cold-intro-structure
Skill0 starsChanged 4 months agoMITView on GitHub
Open a cold email on the prospect's pain, show the one thing that's different about you, then make a single small ask. First-touch outreach to someone who doesn't know the owner. Not for warm leads or existing customers — those get a different open.
In this repository29 other files it gives its agents.
- devils-advocate-first-passSkill
- load-bearing-assumptionSkill
- pre-mortemSkill
- reversibility-checkSkill
- three-option-framingSkill
- boundary-setting-declineSkill
- customer-reply-tone-matchSkill
- quote-follow-upSkill
- subject-line-not-filteredSkill
- end-of-day-reflectionSkill
- inbox-triageSkill
- project-scaffoldingSkill
- quote-drafting-from-notesSkill
- vendor-invoice-categorizationSkill
- competitor-pricing-extractSkill
- customer-voice-extractSkill
- source-verificationSkill
- tactic-extractionSkill
- vertical-landscape-scanSkill
- discovery-call-note-captureSkill
- lead-qualificationSkill
- objection-handlingSkill
- proposal-drafting-frameworkSkill
- stack-the-deck-closeSkill
- dont-be-a-chatbotSkill
- honest-hedgingSkill
- lead-with-the-actionSkill
- specific-over-genericSkill
- write-like-the-userSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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
- Distinctive: line 24
Keep it under 120 words. A cold email that needs scrolling gets archived.
≈ “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.
Files
Cold Intro That Gets a Reply
A cold email earns a reply by being about them, not you. Lead with the pain they actually feel, name the one way you're different, and ask for something small enough to say yes to.
The technique
- Open on their pain in one concrete sentence — the specific problem someone in their seat lives with, not a generic compliment.
- Skip the company autobiography. They don't care what year you were founded.
- Name one differentiator, plainly. The single thing you do that the alternative doesn't. One, not five.
- Make the ask small: a 10-minute call, a yes/no question, a look at one example. Not "let's set up a meeting to explore synergies."
- Keep it under 120 words. A cold email that needs scrolling gets archived.
Do this, not that
Do: "Most roofers in town quote off a ladder and a guess. We measure off satellite and hand you the supplement language carriers actually approve. Worth a 10-minute look at one of your open claims?"
Don't: "We are a full-service, industry-leading provider of innovative roofing solutions committed to excellence. We'd love to schedule a meeting to explore how we can leverage our expertise to add value to your organization."
Why this works
A stranger gives you one sentence before they decide to keep reading or hit delete. Spend it on their problem and they lean in; spend it on your mission statement and they're gone. The small ask works because a busy person will trade ten minutes long before they'll commit to a relationship.
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
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.

