agentleFS
prosyo-aiprosyo-ai/gtm-skill/skills/subject-line-writer/SKILL.md

subject-line-writer

Skill13 starsChanged 25 days agoMITView on GitHub

Use this skill when you need cold email subject lines that get opened and do not look like marketing: \"write subject lines for this email\", \"my open rates are low\", \"A/B test subject lines\". Writes short, lowercase, internal-looking subject lines matched to the email's angle, explains the pattern behind each, flags spam and clickbait risks, and sets up a fair subject-line test. For cold outreach, follow-ups and re-engagement emails.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    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 after the email is written.

    line 16
  2. Distinctive:

    No first-name merge field in the subject (it reads as automated), no emojis, no exclamation marks, no "quick question".

    line 39
  3. Distinctive:

    No spam-pattern words: "free", "guarantee", "act now", "limited time", percentages off.

    line 65
  4. Distinctive:

    MUST keep subject lines under 40 characters.

    line 70
  5. Distinctive:

    MUST match the subject to the email's actual content.

    line 71
  6. Distinctive:

    NEVER use fake reply or forward prefixes ("Re:", "Fwd:") on a first email.

    line 72
  7. Distinctive:

    NEVER use a referral subject unless the referral is real.

    line 73

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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 after the email is written. The subject line's job is to get the email opened by the right person without promising something the body does not deliver.

Inputs

  • The email body (subject lines are written for a specific email, never in a vacuum).
  • The persona and seniority.
  • The trigger or angle the email uses.

The play

1. Write in the patterns that work for cold B2B

PatternExampleWhen
Topic, two to four words"month-end close"Default
Trigger reference"new sdr team", "the series b"Email leads with a trigger
Peer or customer"contoso's close"Strong, approved proof
Question"manual reconciliations?"Pain is very common
Their initiative"europe expansion"Announced plan
Mutual context (only if real)"maria suggested i reach out"Genuine referral

2. Follow the format rules

  • 1 to 5 words; under 40 characters so it is not cut on phones.
  • Lowercase or sentence case; it should look like it came from a colleague.
  • No first-name merge field in the subject (it reads as automated), no emojis, no exclamation marks, no "quick question".
  • The subject must be true to the email. Clickbait wins opens and loses replies and trust.

3. Give options per pattern

Return 2-3 options for 3 patterns. Mark the recommended one.

4. Test fairly

  • Change only the subject; keep body, list and send time the same.
  • At least 200 sends per variant before judging.
  • Judge on reply rate, not opens. Open tracking is unreliable: privacy features pre-load images and inflate opens, and many teams disable tracking pixels to protect deliverability.

Output format

Recommended: <subject>
Topic: <3 options>
Trigger: <3 options>
Question: <3 options>
Avoid: <any risky phrasing found and why>
Test: A = <..>, B = <..>, judge on reply rate after 200+ sends each

What good looks like

  • Reads like a peer's email in a crowded inbox.
  • Connects directly to the first line of the email.
  • No spam-pattern words: "free", "guarantee", "act now", "limited time", percentages off.
  • The common mistake is clever or vague subjects ("thoughts?", "a crazy idea") that get opened out of curiosity and then deleted with irritation.

Rules

  • MUST keep subject lines under 40 characters.
  • MUST match the subject to the email's actual content.
  • NEVER use fake reply or forward prefixes ("Re:", "Fwd:") on a first email.
  • NEVER use a referral subject unless the referral is real.

Example prompts

  • "Write subject lines for this cold email to CFOs."
  • "Give me 10 subject lines for a follow-up that shares a case study."
  • "Set up a subject line test for our new campaign."

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.