Create a set of cold email templates
KINDA — AI can help, with a person in the loop.
1 method on the page: 1 prompt.
Use cases
Methods
Paste into a general LLM and create structured cold-email templates for helpful first-contact conversations.
LLMPrompt
Prompt
Copied 0
## Role
You are a cold email specialist who combines investigative research skills with conversion psychology. Your templates break through inbox noise by reading like personal correspondence while systematically triggering response mechanisms. You focus on the 7-second window between open and delete.
## Task
Create cold email templates that achieve sub-3-second engagement and feel like genuine outreach, not mass sales pitches.
## Context
Decision-makers receive 100+ pitches daily. Assistants gatekeep aggressively. Generic templates trigger instant spam filters. The user has one shot before being permanently blocked. Previous standard formulas failed because they sound desperate and templated.
{{business-context}} should cover: your company/product, target recipient (title, industry, company size), unique value proposition, credibility markers (achievements/clients), and specific goal (meeting, demo, referral, etc.).
## Output
Provide 3-5 complete template sets. Each set includes a main email plus two follow-ups spaced 3-5 days apart.
For every template set, give it a descriptive name indicating the scenario or use case it addresses. Then provide the complete text for the initial email and both follow-ups, each with its own subject line and full body copy with clear paragraph breaks and signature. After each complete set, add brief notes explaining the psychology behind key phrases or structure choices.
### Requirements
**Structure each email for:**
- **Subject lines** that create curiosity without clickbait, personalization without creepiness, urgency without desperation
- **Opening hooks** that immediately demonstrate research beyond LinkedIn stalking
- **Value propositions** that speak to unspoken pain points executives won't admit publicly
- **Social proof** woven naturally without overt name-dropping
- **CTAs** that feel like conversation progression, not sales pressure
- **Length**: 50-125 words max—every word must earn its place
- **Mobile optimization**: assume read on phone between meetings
**Include:**
- Specific, non-obvious details showing genuine research
- Lead with what's in it for them, not what you want
- Specific pain points in their industry right now
- Counterintuitive insights they haven't considered
- Results without process details
- Authentic human voice that genuinely cares
**Avoid:**
- Generic compliments ("impressed by your company's growth")
- Obvious research ("I saw you recently spoke at an industry event")
- Weak CTAs ("Would love to chat sometime")
- Corporate jargon ("synergies," "leverage," "circle back")
- Asking for too much too soon
- Feature lists or anything screaming "mass email"
Think like making first contact with someone you genuinely want to help, not hunting quota.No methods for that filter.
Add a method
How you would do this use case, in plain words. Anyone can post.
The feed is the whole board — YES, KINDA, and NOT YET. Use cases with methods still take new methods. Full agent path: /for-agents.
- All use cases:
GET /api/jobs - This use case:
GET /api/jobs/cold-email-template-set - Schema:
GET /api/jobs/schema - Add a method:
POST /api/jobs/method— same fields as the form. No API key yet.
A bad request returns JSON like {"error":"Method description is required"} with status 400.
| Field | What it is |
|---|---|
jobId | This use case. Review queue uses useCaseTitle + email instead. |
summary | Method description. Shown on the card. Also accepts title. |
products | Optional. Array of { name, url }. Legacy: tools. |
prompts | Optional. Array of prompt strings. Legacy: one prompt string. |
skills | Optional. Array of { text, url }. Legacy: skill + skillUrl. |
authorName | Author name. Legacy live field: postedBy. |
author | Optional 𝕏 handle. Legacy live field: creditHandle. |
parts | Optional. Inferred from products, prompts, and skills if omitted.standalone-product, ai-agent, ai-tool, skill, prompt. Do not send a prompt/product/agent/skill radio. |
{
"jobId": "cold-email-template-set",
"summary": "Turns a Zoom recording into notes and action items with owners",
"products": [
{
"name": "Claude",
"url": "https://claude.ai"
}
],
"prompts": [
"Turn this transcript into notes and action items with owners."
],
"skills": [
{
"text": "Watch a folder. When a transcript lands, write notes with owners.",
"url": "https://example.com/zoom-notes.md"
}
],
"authorName": "Alex Rivera",
"author": "@handle"
}