Token导航 LogoToken导航

Agent Skill · 研究检索

email(邮件)

email 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。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。

email 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为执行命令;许可证信息还不明确,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 65,745。

总安装 275周安装 11GitHub Stars 34下载 89核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

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(邮件)
来源仓库:https://github.com/agricidaniel/claude-email
仓库路径:skills/email
安装命令:
npx skills add https://github.com/agricidaniel/claude-email --skill email
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/agricidaniel/claude-email --skill email

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

email 提供通用电子邮件管理与营销自动化支持。适用于 SaaS、电商、本地服务等各类业务场景。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。支持收件箱分类、邮件撰写、合规审查与送达率诊断。使用前需配置邮箱凭据并遵守反垃圾邮件政策与数据隐私规则。

email 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/email

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/agricidaniel/claude-email --skill email;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要执行命令,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

email 怎么安装?

在终端执行 npx skills add https://github.com/agricidaniel/claude-email --skill email。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

email 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

email 需要什么权限?

权限级别是执行命令。安装流程涉及命令执行,可能通过 npx skills add https://github.com/agricidaniel/claude-email --skill email 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

email 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

email 用的人多吗?

公开数据是累计安装 275 次,近一周安装 11 次,下载 89 次,GitHub 34 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

email 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 需要执行命令,装到常用环境前要先评估影响面。
  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 不能接受 Skill 在你机器上执行命令的人。
  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
email

邮件 · 本页

27534执行命令未明确有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Email -- Universal Email Management & Marketing Skill

Comprehensive email management across all business types (local services, SaaS, e-commerce, creators, agencies). Orchestrates 6 specialized sub-skills and 4 subagents.

Quick Reference

CommandWhat it does
/emailInteractive mode: detect context, show inbox summary or menu
/email checkInbox triage: scan, score importance, categorize, suggest replies
/email writeCompose email: choose framework, generate subject + body + HTML
/email review <email>Pre-send quality check: score subject, copy, HTML, compliance
/email audit <domain>Deliverability audit: SPF/DKIM/DMARC, blacklists, compliance
/email sequence <type>Design automation: welcome, nurture, win-back, cart, custom
/email plan <business>Email marketing strategy with industry template

Orchestration Logic

Interactive Mode (/email)

When invoked without arguments:

  1. Check for email-profile.md in project root
  2. If missing, run first-time onboarding (see User Profile System below)
  3. If profile exists, detect available MCP servers (Gmail, Outlook, SendGrid)
  4. Show interactive menu with inbox summary if email MCP is available

Command Routing

For specific commands, load the relevant sub-skill directly:

  • /email check -> skills/email-check/SKILL.md
  • /email write -> skills/email-write/SKILL.md
  • /email review -> skills/email-review/SKILL.md
  • /email audit -> skills/email-audit/SKILL.md
  • /email sequence -> skills/email-sequence/SKILL.md
  • /email plan -> skills/email-plan/SKILL.md

Audit Delegation

When the user invokes /email audit, delegate to subagents in parallel:

  1. Run scripts/check_deliverability.py for DNS-based checks
  2. Spawn subagents: email-deliverability, email-compliance
  3. Collect results and generate unified Email Health Score (0-100)
  4. Create prioritized fix list (Critical -> High -> Medium -> Low)

User Profile System

On first run, generate email-profile.md in the project root:

  1. Detect existing MCP configurations:

- Check for Gmail MCP tools (search_gmail_messages, send_gmail_message) - Check for Outlook MCP tools (list-mail-messages, send-mail) - Check for marketing MCPs (SendGrid, Mailchimp, Kit.com)

  1. Ask 4 setup questions:

- Business type: local business, SaaS, ecommerce, creator, agency, personal - Primary email platform: Gmail, Outlook, other - Compliance regions: US only, EU/GDPR, both - Brand voice: professional, friendly, casual, authoritative

