Token导航 LogoToken导航

Agent Skill · 研究检索

outbound-email-strategy(出站电子邮件策略)

outbound-email-strategy 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。

outbound-email-strategy 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,权限为只读;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 26,627。

总安装 3,528周安装 147GitHub Stars 42下载 1,176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:outbound-email-strategy(出站电子邮件策略)
来源仓库:https://github.com/manojbajaj95/claude-gtm-plugin
仓库路径:skills/outbound-email-strategy
安装命令:
npx skills add https://github.com/manojbajaj95/claude-gtm-plugin --skill outbound-email-strategy
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/manojbajaj95/claude-gtm-plugin --skill outbound-email-strategy

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。

outbound-email-strategy 用于查找、检索和筛选相关信息。适合在 Codex、Claude、Cursor、Gemini CLI 中根据关键词快速定位候选结果。通过 npx skills add 命令从指定仓库安装,需结合 README 确认具体用法。

安装前建议核实权限范围、维护状态及是否涉及联网或文件操作。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。

来源仓库内路径:skills/outbound-email-strategy

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/manojbajaj95/claude-gtm-plugin --skill outboun…;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

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

outbound-email-strategy 怎么安装?

在终端执行 npx skills add https://github.com/manojbajaj95/claude-gtm-plugin --skill outbound-email-st…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

outbound-email-strategy 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。

outbound-email-strategy 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

outbound-email-strategy 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。

outbound-email-strategy 用的人多吗?

公开数据是累计安装 3,528 次,近一周安装 147 次,下载 1,176 次,GitHub 42 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。

outbound-email-strategy 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

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。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 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。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 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
outbound-email-strategy

出站电子邮件策略 · 本页

3,52842只读未明确通过

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

Outbound Email Strategy

Expert outbound email execution for B2B sales and business development. Build high-response cold outreach campaigns that feel personalized and drive conversations.

Quick Start

  1. Define ICP — Who are you targeting and why?
  2. Research Prospects — Find personalization signals
  3. Craft the Hook — Lead with value, not a pitch
  4. Build Sequence — 5-7 touches across channels
  5. Handle Responses — Script for every outcome

ICP Framework

Define Your Target

ElementQuestionExample
TitleWho decides?VP of Engineering
CompanyWhat type?B2B SaaS, $1-10M ARR
PainWhat hurts?Content isn't converting
TriggerWhy NOW?Just raised funding
ProofWhy YOU?Helped similar company get result

Questions to Answer

1. What's their job title/role? 2. What company size/type? 3. What industry or vertical? 4. What pain are they experiencing RIGHT NOW? 5. Why should THEY specifically care?

Writing Principles

Write Like a Peer, Not a Vendor

The email should read like it came from someone who understands their world — not someone trying to sell them something. Use contractions. Read it aloud. If it sounds like marketing copy, rewrite it.

Every Sentence Must Earn Its Place

Cold email is ruthlessly short. If a sentence doesn't move the reader toward replying, cut it.

Personalization Must Connect to the Problem

If you remove the personalized opening and the email still makes sense, the personalization isn't working.

Lead with Their World, Not Yours

"You/your" should dominate over "I/we." Don't open with who you are.

One Ask, Low Friction

Interest-based CTAs ("Worth exploring?" / "Would this be useful?") beat meeting requests.


Subject Lines

Short, boring, internal-looking. The subject line's only job is to get the email opened.

Rules:

  • 2-4 words, lowercase, no punctuation
  • Should look like it came from a colleague
  • No product pitches, no urgency, no emojis

Examples:

  • "reply rates"
  • "hiring ops"
  • "Q2 forecast"

Email Sequence Framework

Sequence Types

TypeDurationBest For
Classic Cold7 emails, 2 weeksStandard outreach
Fast-Track5 emails, 1 weekQuick follow-up
Long-Play12-14 emails, 4-6 weeksEnterprise/Nurture
Event-Based3-5 emailsTrigger-specific

Sequence Flow

EmailDayGoalLengthCTA
1: Introduction0Awareness + relevance50-100wSoft ask
2: Value Proof2Establish credibility75-125wMeeting time
3: Different Angle4Alternative pain point50-75wYes/no question
4: Social Proof6Peer validation60-90wSimple reply
5: Resource Share8Give before asking40-60wSoft
6: Direct Ask10Be straightforward30-50wMeeting request
7: Breakup14Final attempt + opt-out25-40w"Close your file?"

Optimal Send Times

Tue–Thu, 10–11 AM or 2–3 PM in recipient's timezone.


Personalization Framework

4-Level System

LevelTimeWhat to Include
Tier 1 (Basic)30 secName, company, industry
Tier 2 (Researched)2-3 minNews, LinkedIn content, job postings
Tier 3 (Deep)10-15 minPodcast quotes, custom video, mutual connections

Research Sources

  • LinkedIn posts and activity
  • Company news/press releases
  • Job postings (indicate priorities)
  • Podcast appearances
  • Conference presentations
  • Mutual connections

Personalization Patterns

Content-Based:

"Your post on X resonated — especially the point about Y."

