agentleFS
Sign inStart free
prosyo-aiprosyo-ai/gtm-skill/skills/first-line-personalization/SKILL.md

first-line-personalization

Skill13 starsChanged 22 days agoMITView on GitHub

Use this skill when you need personalised first lines (icebreakers) for cold emails or LinkedIn messages at scale: \"write personalised openers for this list\", \"add a custom first line for each lead\", \"make my outreach feel 1:1\". Researches each prospect for a real, relevant hook, writes a one or two sentence opener that bridges to the email's problem, grades each line, and falls back to an honest role-based line when nothing specific exists. Never invents details.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 9 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    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 add a personal opener to each contact on a list.

    line 16
  2. Distinctive:

    No bridge: "Loved your podcast episode on hiring."

    line 32
  3. Distinctive:

    When research finds nothing, write a C line about the role at their company's stage.

    line 46
  4. Distinctive:

    Every A and B line has a source link a reviewer can click.

    line 61
  5. Distinctive:

    MUST attach a source to every A and B line.

    line 67
  6. Distinctive:

    MUST use a fallback line rather than invent a detail.

    line 68
  7. Distinctive:

    NEVER mention personal life, family, health or appearance.

    line 69
  8. Distinctive:

    NEVER claim to have read, watched or listened to something you did not.

    line 70
  9. Distinctive:

    NEVER reference profile views, website visits or other tracking.

    line 71

≈ “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 add a personal opener to each contact on a list. The line proves the email was written for the reader and leads naturally into the problem the email is about.

Inputs

  • The list: name, title, company, profile link, domain.
  • The email the line will open, so the line can bridge into it.
  • Allowed sources: company site, news, job listings, the person's public posts and talks.

The play

1. Research each lead quickly

Spend 1-3 minutes per lead. Look for, in order: something they said or wrote, a change in their role or team, a company trigger, a specific detail of how their company works.

2. Write the line with a bridge

Formula: specific observation + why it connects to the email's problem. The second half is what makes personalization work; an observation with no bridge is a compliment, and compliments get ignored.

  • No bridge: "Loved your podcast episode on hiring."
  • With bridge: "Your point on the podcast that hiring SDRs is easy and ramping them is hard is exactly the problem below."

3. Grade every line

GradeMeaning
ASpecific to the person and connected to the problem
BSpecific to the company and connected
CRole or industry level, honest and relevant (fallback)
FailInvented, generic flattery, or unrelated trivia; never ship

Aim for A or B on Tier 1 contacts; C is acceptable for Tier 3.

4. Write fallbacks, never fiction

When research finds nothing, write a C line about the role at their company's stage. A sincere role-level line outperforms a fake personal one, and it never gets caught.

5. Check the merge

The line must read naturally after "Hi {first name}," and before the email's second sentence. Check 5 rendered examples.

Output format

name | company | first line | grade | source link | bridge used

Plus counts per grade and the leads where research found nothing.

What good looks like

  • Every A and B line has a source link a reviewer can click.
  • Lines vary in structure; 200 lines starting "I saw that..." read as automation.
  • The common mistake is personalising on trivia (school, hometown, a vacation photo) that has nothing to do with the email.

Rules

  • MUST attach a source to every A and B line.
  • MUST use a fallback line rather than invent a detail.
  • NEVER mention personal life, family, health or appearance.
  • NEVER claim to have read, watched or listened to something you did not.
  • NEVER reference profile views, website visits or other tracking.

Example prompts

  • "Write personalised first lines for these 80 leads. The email is about cutting SDR ramp time."
  • "Grade the first lines in this campaign and rewrite the C and Fail ones."
  • "Give me fallback openers for Heads of Operations when there's no research."

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