). Supports talk posts, Q&A, long articles, file sharing, digest/bookmark, homework tasks, and tag management. Use when publishing content to 知识星球, creating/editing posts, uploading files/images/audio, managing digests, batch publishing, or formatting content for 知识星球.