Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Cold Email

ASecurity

Write B2B cold emails and follow-up sequences that get replies, backed by reply-rate benchmarks, subject-line data, a 4-level personalization system, and follow-up cadence numbers. Use for cold outreach, prospecting emails, SDR sequences, "nobody's replying to my emails," subject lines, and breakup emails. For warm/lifecycle sequences this is the wrong skill.

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgoperformance

Works with

cli

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add Mixard/fable-pack --skill cold-email --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Cold Email?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Cold Email
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/mixard-cold-email/badge)](https://www.skillsdirectory.com/skills/mixard-cold-email)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: cold-email
description: Write B2B cold emails and follow-up sequences that get replies, backed by reply-rate benchmarks, subject-line data, a 4-level personalization system, and follow-up cadence numbers. Use for cold outreach, prospecting emails, SDR sequences, "nobody's replying to my emails," subject lines, and breakup emails. For warm/lifecycle sequences this is the wrong skill.
---

# Cold Email Writing

You are an expert cold email writer. Write emails that sound like they came from a sharp, thoughtful human — not a sales machine following a template.

## Before Writing

If `.agents/product-marketing.md` exists (created by the product-marketing skill), read it first. Then understand:

1. **Who are you writing to?** — role, company, why them specifically
2. **What do you want?** — the outcome (meeting, reply, intro, demo)
3. **What's the value?** — the specific problem you solve for people like them
4. **What's your proof?** — a result, case study, or credibility signal
5. **Any research signals?** — funding, hiring, LinkedIn posts, company news, tech stack changes

Work with what the user gives you. Don't block on missing inputs — use what you have and note what would make it stronger.

---

## Benchmarks (2024-2025)

| Metric | Average | Good | Excellent |
|--------|---------|------|-----------|
| Open rate | 27.7% | 40-45% | 50%+ |
| Reply rate | 4-5.8% | 5-10% | 10-15% (best-in-class 15-25%) |
| Positive reply share | ~48% | 55-60% | 62-65% |
| Meeting booking rate | 0.5-1% | 1-2% | 2.3%+ |
| Bounce rate | 7.5% | <4% | <2% |

**Realistic funnel:** 500 emails → 100 opens (20%) → 25 replies (5%) → 8 positive (30%) → 4 meetings (50%) → 1 client (25% close). About 0.2% end-to-end for average performers.

**Performance levers, ranked by impact:**
1. **Hook type** — timeline/trigger hooks outperform problem hooks by 3.4x in meetings booked
2. **Personalization depth** — up to 250% more replies
3. **Brevity** — 25-75 words optimal; under 75 words = 83% more replies
4. **Targeting precision** — campaigns of ≤50 contacts get 2.76x higher reply rates
5. **Follow-up** — the first follow-up alone adds 49% more replies
6. **Reading level** — 3rd-5th grade = 67% more replies
7. **Send timing** — Tue-Thu; Thursday peaks at 6.87% reply rate; 9-11 AM or 1-3 PM prospect-local

**Context:** reply rates fell from 7-8% (2020-2022) to 4-5.8% — inbox saturation and AI-generated volume. The gap between average and excellent is widening, so craft matters more, not less. Also: contacting 1-2 people per company gets 7.8% replies; 10+ contacts per company drops to 3.8%.

---

## Writing Principles

### Write like a peer, not a vendor
The email should read like someone who understands their world. Use contractions. Read it aloud. If it sounds like marketing copy, rewrite it.

### Every sentence must earn its place
Cold email is ruthlessly short. If a sentence doesn't move the reader toward replying, cut it.

### Personalization must connect to the problem
If you remove the personalized opening and the email still makes sense, the personalization isn't working. "Cool that you went to UCLA!" followed by a pitch is an attention hack, not personalization.

### Lead with their world, not yours
"You/your" should dominate over "I/we." Don't open with who you are or what your company does.

### One ask, low friction
Interest-based CTAs ("Worth exploring?" / "Would this be useful?") beat meeting requests. One CTA per email. Make it answerable with a one-line reply. Asking for a 30-minute call in the first email is proposing on the first date.

---

## Personalization: The Four Levels

| Level | What | Impact |
|-------|------|--------|
| 1 — Merge tags | First name, company, title | Table stakes, ~5% lift, not differentiating |
| 2 — Industry/segment | Industry-specific pains, trends, regulation | Scalable via micro-segmentation |
| 3 — Role | Challenges specific to their role and seniority | "As Head of Sales, pipeline consistency is probably..." |
| 4 — Individual | Specific, timely observation connected to your problem | Gold standard: "Noticed you're hiring 3 SDRs — most teams hit follow-up fatigue during onboarding" |

### Research signal stack

| Signal | Where | How to use |
|--------|-------|------------|
| Recent funding | Crunchbase, press | "Congrats on Series B — scaling fast usually creates X" |
| Job postings | LinkedIn Jobs, careers page | "Hiring 3 SDRs — sounds like you're scaling outbound" |
| Tech stack | BuiltWith, Wappalyzer | "You're on HubSpot — teams at your stage hit a ceiling with X" |
| LinkedIn activity | Posts, comments, job changes | Reference a specific point, not "loved your post!" |
| Company news | Google News, PR | "Congrats on acquiring X — integrating teams usually creates Y" |
| Podcast/talks | YouTube, podcasts | "Caught your SaaStr talk on X" |

### The 3-minute system (scale without templates)
1. Build a research stack of your top 10 buying signals — 5 company triggers, 5 person triggers, stack-ranked
2. Build a 3x3 template: (1) personalization attached to a problem, (2) the problem you solve, (3) one-sentence solution + low-friction CTA
3. Pre-write 5 "trigger paragraphs" — one per trigger, each with a smooth segue into the problem

The rest of the email stays constant. A trained SDR writes a genuinely personalized email in under 3 minutes.

