agentleFS
Sign inStart free
OneWave-AIOneWave-AI/claude-skills/cold-email-sequence-generator/SKILL.md

cold-email-sequence-generator

Skill378 starsChanged 52 days agoMITView on GitHub

Generate personalized cold email sequences (7-14 emails) with A/B test subject lines, follow-up timing recommendations, and integrated social proof. Creates multi-touch campaigns optimized for response rates. Use when users need outbound email campaigns, sales sequences, or lead generation emails.

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Add personalization guidance, performance benchmarks, and optimization recommendations from references/optimization.md.

    line 25
  2. Distinctive:

    Always personalize the first line with something specific about the prospect or their company.

    line 30
  3. Distinctive:

    Keep emails short; the best cold emails run under 100 words.

    line 31
  4. Distinctive:

    Use one ask per email; never bury multiple CTAs.

    line 32
  5. Distinctive:

    Run an A/B test on some variable in every campaign.

    line 34

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Cold Email Sequence Generator

Craft personalized, value-driven cold email sequences with optimal timing, A/B-tested subject lines, and integrated social proof. The goal of cold email is to start a conversation, not to close the sale in the inbox.

Contents

  • references/email-templates.md — Per-position email templates (Emails 1-7), bodies, variables, and social-proof frameworks.
  • references/output-format.md — Delivery structure, flow-and-timing table, sending best practices.
  • references/optimization.md — A/B testing, performance benchmarks, segmentation, pro tips, setup checklist.
  • references/quick-start-templates.md — Vertical-specific subject-line skeletons (SaaS, agency, partnership).

Workflow

  1. Confirm the target audience (ICP) and the core value proposition with the user.
  2. Select the sequence type: Classic Cold Outreach (7 emails / 2 weeks), Fast-Track (5 emails / 1 week), Long-Play Nurture (12-14 emails / 4-6 weeks), Event/Trigger-Based (3-5 emails), or Re-Engagement (5 emails).
  3. Select the personalization level: Hyper-Personal (unique research per prospect), Account-Based (company-specific), Segment-Based (industry/role), or Volume (template with merge tags).
  4. Identify the key pain points and the strongest social proof (case studies, stats, named customers) to support the campaign.
  5. Build the sequence using the per-position templates in references/email-templates.md. Vary the angle across emails: Introduction, Value Proof, Different Angle, Social Proof, Resource Share, Direct Ask, Breakup.
  6. Generate A/B subject-line variations and assign send timing per email, following references/output-format.md.
  7. Add personalization guidance, performance benchmarks, and optimization recommendations from references/optimization.md.
  8. Assemble the final deliverable in the structure defined in references/output-format.md.

Core Rules

  • Always personalize the first line with something specific about the prospect or their company.
  • Keep emails short; the best cold emails run under 100 words.
  • Use one ask per email; never bury multiple CTAs.
  • Honor replies immediately when a prospect says no or asks to stop.
  • Run an A/B test on some variable in every campaign.
  • Invest in follow-up: roughly 80% of responses come from emails 3-7.

Sequence Angle Map

EmailAngleLengthCTA
1Introduction (problem + quick win)50-100 wordsSoft ask
2Value proof (case study)75-125 wordsSpecific meeting time
3Different angle (alt pain point)50-75 wordsYes/no question
4Social proof (peer validation)60-90 wordsSimple reply
5Resource share (give first)40-60 wordsSoft (let me know)
6Direct ask (clear value prop)30-50 wordsDirect meeting request
7Breakup (last attempt + opt-out)25-40 words"Should I close your file?"

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free