Hiring Signal:

"Noticed you're hiring X — usually means Y pain."

Company News:

"Saw the news about X. Insight: Y."

Mutual Connection:

"X mentioned you're working on Y. Made me think of Z."

Message Components

The Hook (First Line)

Make it impossible to ignore. Prove you know them.

Good:

  • "Saw your post about X — made me think of Y"
  • "Noticed you're hiring X — usually means Y"
  • "Your talk on X was Y"

Bad:

  • "Hope this email finds you well"
  • "I'm reaching out because..."
  • "I came across your profile..."

The Observation

Show you understand their world.

"Companies at your stage usually struggle with X" "Saw you're scaling — that usually creates Y"

The Value Offer

Give before you ask.

  • "Made you a quick audit"
  • "Put together resource that might help"
  • "Happy to share how we solved this for X"

The CTA

Make it natural and low-friction.

Good:

  • "Worth a look?"
  • "Interested?"
  • "Want me to send it over?"

Bad:

  • "Let's book a 30-minute call"
  • "When are you free to chat?"

Follow-Up Sequences

Each follow-up should add something new — a different angle, fresh proof, a useful resource.

Follow-Up Templates

Email 2 (Value Bump):

"Quick follow-up — additional insight. [Restate offer]."

Email 3 (Different Angle):

"New observation about their business. Thought this might be relevant."

Email 4 (Social Proof):

"Just helped similar company with result. Thought of you."

Email 5 (Break-Up):

"Closing the loop. If problem isn't a priority, no worries. Door's open."

Response Handling

Classification & SLA

Response TypeExampleSLAAction
Positive"Yes, let's talk"5 minBook meeting
Curious"Tell me more"1 hrSend proof point
Objection"Too small"Same dayHandle with framework
Timing"Not now, Q3"Same daySet reminder
Referral"Talk to CFO"1 hrReach out to referral
Hard No"Not interested"24 hrPolite close

Response Scripts

Positive Response:

"Thanks! Here's what I promised. Quick question: [qualifying question]? If [condition], [next step]."

"Not Now" Response:

"No problem. Would it make sense to reconnect in [timeframe]?"

"What's This?" Response:

"In short: [1-sentence value]. [Reoffer value]. Worth a look?"

Skeptical Response:

"Fair to ask. [Proof point]. Happy to share case study if useful."

Cold Call Scripts

Talk Track

  1. Opener: Permission + value in one line
  2. Discovery: 3 questions (current flow, pain metric, priority)
  3. Value Hits: Match pain, cite proof, propose next step
  4. Objections: Acknowledge → brief proof → micro-commit
  5. Close: Time-bound CTA + send calendar while on call

Performance Benchmarks

MetricGoodGreatExceptional
Open Rate35-45%45-55%55%+
Reply Rate3-8%8-15%15%+
Meeting Booked1-3%3-6%6%+

High Reply Rate Signals

  • Personalized opening
  • Clear value prop in first 2 sentences
  • Similar-company social proof
  • Low-friction CTA
  • Clean plain-text formatting

A/B Testing Strategy

Test Elements

ElementTest Approach
Subject linesQuestion vs. Statement
First lineHook types: signal vs. pain vs. question
CTADirect vs. soft vs. value offer
TimingMorning vs. afternoon
LengthShort (50w) vs. medium (100w)

Method

Send 50/50 split to 100 prospects. Wait 48h, measure opens + replies. Winner goes to remaining list.


Volume Guidelines

StageVolumeFocus
Testing (Week 1-2)20-50/dayFind what works
Scaling (Week 3-4)50-100/daySystematize
Cruising (Month 2+)100+/dayMaintain and iterate

Rule: Never sacrifice personalization for volume.


Compliance & Deliverability

Authentication (Required)

  • SPF: Sender Policy Framework
  • DKIM: DomainKeys Identified Mail
  • DMARC: Domain-based Message Authentication

Spam Rate Thresholds

  • Hard ceiling: 0.3% complaint rate
  • Target: <0.1% for reliable inbox

Best Practices

  • Keep sending identity stable
  • Warm up new domains gradually
  • One-click unsubscribe (List-Unsubscribe-Post)
  • Follow CAN-SPAM requirements

Common Mistakes

MistakeWhy It FailsFix
Generic opener"Hope you're well" ignoredSpecific observation
Feature dumpThey don't care yetLead with their pain
Multiple CTAsConfusionSingle clear ask
Long emailsWon't be readUnder 75 words
Same angle each emailNo reason to replyNew value per touch
No personalizationFeels like spamAdd research

The Outbound Math

Example:

  • 100 emails/day × 5 days = 500 emails/week
  • 5% response rate = 25 responses
  • 50% positive = 12-13 interested
  • 50% book calls = 6-7 calls/week
  • 20% close = 1-2 customers/week

That's 4-8 customers/month from outbound.


Related Skills

平台分布

Codex

35.11%
按下载量换算413

Claude

28.37%
按下载量换算334

Cursor

19.3%
按下载量换算227

Gemini CLI

8.25%
按下载量换算97

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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。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