cold-email-personalization — Claude Code skill: cold email writing
cold-email-personalization turns a prospect brief into a cold email and a follow-up series: research first, a 60-120 word draft, then a scored QA pass.
Apache-2.0 ★ 450 updated 2026-04-03
npx skills add gtmagents/gtm-agents --skill cold-email-personalization -a claude-codeWhat cold-email-personalization does
The skill walks a fixed six-step workflow. You begin with an ICP map: the persona, the three objections that come up most, and the next step you want. Then it hunts for recent signals on each prospect, no older than 90 days, following assets/research-playbook.md.
A campaign path comes next: custom signal, creative idea, whole offer or fallback, as laid out in assets/campaign-types.md. The draft follows assets/email-structure.md: plain text, 60-120 words, one CTA. Merge fields come from assets/variable-schema.md, and the last pass runs the assets/qa-checklist.md checks plus a score from assets/scoring-rubric.md.
The gates are strict. Two verified signals per prospect, a score of at least 80, and a 3:1 recipient-to-sender ratio; fall short on any of them and the draft stops there. Made-up details are ruled out as well, so personalization has to rest on research you actually did. Follow-ups live in assets/follow-up-strategy.md, and every touch swaps the value prop.
What it helps with
- draft a first email around a real prospect signal
- build a follow-up series that changes its argument each touch
- run a draft through the checklist before it goes out
- get a quality score and see what to fix
- map the objections a persona will raise
Example prompts for the agent
- Write a cold email to the VP of Sales at
{{company}}, the signal is their new sales hire last week - Add a follow-up sequence to that email and swap the value prop on each touch
- Run the draft through the QA checklist and tell me the score
How to install cold-email-personalization
1Skills CLI (Vercel)
npx skills add gtmagents/gtm-agents --skill cold-email-personalization -a claude-code2Manually: put the files in place
~/.claude/skills/cold-email-personalization/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/cold-email-personalization/
1Skills CLI (Vercel)
npx skills add gtmagents/gtm-agents --skill cold-email-personalization -a codex2Manually: put the files in place
.agents/skills/cold-email-personalization/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add gtmagents/gtm-agents --skill cold-email-personalization -a cursor2Manually: put the files in place
.cursor/skills/cold-email-personalization/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install gtmagents/gtm-agents plugins/copywriting/skills/cold-email-personalization2Manually: put the files in place
.github/skills/cold-email-personalization/SKILL.md1Skills CLI (Vercel)
npx skills add gtmagents/gtm-agents --skill cold-email-personalization -a gemini-cli2Platform CLI
gemini skills install https://github.com/gtmagents/gtm-agents --path plugins/copywriting/skills/cold-email-personalizationManually: put the files in place
.devin/skills/cold-email-personalization/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about cold-email-personalization
How do I install cold-email-personalization in Claude Code?
Run npx skills add gtmagents/gtm-agents --skill cold-email-personalization -a claude-code; the skill file then sits at ~/.claude/skills/cold-email-personalization/SKILL.md.
What does cold-email-personalization do?
It takes an email from ICP mapping through signal research, campaign choice, drafting, QA scoring and follow-up building. The output is plain text of 60-120 words with a single CTA.
What has to be true before a draft passes?
Two verified signals per prospect from the last 90 days, a score of at least 80, and a 3:1 recipient-to-sender ratio.
Source text
SKILL.md · Apache-2.0
---
name: cold-email-personalization
description: >-
Writes personalized cold emails by researching prospects, crafting attention-grabbing
openers, and scoring drafts against a quality rubric. Use when the user asks to write
cold emails, outreach emails, sales prospecting messages, outbound email campaigns, or
B2B email sequences.
---
# Cold Email Personalization
## When to Use
- Writing cold outreach, sales prospecting, or outbound B2B emails
- Personalizing email openers from prospect research signals
- Building multi-touch follow-up sequences
- Reviewing or scoring email drafts before sending
## Workflow
1. **Map the ICP** — Complete [ICP & Objection Mapping](assets/icp-objection-mapping.md). Gate: persona, top 3 objections, and desired next step are defined.
2. **Research signals** — Follow the [Research Playbook](assets/research-playbook.md) to find custom signals from the last 90 days. Gate: at least 2 verified signals per prospect.
3. **Choose campaign path** — Pick Custom Signal, Creative Idea, Whole Offer, or Fallback from [Campaign Types](assets/campaign-types.md).
4. **Draft the email** — Apply [Email Structure](assets/email-structure.md) rules: plain text, 60-120 words, one CTA. Use [Variable Schema](assets/variable-schema.md) for merge fields.
5. **QA and score** — Run the [QA Checklist](assets/qa-checklist.md), then score with the [Scoring Rubric](assets/scoring-rubric.md). Gate: score >= 80 and 3:1 recipient-to-sender ratio.
6. **Build sequence** — Add follow-ups per [Follow-Up Strategy](assets/follow-up-strategy.md), rotating value props each touch.
## Principles
- **Message-market fit over cleverness** — Show you understand the prospect's situation immediately.
- **Research is the personalization** — Custom signals prove homework; never fabricate facts.
- **One job per email** — Single sharp question or CTA; earn a reply, not a meeting.
- **Two personalization paths** — Path A: custom signal research. Path B: whole-offer strategy. See [Creative Ideas](assets/creative-ideas.md) for Path B tactics.
## Example
**Signal found**: Prospect's company posted a VP Sales hire on LinkedIn 2 weeks ago.
**Subject**: {{first_name}}, growing the sales team?
**Body**: Hi {{first_name}}, saw {{company}} just brought on a new VP Sales — congrats. Specifically, it looks like you're scaling outbound to {{customer_type}}. We helped [similar company] ramp 3 new reps to quota 40% faster by templatizing their top performer's research workflow. Worth a 15-min look?
**Why it works**: Uses a verified, recent signal in the first line; ties it to a specific, relevant outcome; single clear CTA.
## References
- [Research Playbook](assets/research-playbook.md) — Finding custom signals
- [Variable Schema](assets/variable-schema.md) — Standard merge variables
- [Email Structure](assets/email-structure.md) — Subject lines, body, punchiness
- [Campaign Types](assets/campaign-types.md) — Four campaign patterns
- [Creative Ideas](assets/creative-ideas.md) — Generating credible prospect ideas
- [Follow-Up Strategy](assets/follow-up-strategy.md) — Sequence logic and value rotation
- [ICP & Objection Mapping](assets/icp-objection-mapping.md) — Persona and objection prep
- [QA Checklist](assets/qa-checklist.md) — Pre-send verification
- [Scoring Rubric](assets/scoring-rubric.md) — 0-100 quality score
- [Examples](assets/examples.md) — Full campaign examples
© gtmagents · Apache-2.0 · gtmagents/gtm-agents