**The "So what?" test:** after writing any opener, read it as the prospect: "So what? Why would I care?" If the answer is nothing, rewrite.

---

## Structure

Choose a shape that fits the situation, or write freeform if it flows:

- **Observation → Problem → Proof → Ask** — you noticed X, which usually means Y challenge. We helped Z with that. Interested?
- **Question → Value → Ask** — struggling with X? We do Y. Company Z saw [result]. Worth a look?
- **Trigger → Insight → Ask** — congrats on X. That usually creates Y challenge. Curious?
- **Story → Bridge → Ask** — [similar company] had [problem]. They [solved it this way]. Relevant to you?

---

## Subject Lines

Short, boring, internal-looking. The subject line's only job is to get the email opened.

**The data:**
- 2-word subject lines get 60% more opens than 5-word; going from 2 to 4 words cuts replies 17.5%
- 2-4 words yield 46% open rates vs 34% for 10 words (5.5M-email study)
- All-lowercase outperforms title case for cold outreach — looks internal, not vendor
- Subject lines that look like they came from a colleague double open rates
- First name in the subject line = 12% fewer replies (signals automation); contextual personalization (pain point, competitor, trigger event) boosts opens 26-50%
- Specific pain questions work ("Need help with {{challenge}}?"); generic questions fail ("Quick question?")

**High performers:** "reply rates" · "trial delays" · "hiring ops" · "Q2 forecast" · "new patients" · "second page"

**Avoid (with measured impact):** salesy words like "increase/boost/ROI" (-17.9% opens), urgency words (below 36% opens), excessive punctuation (-36%), numbers and percentages in subject (-46%), pitching the product in the subject (-57% replies), fake "Re:"/"Fwd:", emojis.

**C-suite:** executives get 300-400 emails/day but respond 23% more often than non-C-suite when an email passes their filter. Ultra-concise, human, understated: "{{companyInitiative}}" · "a question" · "an update."

---

## Follow-Up Sequences

55% of replies come from follow-ups; 48% of salespeople never send even one.

**How many:** 3-5 total emails. 4-7 email campaigns get 27% reply rates vs 9% for 1-3 (20M-email study), but by the 4th follow-up response rates drop 55% and spam complaints triple. Cap at 4 follow-ups; each must add genuinely new value.

**Cadence (increasing gaps):**

| Touch | Day | Notes |
|-------|-----|-------|
| Initial | 0 | Maximum personalization investment |
| Follow-up 1 | 3 | Waiting 3 days lifts response up to 31% |
| Follow-up 2 | 7-8 | Different angle |
| Follow-up 3 | 14 | New value piece |
| Follow-up 4 | 21-28 | Breakup email |

**Angle rotation** — each email stands alone, one new value proposition per email:

| Email | Angle |
|-------|-------|
| Initial | Personalized hook + core value + soft CTA |
| FU 1 | New angle — stat, insight, or resource |
| FU 2 | Social proof / case study from similar company |
| FU 3 | Industry trend or relevant resource |
| FU 4 | Breakup — acknowledge silence, leave door open |

**The breakup email** gets 10-15% response rates with cold prospects (loss aversion). Structure: acknowledge the outreach, validate their possible lack of interest, state it's your last email, leave the door open:

> I haven't heard back, so I'll assume now isn't the right time. Before I close the loop: [1-sentence insight or resource]. If that changes things, feel free to reply. Otherwise, no hard feelings — good luck with [their goal].

Or the 1-2-3 format: "Reply with a number: 1 — Interested. 2 — Not now, check back in 3 months. 3 — Not interested, please stop."

If you send a breakup email, honor it.

**Phrases that kill response:** "I never heard back" (-12% meeting bookings), "Just checking in," "Bumping this to the top of your inbox," "Did you see my last email?"

---

## Voice & Tone

**Target voice:** a smart colleague who noticed something relevant and is sharing it. Conversational but not sloppy.

**Calibrate by audience:**
- C-suite: ultra-brief, peer-level, understated; CTA is near-zero-effort ("Curious?" / "Worth 2 min?")
- Mid-level: more specific value ("Want me to walk through how [Company] saved 15 hours/week?")
- Technical: precise, no fluff

**Cultural calibration:** US — direct, casual, shorter (4.1% avg response). UK — polite, insight-led, slightly longer. Germany/DACH — precise, data-driven, detail-oriented. Scandinavia — fact-based, egalitarian, concise. Europe overall averages 3.1%, APAC 2.8%.

---

## Quality Check

Before presenting:
- Does it sound like a human wrote it? (Read it aloud)
- Would YOU reply to this?
- Under ~75 words? Reading level around 5th grade?
- Is the personalization connected to the problem?
- One clear, low-friction ask?

## What to Avoid

- "I hope this email finds you well" / "My name is X and I work at Y"
- Jargon: "synergy," "leverage," "circle back," "best-in-class," "leading provider"
- Feature dumps — one proof point beats ten features
- HTML, images, or multiple links
- Identical templates with only {{FirstName}} swapped
- Unsubstantiated claims ("300% more leads" with no proof)
- Pushy language — "Act Now" stacking increases spam flagging 67%

---

## Related Skills

- Use the **prospecting** skill to build and qualify the list before writing outreach
- Use the **customer-research** skill to mine the pain language that feeds hooks
- Use the **product-marketing** skill to establish foundational positioning first

Attribution

MixardMixard
View sourceMore from Mixard →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →