agentleFS
Sign inStart free
prosyo-aiprosyo-ai/gtm-skill/skills/cold-email-sequence/SKILL.md

cold-email-sequence

Skill13 starsChanged 21 days agoMITView on GitHub

Use this skill when you need a complete cold email sequence (cadence) for a campaign: \"write a 4-step outbound sequence\", \"build an email campaign for this segment\", \"plan the follow-ups\". Designs the number of steps, spacing and angle of each email so every touch adds something new, writes all emails with subject lines, defines when people leave the sequence, and sets the metrics that decide whether to keep, change or kill it.

2 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

8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this to build a whole campaign rather than one email.

    line 16
  2. Distinctive:

    Add LinkedIn or phone steps between emails when the channel fits the persona.

    line 36
  3. Distinctive:

    No step repeats the previous one.

    line 39
  4. Distinctive:

    MUST give every step a distinct angle.

    line 66
  5. Distinctive:

    MUST stop the sequence on reply, booking, bounce or opt-out.

    line 67
  6. Distinctive:

    MUST pause, not continue, when an out-of-office names a return date.

    line 68
  7. Distinctive:

    NEVER send more than 5 cold emails to one person in a sequence.

    line 69
  8. Distinctive:

    NEVER guilt-trip in follow-ups.

    line 70

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Use this to build a whole campaign rather than one email. It produces a sequence where each step has its own angle, so follow-ups add value instead of saying "just bumping this".

Inputs

  • Segment, persona and the problem the campaign is about.
  • Approved proof: customer stories, numbers, assets you can share.
  • Goal: meetings, replies to a question, sign-ups.

The play

1. Set the shape

The default for cold B2B is 4 emails over about 14-18 days:

StepDayAngleLength
10Observation → problem → proof → ask50-90 words
23New angle: a different pain or a sharper insight40-70 words, same thread
37-8Proof: a short customer story or a useful asset60-90 words, new thread
414-16Close the loop: a polite final note, easy out25-50 words

Add LinkedIn or phone steps between emails when the channel fits the persona; the multichannel cadence covers that.

2. Give each step one job

No step repeats the previous one. Every follow-up must stand alone: many people only ever see one of the emails. Read references/sequence-example.md for a full annotated 4-step example and step-by-step variations.

3. Thread deliberately

Step 2 replies in the same thread (it reads as a natural follow-up). Step 3 starts a new thread with a new subject, which gives a second chance at the inbox. Step 4 can go either way.

4. Define exits

People leave the sequence when they reply (any reply, including out-of-office with a return date: pause, not stop), book, bounce, opt out, or when anyone at the same account books a meeting.

5. Set the scorecard

Judge after 150-300 contacts per variant:

MetricHealthyAction if below
Bounce rateunder 2%Stop; clean the list
Reply rate5%+Rework angle or targeting
Positive reply rate1.5-3%+Rework offer and ask
Meetings per 100 contacts1+Check reply handling speed

What good looks like

  • Step 3 could be someone's first email and still make sense.
  • No "just following up", "bumping this to the top", or "did you see my last email".
  • The final email is gracious and gets replies in its own right: "not a priority" answers are useful data.
  • The common mistake is seven emails with the same pitch reworded; volume of touches without new value burns the list.

Rules

  • MUST give every step a distinct angle.
  • MUST stop the sequence on reply, booking, bounce or opt-out.
  • MUST pause, not continue, when an out-of-office names a return date.
  • NEVER send more than 5 cold emails to one person in a sequence.
  • NEVER guilt-trip in follow-ups.

Example prompts

  • "Write a 4-step sequence for Heads of Finance at 200-1,000 person SaaS companies. Problem: month-end close takes too long."
  • "Turn this single cold email into a full sequence."
  • "Our sequence gets replies on step 1 only. Rewrite steps 2-4."

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