# Cold email skill Human Guide

## What This Is For
Write a cold sales/B2B outreach email that earns a reply. It gives the agent a clearer input/output frame for email marketing: what context to ask for, what decisions to make, and what usable artifact to return.

Use this as a human-readable version of the Cold email skill agent skill. It is meant for marketers, operators, founders, and other non-coders who want the workflow without reading agent-specific implementation instructions.

## When To Use This
- Use this when you need a repeatable process for cold email skill.
- Use this when the task needs judgment, examples, constraints, or a clear output format rather than a one-off prompt.
- Use this when you want to hand an AI assistant enough context to produce a usable marketing artifact.

## When Not To Use This
- Do not use this when you only need a quick factual answer.
- Do not use this when the work depends on private data you cannot share with the assistant.
- Do not use this as a replacement for legal, compliance, financial, or medical review.

## What You Need Before Starting
- The goal or business outcome you want.
- The audience, customer segment, or market context.
- Any source material the assistant should respect, such as notes, briefs, examples, URLs, or brand guidance.
- Constraints such as tone, length, channel, deadline, region, or approval requirements.
- A clear definition of what a good final answer should look like.

## Step-By-Step Workflow
1. State the job clearly: "Use the Cold email skill guide to help me with..."
2. Add context: audience, goal, offer, channel, source material, and constraints.
3. Ask the assistant to identify missing inputs before producing the final output.
4. Have the assistant follow the skill-specific guidance below.
5. Review the result against the final checklist and ask for revisions where needed.

## Skill-Specific Guidance
- **Who you're emailing** — role, company, and the segment/ICP.
- **The relevance hook** — a real reason to contact *them now* (a trigger event, a specific pain in their role/industry, a mutual connection).
- **What you offer** — the outcome you drive for people like them (not your feature list).
- **Proof** — a comparable customer, a result, a number.
- **The ask** — ideally low-friction (a 15-min call, a relevant resource, an "open to it?" reply).
- **Opener** — the relevance hook: something true about *them* (trigger, pain, connection). Not "I hope this finds you well."
- **Value** — the outcome you drive for people in their seat, with one proof point. One or two sentences.
- **Ask** — one clear, low-friction request, phrased to make "yes" or even "not now" easy.
- [`references/reply-rate-calibration.md`](references/reply-rate-calibration.md) — line-by-line calibration of what actually moves reply rates, with honest expectations
- [ ] Under ~120 words and skimmable on a phone
- [ ] Opens with a real, specific relevance hook about the recipient
- [ ] Frames value as the prospect's outcome, with one proof point

## Decision Points And Nuance
The original skill emphasizes: Required Inputs, Output Format, Cold Email: [offer] → [persona], Deeper Materials, Quality Checks, Anti-Patterns, Based On, Supporting file: references/reply-rate-calibration.md, The hierarchy of what matters (most → least), Line-by-line judgments.

Use these questions to steer the work:
- What is the intended audience or buyer?
- What source material must be preserved?
- What should the assistant optimize for: clarity, persuasion, accuracy, speed, creativity, or conversion?
- What examples represent the desired quality bar?
- What should the assistant avoid?

## Common Mistakes
- [ ] Do not open about yourself ("We're a leading platform…") — lead with them
- [ ] Do not feature-dump — one outcome + one proof beats a capability list
- [ ] Do not stack asks or ask for too much ("30-min demo" cold) — make the first yes tiny
- [ ] Do not use fake personalisation ("loved your post!") — be specifically, verifiably relevant or don't claim it
- [ ] Do not skip follow-ups or make them "just checking in" — each must add a reason to reply
- **Opener:** never "I hope this finds you well" (reads as merge-field), never your company's founding story. The observation goes first.
- [ ] Do not write a long message — every extra sentence lowers the reply rate
- [ ] Do not make it about you — lead with why *them*, then a tight credibility line

## Copy-And-Paste Prompt
```text
Use the Cold email skill human guide.

My goal:
[Describe the business outcome]

Audience:
[Describe who this is for]

Context and source material:
[Paste notes, examples, links, or existing copy]

Constraints:
[Tone, length, channel, timeline, must-include items, must-avoid items]

Before producing the final output, ask me for any missing information that would materially improve the result.
```

## Final Checklist
- [ ] The output matches the original goal.
- [ ] The audience and context are reflected in the answer.
- [ ] Important constraints and source material were preserved.
- [ ] The assistant made the relevant decisions explicit.
- [ ] The final artifact is ready to use, review, or hand to the next person.