  1. Generate email-profile.md with these settings
  2. All sub-skills reference this profile to adapt recommendations

Profile-Driven Behavior

Business TypeEmphasis
Local businessReview requests, appointment reminders, loyalty, seasonal promos
SaaSOnboarding sequences, feature announcements, churn prevention, NPS
EcommerceAbandoned cart, post-purchase, promotional, cross-sell/upsell
CreatorNewsletter, community engagement, monetization, content teasers
AgencyClient communication, project updates, case studies, proposals
PersonalInbox management, reply drafts, organization

Quality Gates

Hard rules enforced across all sub-skills:

  • Subject lines: 6-10 words / 30-50 characters
  • Spam complaint rate must stay under 0.1% (hard limit: 0.3%)
  • Bounce rate must stay under 2% (ideal: under 1%)
  • HTML email total size under 102 KB (Gmail clips larger emails)
  • Image-to-text ratio: minimum 60% text / 40% images
  • Every marketing email must include unsubscribe mechanism
  • Every marketing email must include physical postal address (CAN-SPAM)
  • One-click unsubscribe headers required (RFC 8058) for bulk senders
  • Honor unsubscribe requests within 2 business days
  • Never send more than 20 emails per session without explicit approval
  • Always show email draft for approval before sending

Reference Files

Load these on-demand as needed -- do NOT load all at startup:

  • references/deliverability-rules.md -- SPF/DKIM/DMARC validation, bulk sender rules
  • references/benchmarks.md -- KPI benchmarks by industry, scoring thresholds
  • references/compliance.md -- CAN-SPAM, GDPR, CCPA, RFC 8058 requirements
  • references/copy-frameworks.md -- PAS, AIDA, BAB, FAB, 4Ps with templates
  • references/technical-standards.md -- HTML rendering, dark mode, responsive design
  • references/mcp-integration.md -- Setup guides for Gmail, Outlook, SendGrid, etc.

Scoring Methodology

Email Health Score (0-100) -- for /email audit

CategoryWeight
Authentication (SPF+DKIM+DMARC)40%
Blacklist Status20%
DNS Configuration15%
Compliance15%
TLS/Security10%

Email Quality Score (0-100) -- for /email review

CategoryWeight
Subject Line25%
Copy Quality25%
Technical (HTML)20%
Deliverability Signals15%
Compliance15%

Priority Levels

  • Critical: Blocks delivery or causes blacklisting (immediate fix)
  • High: Significantly impacts inbox placement (fix within 1 week)
  • Medium: Optimization opportunity (fix within 1 month)
  • Low: Nice to have (backlog)

Sub-Skills

This skill orchestrates 6 specialized sub-skills:

  1. email-check -- Inbox triage, importance scoring, reply suggestions
  2. email-write -- Email composition with copy frameworks and templates
  3. email-review -- Pre-send quality scoring (0-100)
  4. email-audit -- Domain deliverability audit (SPF/DKIM/DMARC, blacklists)
  5. email-sequence -- Automation sequence design (welcome, nurture, win-back)
  6. email-plan -- Email marketing strategy with industry templates

Subagents

For parallel analysis during audits:

  • email-deliverability -- SPF/DKIM/DMARC + blacklist + reputation checks
  • email-compliance -- CAN-SPAM/GDPR/CCPA compliance scanning
  • email-content -- Copy quality and framework adherence scoring
  • email-inbox -- Inbox categorization and importance scoring

MCP Integration

Detecting Available MCP Tools

Check for these tool patterns to determine available platforms:

  • Gmail: search_gmail_messages, send_gmail_message, get_gmail_message_content
  • Outlook: list-mail-messages, send-mail, get-mail-message
  • SendGrid: send_single_email, list_all_contacts, get_stats
  • Mailchimp: get_campaigns, create_campaign, send_campaign
  • Kit.com: kit_list_subscribers, kit_create_broadcast

If no email MCP is detected, inform the user and offer setup guidance from references/mcp-integration.md.

平台分布

Codex

35.6%
按下载量换算32

Claude

32.16%
按下载量换算29

Cursor

17.39%
按下载量换算15

Gemini CLI

10.25%
按下载量换算9

安全审计

Gen Agent Trust Hub

通过

Socket

可疑

Snyk

可疑

权限和风险

执行命令

安装流程涉及命令执行,可能通过 npx skills add https://github.com/agricidaniel/claude-email --skill email 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills