agentleFS
alebgl77alebgl77/claude-inc/skills/draft-outreach/SKILL.md

draft-outreach

Skill21 starsChanged 4 months agoMITView on GitHub

Writes personalised cold outreach — first-touch email or DM plus a 3-step follow-up sequence — grounded in real research, with subject-line variants. Use when the user says "write a cold email", "reach out to this prospect", "draft outreach to X", or after account-research produces a PURSUE verdict.

11 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

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 1

    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:

    Compliance pass: no false claims, honour opt-outs, one-click identifiable sender.

    line 26

“Common” is measured: kept by at least 6 in 10 of the 7 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

Draft Outreach — Cold Emailer

"Earn the reply, don't trick it."

When to use

  • "Write a cold email to {prospect}"
  • "Draft outreach for this account"
  • "Follow up, they never answered"
  • Right after account-research — never write outreach to a stranger you haven't researched
  • LinkedIn DMs, X DMs and short-form intros included

Workflow

  1. Load the account brief (or run a quick research pass if none exists — no brief, no outreach).
  2. Pick the angle: one observed signal → one pain → one credible promise. One. Multi-pain emails read like spam.
  3. Draft the first touch: ≤ 90 words. Line 1 proves you did homework (specific, non-creepy). Line 2-3 connect pain → outcome with proof. Close with a low-friction CTA (question or 15-min ask), never "let me know your availability for a quick sync".
  4. Write 3 subject lines: 2-4 words, lowercase-friendly, zero clickbait. No "Re:", no fake forwards, ever.
  5. Build the follow-up ladder: +3 days (new value: insight/resource), +7 days (different angle or social proof), +14 days (graceful breakup that leaves the door open). Each ≤ 60 words, none saying "just bumping this".
  6. Personal-ify: adapt to the user's voice profile if one exists (voice-builder output); default to plain, human, contraction-friendly prose.
  7. Compliance pass: no false claims, honour opt-outs, one-click identifiable sender. Flag anything Legal should see.

Output format

## Outreach kit — {prospect}
Angle: {signal} → {pain} → {promise}

**Subject options**: 1. ... 2. ... 3. ...
**Email 1 (day 0, ≤90w)**: ...
**Email 2 (day 3, ≤60w)**: ...
**Email 3 (day 7, ≤60w)**: ...
**Email 4 (day 14, breakup)**: ...
**DM variant (≤300 chars)**: ...
Send window: {day/time + rationale}

Quality bar

  • First line is specific to THIS prospect (passes the "could this be sent to anyone else?" test — answer must be no)
  • ≤ 90 words for touch 1; zero jargon; reads aloud naturally
  • Exactly one CTA per message
  • No deceptive subjects, no fake familiarity, no guilt-tripping follow-ups
  • Sequence provides new value at every touch

Example

Ask: "Cold email to the CTO of a startup that just migrated to PrestaShop 9, I sell SEO rescue." Produced: subject "category pages 404" · touch 1 citing two live broken URLs, one promise (recover pre-migration rankings in 30 days), CTA "worth 15 minutes?", plus 3 follow-ups ending in a clean breakup.

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.