agentleFS
holaroluwaholaroluwa/outbound-skills/skills/cold-call-script/SKILL.md

cold-call-script

Skill0 starsChanged 44 days agoMITView on GitHub

Write a full cold-call script, opening, permission ask, pain question, value bridge, and three objection handlers, from a target title and company type. Use when the user wants a "cold call script", "phone script", "what do I say when they pick up", or is prepping to dial. Reads persona, pains, value props, and competitors from outreach-brief.md. Built to sound like a confident human on the phone, not a telemarketer reading a card.

4 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

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 2

    Distinctive

    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:

    Write the script in these beats:

    line 15
  2. Distinctive:

    No scripted-robot phrases.

    line 25

“Common” is measured: kept by at least 6 in 10 of the 4 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 Call Script

A good cold call earns the next 30 seconds, then the next. This script is built in beats you can actually say out loud, with room to listen.

Input needed

  • Target title and company type.
  • Persona, top pains, value props, and competitor handling from outreach-brief.md if present.

Method

Write the script in these beats:

  1. Opening, an honest pattern-interrupt. Name who you are and that it's a cold call, like a human.
  2. Permission, ask for 30 seconds. Earning permission beats steamrolling.
  3. Pain question, a sharp question tied to pain #1 that gets them talking, in their language.
  4. Value bridge, one or two lines connecting their answer to your offer. Short.
  5. CTA, a small next step (a 15-minute look, not a signature).
  6. Three objection handlers, for the likely pushbacks ("we already use X", "no budget", "send me an email"). Calm, short, re-open the conversation.

Voice rules

  • Conversational and spoken, not written-and-read. Contractions, short lines.
  • No scripted-robot phrases. Leave explicit "[pause / listen]" cues so it stays a conversation.

Output

The full script in labelled beats, plus the three objection handlers, each with the likely objection and the response underneath.

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.