Token导航 LogoToken导航

Agent Skill · 研究检索

cold-email-sequence-generator-skill(冷邮件序列生成器技巧)

cold-email-sequence-generator-skill 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。

cold-email-sequence-generator-skill 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,第三方扫描有未通过项,按安装量在研究检索类的 73,675 个 Skill 里排第 67,439。

总安装 245周安装 10GitHub Stars 12下载 78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:cold-email-sequence-generator-skill(冷邮件序列生成器技巧)
来源仓库:https://github.com/scientiacapital/skills
仓库路径:skills/cold-email-sequence-generator-skill
安装命令:
npx skills add https://github.com/scientiacapital/skills --skill cold-email-sequence-generator-skill
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/scientiacapital/skills --skill cold-email-sequence-generator-skill

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。

cold-email-sequence-generator-skill 支持 A/B 变体的冷邮件序列生成。读取 config.json 判断是否启用变体分配机制,自动标记测试组。输出包含完整七封邮件模板、主题行、个性化变量与性能基准。

需配合 scripts/variant-assigner.sh 脚本来实现分组逻辑处理。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/cold-email-sequence-generator-skill

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/scientiacapital/skills --skill cold-email-sequ…;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

cold-email-sequence-generator-skill 怎么安装?

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

cold-email-sequence-generator-skill 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。

cold-email-sequence-generator-skill 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。

cold-email-sequence-generator-skill 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。

cold-email-sequence-generator-skill 用的人多吗?

公开数据是累计安装 245 次,近一周安装 10 次,下载 78 次,GitHub 12 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。

cold-email-sequence-generator-skill 安全吗?

第三方扫描有未通过项,风险较高。除非你确认过源码,否则不建议直接安装到常用环境。

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。
  • 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。
  • 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
cold-email-sequence-generator-skill

冷邮件序列生成器技巧 · 本页

24512只读未明确未通过

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

Cold Email Sequence Generator

<quick_start> Trigger: "Create a cold email sequence for [audience]" or "Write a 7-email sequence for [use case]" Input: Target audience/ICP, your value proposition, social proof/case studies, sequence length Output: Full email sequence with subject lines (A/B), body copy, timing, personalization variables, and performance benchmarks </quick_start>

<variant_support> This skill supports A/B variants via config.json.

  1. Read this skill's config.json — check if variants.enabled is true
  2. If enabled, run: bash scripts/variant-assigner.sh cold-email-sequence-generator-skill $(date +%s)
  3. Apply the prompt_suffix from the assigned variant's definition to modify the workflow
  4. Record the variant name in the outcome sidecar (see final stage below)

Current experiment: cold-email-subject-style-001

  • control: Standard 7-email framework
  • concise: 5-email framework, 50-word max per email </variant_support>

<success_criteria>

  • Sequence type selected (Classic 7-email, Fast-Track 5, Long-Play 12-14, Event-Based, Re-Engagement)
  • Each email has A/B subject lines, body copy, and clear single CTA
  • Send timing and day/time recommendations included
  • Personalization variables identified with sourcing guidance
  • Social proof integrated (case studies, stats, testimonials)
  • Breakup email included as final touch
  • Performance benchmarks provided for optimization </success_criteria>

Sequence Types

  1. Classic Cold Outreach (7 emails, 2 weeks)
  2. Fast-Track (5 emails, 1 week)
  3. Long-Play Nurture (12-14 emails, 4-6 weeks)
  4. Event/Trigger-Based (3-5 emails, event-specific)
  5. Re-Engagement (5 emails, revive old leads)

Email Sequence Framework

Email #RoleGoalLengthCTA Style
1IntroductionMake them aware you exist50-100 wordsSoft ask (reply, quick question)
2Value ProofEstablish credibility75-125 wordsSpecific meeting time
3Different AngleAddress alternative pain50-75 wordsYes/no question
4Social ProofShow peer validation60-90 wordsSimple reply
5Resource ShareGive before asking40-60 wordsSoft (let me know if helpful)
6Direct AskBe straightforward30-50 wordsDirect meeting request
7BreakupLast attempt + opt-out25-40 words"Should I close your file?"

Timing & Sending

Email #DayTimeExpected Open Rate
1Day 010:00 AM40-50%
2Day 211:00 AM30-40%
3Day 42:00 PM25-35%
4Day 610:30 AM20-30%
5Day 83:00 PM15-25%
6Day 109:00 AM12-20%
7Day 144:00 PM10-18%

Best Practices: Tuesdays-Thursdays highest open rates. 10-11 AM and 2-3 PM optimal. Avoid Mondays (inbox overload) and Fridays (weekend mode). Send in recipient's local timezone.

Email Templates

Email #1: The Introduction

Subject Lines (A/B Test):

  • A (Curiosity): Quick question about [their company]'s [specific challenge]
  • B (Value): [Quantifiable outcome] for [their company type]
  • C (Personal): [Name], saw your post about [specific topic]
Hi [First Name],

I noticed [specific observation about their company/role] and thought you might be facing [specific challenge].

We've helped [similar company 1] and [similar company 2] [achieve specific outcome] without [common objection].

Worth a quick 15-minute conversation to see if we can do the same for [their company]?

Best,
[Your Name]

P.S. - [Personalized one-liner based on research]

Email #2: The Value Proof

Subject: "How [Similar Company] achieved [specific result]"

[First Name],

Following up—wanted to share how this worked for a company like [theirs].

[Similar Company] was [specific situation]. In just [timeframe], they:
- [Specific result #1 with metric]
- [Specific result #2 with metric]
- [Specific result #3 with metric]

The best part? They got started in under [timeframe] without [common objection].

Would [Day] at [Time] work for 15 minutes?

[Your Name]

Email #3: The Different Angle

Subject: "Different thought about [their company]"

Hi [First Name],

I realize [original pain point] might not be top of mind right now.

But what about [alternative pain point]?

Most [their role]s say [common complaint], which is why [mini value prop].

If this hits closer to home, happy to share how [quick win].

[Your Name]

P.S. - If neither is relevant, just let me know and I'll stop!

Email #4: The Social Proof

Subject: "[Mutual connection] suggested I reach out" OR "How [competitor] handles [challenge]"

[First Name],

I was speaking with [name/title] at [similar company] about [challenge].

Here's what they said after implementing [solution]:
"[Direct quote with specific result]"

Open to a quick call to hear more about what's working in [their industry]?

[Your Name]

Email #5: The Resource Share

Subject: "Thought you might find this useful"

[First Name],

No ask here—just sharing something helpful:

[Brief description of resource]: [Link]

We created this after hearing [their role]s struggle with [pain point]. Actionable tips even if you never use our product.

Hope it helps!

[Your Name]

Email #6: The Direct Ask

Subject: "Let's cut to the chase"

[First Name],

Let me be direct: I think we could help [their company] [achieve outcome] based on [observation].

I'd like to show you:
1. [Specific thing #1]
2. [Specific thing #2]
3. [How others in their position use it]

15 minutes. No pressure. How's [specific day/time]?

[Your Name]
[Phone number]

Email #7: The Breakup

Subject: "Should I close your file?"

[First Name],

I'll assume [topic] isn't a priority right now—totally fine.

I'll close your file unless I hear otherwise. For what it's worth, we see best results when [time-sensitive reason], so if you want to revisit, might be worth a quick chat now.

No worries either way—appreciate your time.

[Your Name]

P.S. - If someone else at [their company] should hear about this, happy to redirect.

Breakup Variations:

  • FOMO: "Taking you off the list. FYI—[competitor] just started and is seeing [early result]."
  • Permission: "Assuming this is: 1) Not relevant, 2) Not priority, 3) Bad timing. Which? If #3, when should I check back?"
  • Referral: "Clearly I'm not reaching the right person. Should I talk to someone else about [topic]?"

A/B Testing Strategy

Test Priority (in order):

  1. Subject Lines: Question vs. Statement, Generic vs. Personalized, Short vs. Long
  2. Email Body: Length (50 vs. 100 words), CTA style (Link vs. Question vs. Time slot)
  3. Send Time: Morning vs. Afternoon, Tue vs. Wed vs. Thu

Method: Send to 100 prospects (50/50 split), wait 48 hours, measure open + reply rates, winner goes to remaining list.

Performance Benchmarks

MetricGoodGreatExceptional
Email 1 Open Rate35-45%45-55%55%+
Email 1 Reply Rate3-8%8-15%15%+
Sequence Reply Rate8-15%15-25%25%+
Positive Reply %40-50%50-70%70%+
Meeting Booked %1-3%3-6%6%+

Segmentation

Adjust sequences by Industry (swap case studies, use industry terminology), Company Size (Startup: ROI focus; Mid-Market: scalability; Enterprise: security/compliance), Role (Executive: strategic outcomes; Practitioner: time savings; Technical: architecture/specs), and Intent (Hot: shorter/faster; Warm: standard 7-email; Cold: longer nurture).

Quick-Start Templates

SaaS Sales: Question about growth metric → Competitor case study → Alternative pain → Mutual connection → Free benchmark report → 15-min demo → Close file

Agency/Services: Recent achievement → Client case study → Quick idea for challenge → Competitor approach → No-strings audit → 15-min call → Bad timing?

Partnership: Mutual contact intro → Win-win opportunity → Similar partner example → Partnership program question → Worth exploring?

Pro Tips

  1. 3-Second Rule: Prospect should understand value in first 3 seconds
  2. One CTA Only: Don't give multiple options
  3. Mobile-First: 50%+ opened on mobile; keep scannable
  4. No Attachments: Use links; attachments trigger spam filters
  5. The P.S. Works: PostScripts get read; use for secondary CTA
  6. Follow-Up Matters: 80% of responses come from emails 3-7

Pre-Launch Checklist

  • Sender email has good deliverability (SPF, DKIM, DMARC)
  • Email warmed up (sent successful emails recently)
  • List cleaned (no invalid emails)
  • Personalization variables all filled
  • Links tested and tracked
  • CRM integration working
  • A/B tests configured
  • Daily send limits set (avoid spam flags)

Emit Outcome Sidecar

As the final step, write to ~/.claude/skill-analytics/last-outcome-cold-email-sequence-generator.json:

{"ts":"[UTC ISO8601]","skill":"cold-email-sequence-generator","version":"1.1.0",
 "variant":"[assigned variant or default]","status":"[success|partial|error]",
 "runtime_ms":[estimated ms from start],
 "metrics":{"sequences_created":1,"emails_generated":[count],"subject_variants_generated":[count]},
 "error":null,"session_id":"[YYYY-MM-DD]"}

平台分布

Codex

38.81%
按下载量换算30

Claude

30.77%
按下载量换算24

Cursor

17.18%
按下载量换算13

Gemini CLI

10.45%
按下载量换算8

安全审计

Gen Agent Trust Hub

未通过

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。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