agentleFS
volodymyrkhodonovychvolodymyrkhodonovych/claude-sales-skills/skills/cold-outreach-email/SKILL.md

cold-outreach-email

Skill1 starsChanged 10 days agoMITView on GitHub

Drafts a short first-touch email to a B2B prospect who has never heard from the sender, grounded in a real, checkable trigger. Use whenever the user names a target company or contact and asks for an intro, outreach, prospecting or cold email, or for help with first-touch messaging, even if they don't say "cold".

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:

    If any of these are still placeholders, ask for them once before drafting.

    line 22
  2. Distinctive:

    Ask only for what is missing:

    line 25
  3. Distinctive:

    Search the web for the company and contact.

    line 31
  4. Distinctive:

    If none exists, say so and write a relevance-based email built on their role or industry problem.

    line 32
  5. Distinctive:

    Check against the rules, then deliver with flags: the trigger and its source, assumptions, and anything the sender must verify.

    line 35
  6. Distinctive:

    Ask: one interest question ("Is this on your radar?").

    line 43
  7. Distinctive:

    Only verifiable facts: Never invent numbers, clients, mutual connections or results.

    line 48

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Cold outreach email

A cold email earns a reply by being relevant and easy to answer. Relevance comes from a real, recent reason to write; ease comes from a short email with one low-friction question.

Setup (fill in once)

  • SENDER_NAME: {{your first name}}
  • COMPANY_NAME: {{your company}}
  • WHAT_WE_DO: {{one plain sentence, no buzzwords}}
  • PROOF_POINT: {{one real, verifiable result or client you may cite, or "none"}}
  • SIGNATURE: does the email client add it automatically? {{yes/no}}
  • LANGUAGE: {{language for external emails}}

If any of these are still placeholders, ask for them once before drafting.

Inputs

Ask only for what is missing:

  • Prospect first name, role, company, country
  • A real, recent, checkable trigger (news, hire, launch, job post, event, public statement)
  • The one problem of theirs we can plausibly help with

Steps

  1. Search the web for the company and contact. Find one real, recent trigger and note its source.
  2. If none exists, say so and write a relevance-based email built on their role or industry problem. A made-up trigger gets spotted quickly and burns the sender's credibility.
  3. Pick one problem and one angle. Extra angles dilute the question.
  4. Draft one email in LANGUAGE, adjusting tone to the prospect's country.
  5. Check against the rules, then deliver with flags: the trigger and its source, assumptions, and anything the sender must verify.

Format

  • Subject: 2–5 words, specific, no hype. Avoid "Quick question" and "Partnership", which read as templates.
  • Greeting: "Hi [First name],"
  • Line 1: the real trigger or observation about them, without flattery.
  • Line 2: the problem it usually creates, plus one concrete sentence on how we help (WHAT_WE_DO).
  • Line 3 (optional): PROOF_POINT, only if real.
  • Ask: one interest question ("Is this on your radar?"). Leave out the calendar link in a first touch, because it asks for time before any interest exists.
  • Stay under about 90 words, in short sentences.

Rules, and why

  • One variant only.
  • Only verifiable facts. Never invent numbers, clients, mutual connections or results; they are easy to check and fatal when wrong.
  • No ROI claims, hype words or "I hope this finds you well". They mark the email as a template.
  • No pricing, attachments or budget questions. Those come after interest is confirmed.
  • Don't pretend a relationship exists or fake "Re:" or "Fwd:" subjects. Deceptive subjects damage trust and may break the law in some countries.
  • Unsolicited-email rules differ by country (for example GDPR / ePrivacy in the EU, prior-consent requirements in some states, CAN-SPAM in the US). This skill does not verify legality: the sender must check the rules for the recipient's country and include an easy opt-out.
  • If the prospect looks like a private individual rather than a business contact, stop and ask the user.

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.