## Source
This guide was generated from the mohitagw15856/pm-claude-skills skill entry for `cold-email`.

## Source Skill Notes
These notes preserve the nuance from the original skill. Use them as supporting reference when the workflow above feels too generic.

# Cold Email Skill

Cold email works when it's short, clearly about *them*, and asks for one small thing. Most cold email
fails because it's a feature dump that's all about the sender. This skill writes a tight, personalised
email built on a real trigger or relevance hook, with a single low-friction ask — plus the follow-ups
that actually drive most replies. (For job-search / networking outreach, use [`outreach-message`](../outreach-message/SKILL.md); this is B2B sales prospecting.)

## Required Inputs

Ask for these only if they aren't already provided:

- **Who you're emailing** — role, company, and the segment/ICP.
- **The relevance hook** — a real reason to contact *them now* (a trigger event, a specific pain in their role/industry, a mutual connection).
- **What you offer** — the outcome you drive for people like them (not your feature list).
- **Proof** — a comparable customer, a result, a number.
- **The ask** — ideally low-friction (a 15-min call, a relevant resource, an "open to it?" reply).

## Output Format

### Cold Email: [offer] → [persona]

**Subject lines** — 3 options, short (≤6 words), specific, no clickbait or "Quick question."

**The email** (≤120 words):
- **Opener** — the relevance hook: something true about *them* (trigger, pain, connection). Not "I hope this finds you well."
- **Value** — the outcome you drive for people in their seat, with one proof point. One or two sentences.
- **Ask** — one clear, low-friction request, phrased to make "yes" or even "not now" easy.
- **Signature** — minimal.

**Follow-ups** — 2 short ones (send ~3–4 days apart): a value-add nudge (a resource/insight, not "just bumping this") and a graceful breakup email ("I'll close the loop — want me to circle back next quarter?"). Most replies come from these.

**Note** — what to personalise per prospect (the one line that proves it isn't a blast), and the one metric to watch (reply rate, not open rate).

## Deeper Materials

- [`references/reply-rate-calibration.md`](references/reply-rate-calibration.md) — line-by-line calibration of what actually moves reply rates, with honest expectations

## Quality Checks

- [ ] Under ~120 words and skimmable on a phone
- [ ] Opens with a real, specific relevance hook about the recipient
- [ ] Frames value as the prospect's outcome, with one proof point
- [ ] Exactly one low-friction ask
- [ ] Includes 2 follow-ups (value-add + graceful breakup)
- [ ] Subject is specific and honest (no bait)

## Anti-Patterns

- [ ] Do not open about yourself ("We're a leading platform…") — lead with them
- [ ] Do not feature-dump — one outcome + one proof beats a capability list
- [ ] Do not stack asks or ask for too much ("30-min demo" cold) — make the first yes tiny
- [ ] Do not use fake personalisation ("loved your post!") — be specifically, verifiably relevant or don't claim it
- [ ] Do not skip follow-ups or make them "just checking in" — each must add a reason to reply

## Based On

B2B cold-email practice — relevance/trigger-led openers, one-outcome value, single low-friction ask, value-adding follow-up cadence.

---

## Supporting file: references/reply-rate-calibration.md

# Reply-Rate Calibration — what actually moves cold email, line by line

Field-calibrated guidance for judging a draft. Rates are directional (B2B, decision-maker targets); the *ordering* of what matters is the durable part.

## The hierarchy of what matters (most → least)
1. **Who it's from and to** — right person ≈ 10× the best copy edit. A mediocre email to the right owner beats a brilliant one to the wrong department.
2. **The first line in the preview pane** — it's the real subject line. If it could open an email to anyone, it opens replies from no one.
3. **The specific observation** — one verifiable fact about *them* (their pricing page, their job post, their outage last Tuesday). This is the line that proves a human looked.
4. **The size of the ask** — replies scale inversely with commitment. "Worth a look?" out-pulls "Can we book 30 minutes?" roughly 2-3×.
5. Subject line cleverness — last, despite the folklore.

## Line-by-line judgments
- **Subject:** 2-5 words, lowercase-adjacent, zero adjectives. Internal-forward energy ("data pipeline question") beats marketing energy ("Transform your data stack!") every measured time.
- **Opener:** never "I hope this finds you well" (reads as merge-field), never your company's founding story. The observation goes first.
- **The bridge:** one sentence connecting their situation to why you exist. If it needs two sentences, the targeting is wrong.
- **Proof:** one number with a name attached ("cut Meridian's close time 40%") — unnamed numbers read as invented.
- **Ask:** one question, answerable with one word. Two asks = zero answers.
- **Length:** 50-100 words. Above 120, reply rates fall off a cliff — it signals the sender's time matters more than the reader's.