This handles email sending and receiving through QQ or 163 mailboxes in China, with support for attachments, checking for new messages, and deletion. You'll need to grab an authorization code from your email provider's IMAP/SMTP settings, not your regular login password. The command line interface is straightforward with JSON output options for AI parsing. Worth noting that QQ uses IMAP so deleted emails go to trash and can be recovered, while 163 uses POP3 so deletions are permanent. If you're working with Chinese email services and need programmatic access, this covers the basics without much fuss.

GitHub stars
722
last updated
Jun 1, 2026

Install

$ npx -y skills add countbot-ai/countbot --skill email --agent claude-code

Installs into .claude/skills of the current project.

Files

邮件管理

通过 QQ 或 163 邮箱发送和接收邮件。

配置

编辑 skills/email/scripts/config.json,填写邮箱地址和授权码(非登录密码)。

授权码获取:

  • QQ 邮箱:设置 > 账户 > 开启 IMAP/SMTP > 生成授权码
  • 163 邮箱:设置 > POP3/SMTP/IMAP > 开启服务 > 设置授权密码

可通过 default_mailbox 字段设置默认邮箱("qq" 或 "163")。

命令行调用

# 发送邮件
python3 skills/email/scripts/mail.py send --to user@example.com --subject "主题" --content "内容"

# 发送带附件
python3 skills/email/scripts/mail.py send --to user@example.com --subject "报告" --content "请查收" --attach report.pdf

# 接收最新邮件
python3 skills/email/scripts/mail.py receive --limit 5

# 接收邮件(JSON 输出,推荐 AI 使用)
python3 skills/email/scripts/mail.py receive --limit 5 --json

# 检查新邮件(最近 N 天)
python3 skills/email/scripts/mail.py check-new --since 1

# 检查新邮件(JSON 输出)
python3 skills/email/scripts/mail.py check-new --since 1 --json

# 删除邮件(移到已删除文件夹,QQ邮箱可恢复)
python3 skills/email/scripts/mail.py delete --ids 123

# 批量删除
python3 skills/email/scripts/mail.py delete --ids 123 124 125

# 彻底删除(不可恢复)
python3 skills/email/scripts/mail.py delete --ids 123 --permanent

# 指定邮箱类型
python3 skills/email/scripts/mail.py --mailbox 163 send --to user@example.com --subject "测试"

删除邮件说明

Sponsors

Details

Repository
github.com/countbot-ai/countbot
License
MIT
First seen
Jun 11, 2026

More from countbot-ai/countbot

All 14

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs