Token导航 LogoToken导航TokenDH.com
待分类需要联网github未标认证来源可访问许可证需确认审计通过

email-skills电子邮件技巧

Agent Skill

email-skills 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

541

周安装

12

GitHub Stars

13

下载量

97
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:email-skills(电子邮件技巧)
来源仓库:https://github.com/autosendhq/email-skills
仓库路径:skills/email-skills
安装命令:
npx skills add https://github.com/autosendhq/email-skills --skill email-skills
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/autosendhq/email-skills --skill email-skills

简介

email-skills 聚焦于提升 AI 代理撰写、审核或建议专业邮件的能力。

  • 强调收件箱到达率而非单纯发送量,涵盖认证、信誉、内容和列表管理等维度。
  • 为不同业务场景提供结构化指导,确保邮件风格一致且符合行业最佳实践。
  • 使用时应结合具体品牌调性和目标受众调整输出结果。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

Email Skills by AutoSend

A modular skill set for AI agents writing, reviewing, or advising on email. The goal is inbox placement, not just sending. Every decision here connects back to that.

This is the entry point. Read this first, then load the relevant sub-skill for deeper guidance on a specific topic.


The Deliverability Stack

Inbox placement depends on four pillars working together. A failure in any one of them can undo the other three.

1. Authentication   → Proves you are who you say you are
2. Sender Reputation → Proves you are a responsible sender
3. Content Quality  → Proves your email is wanted
4. List Quality     → Proves your recipients consented and are real

Sub-Skills (Load as Needed)

TopicSub-SkillWhen to Use
SPF, DKIM, DMARC, BIMIauthentication/SKILL.mdSetting up or debugging email authentication
Subject lines, HTML, copycontent/SKILL.mdWriting or reviewing email content
CAN-SPAM, GDPR, CASLcompliance/SKILL.mdAny question touching legal requirements or consent
Validation, suppression, sunsetlist-hygiene/SKILL.mdManaging contacts, bounces, or unsubscribes
OTP, receipts, password resettransactional/SKILL.mdBuilding or writing transactional email flows
Drip, campaigns, segmentationmarketing-campaigns/SKILL.mdWriting or planning marketing email
Drip sequences, lifecycle flowsemail-automation/SKILL.mdChoosing or building automated email sequences
Postmaster Tools, blacklistsmonitoring/SKILL.mdDiagnosing issues or setting up monitoring

Core Principles (Always Apply)

These apply regardless of which sub-skill you load.

Separate transactional from marketing. Different sending streams, different subdomains. A spam complaint on your marketing stream should never affect transactional delivery.

Send from a subdomain, not your root domain. Use mail.yourdomain.com or em.yourdomain.com. This isolates email reputation from your web domain.

Authenticate before you send anything. SPF, DKIM, and DMARC must be in place before volume matters. See authentication/SKILL.md.

List quality beats list size. Sending to disengaged or invalid addresses actively damages your domain reputation. See list-hygiene/SKILL.md.

Open rate is not a reliable metric. Apple Mail Privacy Protection inflates open rates by pre-fetching tracking pixels. Use click rate, reply rate, and conversion rate instead.

Consistency matters more than volume. Sudden spikes in sending volume look like compromised accounts to inbox providers. Ramp gradually and send at a predictable cadence.

Google's spam rate threshold is 0.08%. Above this, Gmail delivery degrades. Above 0.1%, mail starts getting blocked. Monitor this daily via Google Postmaster Tools.


Transactional vs. Marketing: The Key Distinction

DimensionTransactionalMarketing
TriggerUser actionSender-initiated
Unsubscribe requiredNo (best practice: include support path)Yes, legally required
Consent requiredImplied by account creationExpress opt-in
Promotional contentIncidental onlyYes
Sending streamSeparateSeparate

Common transactional types: password reset, 2FA/OTP, order confirmation, shipping update, billing receipt, account alert, email verification.


Pre-Send Checklist (Quick Reference)

Authentication

  • SPF record published and valid
  • DKIM signing active and selector resolving
  • DMARC policy published (p=none minimum to start)

Content

  • Subject line: under 60 chars, no spam trigger words, not misleading
  • Preview text set explicitly (not left to the client to guess)
  • Plain-text version included alongside HTML
  • No JavaScript, no URL shorteners
  • All images have alt text
  • Physical mailing address in footer (required for commercial email)
  • Unsubscribe link present and functional (marketing only)

List

  • Addresses validated before import
  • Suppression list applied before send
  • Consent documented for all marketing contacts

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

34.6%
按下载量换算34

Claude

33.22%
按下载量换算32

Cursor

17.64%
按下载量换算17

Gemini CLI

9.39%
按下载量换算9

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills