Agent skill

Cold Email

by borghei in borghei/Claude-Skills

Write and optimize B2B cold email outreach sequences that get replies, covering personalization, follow-up cadence, deliverability, and compliance.

MITAuto-check passedSales & Support

Install Cold Email

skills CLI
$ npx skills add borghei/Claude-Skills --skill cold-email -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install borghei/Claude-Skills cold-email --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/borghei/Claude-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/marketing/cold-email .claude/skills/cold-email && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
cold-email
GitHub stars
881
Token cost
~5.7k tokens
SKILL.md length
2,809 words
Files
4 (incl. scripts)
Skills in repo
349
Repo updated
First seen
Licence
MIT

At a glance

Write and optimize B2B cold email outreach sequences that get replies, covering personalization, follow-up cadence, deliverability, and compliance.

  • Works in 8 steps: Write Like a Peer, Not a Vendor → Every Sentence Earns Its Place → Personalization Must Connect to the… → …
  • Writing cold outreach
  • SKILL.md covers Table of Contents, Keywords, Clarify First and Quick Start, plus 7 more sections
  • Runs Python scripts from its folder; calls python

What it does

Cold Email is an agent skill from borghei/Claude-Skills. Write and optimize B2B cold email outreach sequences that get replies, covering personalization, follow-up cadence, deliverability, and compliance. Use when writing cold outreach, prospecting/SDR emails, or building outbound sequences.

Its SKILL.md is about 5.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `scripts/deliverability_checker.py`, `scripts/sequence_optimizer.py` and `scripts/subject_line_scorer.py`).

It sits in Sales & Support, covering Cold outreach. The repository describes itself as: 385 AI skills, 77 expert agents, and 900 stdlib Python tools for every team: engineering, PM, marketing, C-level, compliance, business ops, research, and a LinkedIn toolkit… The licence is MIT.

When your agent uses it

  • Writing cold outreach
  • Prospecting/SDR emails
  • Building outbound sequences

Example prompts

  • “/cold-email”

Requirements

  • Python 3

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. Write Like a Peer, Not a Vendor
  2. Every Sentence Earns Its Place
  3. Personalization Must Connect to the Problem
  4. Lead with Their World, Not Yours
  5. One Ask Per Email
  6. Subject Line Scorer (scripts/subject_line_scorer.py)
  7. Deliverability Checker (scripts/deliverability_checker.py)
  8. Sequence Optimizer (scripts/sequence_optimizer.py)

What it can do on your machine

Read from SKILL.md and the folder at commit 4a698e8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 3 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Cold Email loads about 5.7k tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 2,809 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~62
When it runs · the whole SKILL.md, loaded when a task matches
~5.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from borghei/Claude-Skills at commit 4a698e8, republished under its MIT licence (© borghei). 2,809 words, ~5,711 tokens.

Download SKILL.mdSave it as .claude/skills/cold-email/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
cold-email
description
Write and optimize B2B cold email outreach sequences that get replies, covering personalization, follow-up cadence, deliverability, and compliance. Use when writing cold outreach, prospecting/SDR emails, or building outbound sequences.
license
MIT
metadata.version
1.0.0
metadata.author
borghei
metadata.category
marketing
metadata.domain
outbound
metadata.updated
2026-03-09

Cold Email Outreach

Production-grade B2B cold email that sounds like it came from a person, not a sequence tool.


Table of Contents


Keywords

cold email, cold outreach, prospecting email, SDR email, sales email, first-touch email, follow-up sequence, email prospecting, outbound email, sales development, sequence building, email personalization, email deliverability, CAN-SPAM, GDPR, B2B outreach, email compliance, subject lines, reply rates, breakup email


Clarify First

Before generating the email, confirm these inputs. If any is unknown or vague, ASK — do not assume:

  • ICP / prospect context — job title, company type/size, seniority (drives the opener, relevance, and voice calibration)
  • Specific problem + outreach trigger — the pain and why now (selects the framework and shapes the opener)
  • The one proof point — a specific number, named customer, or result (drives the credibility line)
  • The single CTA / goal — book a call, get a reply, or get a referral (drives the one ask)

Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.

Quick Start

Write a First-Touch Email
  1. Define the ICP, specific problem, and outreach trigger
  2. Select voice calibration based on recipient seniority
  3. Write opener about their world (not yours)
  4. State relevance in 1-2 sentences with specific proof
  5. Close with a single, low-friction ask
  6. Generate 3 subject line variants
  7. Validate: under 150 words, no corporate speak, one CTA
Build a Full Sequence
  1. Write the first email (above)
  2. Plan 4-5 follow-ups, each with a different angle
  3. Set escalating gap cadence (Day 1, 4, 9, 16, 25, 35)
  4. Write each follow-up as a standalone (recipient does not remember earlier emails)
  5. End with a breakup email that closes the loop professionally
  6. Validate deliverability setup before sending

Core Workflows

Workflow 1: Single First-Touch Email

Step 1: Gather Context

Required information:

  • Sender context: Role, company, what they sell, key proof points
  • Prospect context: Job title, company type/size, likely problem, trigger for outreach
  • Goal: Book a call? Get a reply? Get a referral?

Step 2: Choose Framework

FrameworkBest WhenStructure
Problem-FirstProspect has a visible pain pointProblem observation > Relevance > Ask
Trigger-BasedThere is a specific event (funding, hiring, news)Trigger reference > Connection to problem > Ask
Mutual ConnectionReferral or shared networkName drop > Context > Ask
Value-FirstYou have something genuinely useful to shareInsight/resource > Brief context > Ask
Direct AskProspect is high-intent or very seniorBrief context > Direct question

Step 3: Draft the Email

Structure:

Subject: [2-4 words, looks like an internal email]

[Opener: 1 sentence about their world — trigger, observation, or question]

[Relevance: 1-2 sentences connecting their situation to what you do]

[Proof: 1 sentence of credible evidence — specific number, named customer, result]

[Ask: 1 sentence with a single, specific, low-friction CTA]

[Sign-off]

Step 4: Validate

  • Under 150 words total
  • Opener is about them, not you
  • No sentence starts with "I" or "We"
  • One CTA, not multiple
  • CTA is a question, not a statement
  • No jargon or corporate speak
  • Would a friend send this to another friend in business?
Workflow 2: Full Sequence Build

Step 1: Write Email 1 (Using Workflow 1)

Step 2: Plan Follow-Up Angles

Each follow-up needs a distinct angle. Plan before writing:

EmailDayAngleWhat is New
1Day 1Problem-firstInitial outreach
2Day 4New evidenceCase study, data point, or recent result
3Day 9Different pain pointAlternative angle on their world
4Day 16Industry insightSomething notable about their space
5Day 25Direct questionSimple, clear ask without context
6Day 35BreakupProfessional close, referral ask

Step 3: Write Each Follow-Up

Rules for every follow-up:

  • Standalone: does not require reading previous emails
  • New angle: brings something the previous email did not
  • Shorter than Email 1 (each subsequent email gets shorter)
  • Never says "just checking in" or "circling back"
  • Never references all previous emails ("As I mentioned in my last three emails...")

Step 4: Write the Breakup Email

The breakup email closes the loop. It signals this is the last one, which paradoxically increases reply rate.

Template:

Subject: closing the loop

[Name],

Last note from me. If [specific problem] becomes a priority,
reply here and I'll pick it up.

If there's someone else at [Company] better suited for this
conversation, a name would help.

Either way — [genuine well-wish related to something specific].

[Sign-off]
Workflow 3: Performance Iteration

Step 1: Diagnose the Problem

SymptomLikely CauseFix
Low open rate (< 25%)Subject linesTest new subject line patterns
Opens but no replies (< 2% reply rate)Email bodyRewrite with stronger relevance and lower-friction CTA
Replies but wrong outcomeCTA mismatchAdjust the ask
High bounce rate (> 5%)List qualityVerify email addresses before sending
Landing in spamDeliverabilityCheck SPF/DKIM/DMARC, reduce send volume, warm domain

Step 2: Rewrite the Underperforming Element

Focus on one element at a time. Do not rewrite the entire email when only the subject line is the problem.

Step 3: Test and Measure

  • A/B test subject lines with minimum 100 sends per variant
  • Test one variable at a time
  • Wait for 3-5 days of data before drawing conclusions
  • Document every test and result for future reference

Writing Principles

1. Write Like a Peer, Not a Vendor

The moment your email sounds like marketing copy, it is deleted.

Test: Would you send this to a smart colleague at another company? If not, rewrite.

2. Every Sentence Earns Its Place

Each sentence must do one of these jobs:

  • Create curiosity
  • Establish relevance
  • Build credibility
  • Drive to the ask

If a sentence does none of these, cut it.

3. Personalization Must Connect to the Problem

Generic personalization is worse than none.

  • Bad: "I saw you went to Stanford" followed by a pitch unrelated to Stanford
  • Good: "I saw you're hiring three SDRs — usually a signal that you're scaling cold outreach. That's exactly the challenge we help with."

The personalization must bridge to the reason for reaching out.

4. Lead with Their World, Not Yours

The opener should be about their situation, problem, or context. Not about you or your product.

5. One Ask Per Email

Do not ask them to book a call, watch a demo, read a case study, AND reply with their timeline. Pick one.


Voice Calibration by Audience

AudienceLengthToneSubject StyleWhat Works
C-suite (CEO, CRO, CMO)3-4 sentencesUltra-brief, peer-level, strategicShort, vague, internal-lookingBig problem > relevant proof > one question
VP / Director5-7 sentencesDirect, metrics-consciousSlightly more specificSpecific observation + clear business angle
Manager7-10 sentencesPractical, shows homeworkCan be descriptiveSpecific problem + practical value + easy CTA
Technical (Engineer, Architect)7-10 sentencesPrecise, no fluffTechnical specificityExact problem > precise solution > low-friction ask
Founder / Solo5-7 sentencesEmpathetic, peer-to-peerCasual, humanShared experience + relevant proof + conversational ask

Rule: The higher up the org chart, the shorter your email needs to be.


Subject Line Framework

Principles

The goal of a subject line is to get the email opened. Not to convey value, not to be clever. Just opened.

The best cold email subject lines look like internal emails: short, slightly vague, enough curiosity to click.

Patterns That Work
PatternExampleWhy It Works
Two or three words"quick question"Looks like a real email from a colleague
Specific trigger + question"your TechCrunch piece"Specific enough to not look like spam
Shared context"re: Series B"Feels like a follow-up, not cold
Observation"your ATS setup"Relevant, not salesy
Referral hook"[mutual name] suggested I reach out"Social proof front-loaded
Role-specific"SDR team scaling"Shows you know who they are
Patterns That Kill Opens
  • ALL CAPS anything
  • Emojis in subject lines
  • Fake Re: or Fwd: (damages trust before the first word)
  • Question format ("Are you struggling with X?") — sounds like an ad
  • Company name mention ("Acme Corp: helping you achieve...")
  • Blog headline format ("5 ways to improve your...")
  • Exclamation marks

Follow-Up Strategy

Cadence
EmailSend DayGapNotes
Email 1Day 1—First touch
Email 2Day 4+3 daysNew evidence angle
Email 3Day 9+5 daysDifferent pain point
Email 4Day 16+7 daysIndustry insight
Email 5Day 25+9 daysDirect question
BreakupDay 35+10 daysClose the loop

Gaps increase over time. Persistent but not annoying.

Follow-Up Angle Rotation
Angle TypeDescriptionExample
New evidenceCase study, data point, recent result"Since my last note, we helped [Company] reduce [metric] by [%]"
Different painAlternative problem in their world"Setting aside [topic A] — are you dealing with [topic B]?"
Industry insightSomething notable about their space"Saw [industry trend]. Most teams are responding by [approach]"
Direct questionSimple ask without buildup"[Name], quick one: who handles [function] at [Company]?"
Reverse askRequest for referral"If this isn't your area, who would you point me to?"
Social proofRelevant peer doing it"[Similar company] just went through this — here's what worked"

Personalization Framework

Three Tiers of Personalization

Tier 1: Segment-Level (Minimum)

  • Industry-specific pain points
  • Company size-specific challenges
  • Role-specific language and priorities

Tier 2: Company-Level (Standard)

  • Recent company news (funding, hiring, product launch)
  • Tech stack signals (what tools they use)
  • Growth signals (job postings, office expansion)

Tier 3: Individual-Level (Premium)

  • Content they have published (posts, articles, talks)
  • Career moves (new role, promotion)
  • Shared connections or experiences
  • Specific project or initiative they are leading
Personalization Sources
SourceWhat You FindHow to Use
LinkedIn profileRole, tenure, content they shareRole-specific opener, reference their posts
Company blogPriorities, culture, technology choicesConnect your solution to their stated priorities
Job postingsGrowth areas, pain points, tech stack"You're hiring for X, which usually means..."
Press/newsFunding, partnerships, launchesTrigger-based openers
GitHub/tech blogsTechnical decisions, stack choicesTechnical relevance and credibility
Podcast/talksOpinions, expertise areas"Your point about X in [talk] resonated..."

Deliverability Setup

Infrastructure Requirements
ComponentWhatWhy
Dedicated sending domainmail.yourdomain.com or outreach.yourdomain.comProtects primary domain reputation
SPF recordDNS TXT record authorizing sending serversProves you are authorized to send
DKIM signingCryptographic signature on emailsProves emails were not modified in transit
DMARC policyDNS record specifying SPF/DKIM enforcementTells receiving servers how to handle failures
Domain warmup4-6 weeks of gradually increasing volumeBuilds sender reputation with ISPs
Warmup Schedule
WeekDaily VolumeNotes
110-20Send to engaged contacts only
220-40Mix of warm and cold contacts
340-70Begin cold outreach at low volume
470-100Monitor bounce rates closely
5-6100-150Increase if bounce rate < 3%
7+150-200 maxSteady state for cold outreach
Show full SKILL.md (1,133 more words)Show less
Deliverability Monitoring
  • Bounce rate: Keep under 3% (above 5% damages reputation)
  • Spam complaint rate: Keep under 0.1%
  • Verify email addresses before sending (use verification services)
  • Monitor blacklists monthly (MXToolbox, Google Postmaster)
  • Use mail-tester.com to check deliverability score before campaigns
Email Format Rules
  • Plain text or minimal HTML (no logos, images, or heavy formatting)
  • No tracking pixels if possible (they trigger spam filters)
  • Limit links to 1-2 maximum
  • Avoid spam trigger words: "free," "guarantee," "act now," "limited time"
  • Keep emails under 200 words
  • Include a physical address (CAN-SPAM requirement)
  • Include an unsubscribe mechanism

Compliance Requirements

CAN-SPAM (United States)

Required for all commercial email to US recipients:

  • Sender identity is clear and not misleading
  • Subject line is not deceptive
  • Physical postal address included
  • Opt-out mechanism present and functional
  • Opt-out requests honored within 10 business days
  • Message identified as an advertisement (if applicable)
GDPR (European Union)

Required for email to EU/EEA residents:

  • Legitimate interest basis documented for B2B outreach
  • Prospect data collected from lawful sources
  • Privacy notice accessible
  • Data processing records maintained
  • Right to erasure honored promptly
  • Data minimization: only collect what you need
  • No consent required for B2B if legitimate interest applies, but this must be documented and defensible
CASL (Canada)

Required for commercial electronic messages to Canadian recipients:

  • Express or implied consent documented
  • Sender identification clear
  • Unsubscribe mechanism functional
  • Implied consent valid for 2 years from last transaction or 6 months from inquiry
Best Practice Regardless of Jurisdiction
  • Always include an easy unsubscribe option
  • Honor opt-outs immediately (do not wait the legal maximum)
  • Do not buy email lists (poor quality, compliance risk)
  • Document your legal basis for outreach
  • Keep records of consent and opt-out requests

Anti-Patterns

PatternWhy It Fails
"I hope this email finds you well"Instant signal that this is templated mass outreach
"I wanted to reach out because..."Three words of nothing before saying anything
Opening with "My name is X and I work at Y"They can see your name. Start with something useful.
Feature dump in email 1Nobody cares about features when they do not trust you yet
HTML templates with logos and colorsLooks like marketing, gets spam-filtered
Fake Re:/Fwd: subject linesDeceptive, destroys trust
"Just checking in" follow-upsAdds no value, removes credibility
Social proof without context"We work with 500 companies" means nothing without relevance
Long-form case study in email 1Save it for follow-up
Passive CTAs ("Let me know if you're interested")Weak. Ask a direct question or propose a specific step.
Multiple CTAs in one emailCreates decision paralysis. One ask per email.
Sending from your primary domainRisks your entire domain reputation

Best Practices

  1. Send from a real person, not a company alias — "sarah@mail.acme.com" outperforms "sales@acme.com" every time.

  2. Read the email aloud before sending — If you hear yourself droning, cut. If it sounds like a brochure, rewrite.

  3. Time your sends — Tuesday through Thursday, 8-10 AM in the prospect's timezone, produces the highest open rates for B2B.

  4. Verify emails before campaigns — A 5% bounce rate damages your domain reputation. Verify every address.

  5. Track reply rate, not open rate — Open tracking is unreliable (privacy features block tracking pixels). Reply rate is the metric that matters.

  6. Build sequences, not individual emails — Most replies come from follow-ups, not the first email. Plan the full sequence before writing.

  7. Document your playbook — Every winning email, subject line, and angle should be documented for the team. Build institutional knowledge.

  8. Respect opt-outs immediately — Not just legally required, but professionally essential. Process within 24 hours.

  9. Rotate sending domains — Use 2-3 sending domains to distribute volume and protect reputation.

  10. Segment relentlessly — A generic template sent to 1,000 people will underperform a personalized email sent to 50 who match your ideal profile.


Integration Points

  • Copywriting — Use for landing page copy and marketing page copy. Cold email follows different constraints (shorter, personal tone, no visual design).
  • Content Strategy — Use to create content assets (case studies, guides) referenced in follow-up emails.
  • Marketing Context — Use for ICP definition and positioning. If you do not know who you are targeting and why, cold email is the wrong tool.
  • Marketing Psychology — Apply psychological principles (reciprocity, social proof, scarcity) to strengthen email messaging.
  • Campaign Analytics — Use to track sequence performance and optimize based on data.

Troubleshooting

SymptomLikely CauseFix
Open rate below 15%Subject lines too long, spammy, or genericTest 2-4 word internal-email-style subjects. Run subject_line_scorer.py.
Opens but reply rate below 1%Email body lacks relevance or CTA is too high-frictionRewrite opener about their world. Use a question CTA, not a statement.
Emails landing in spam (2026)Missing SPF/DKIM/DMARC or RFC 8058 one-click unsubscribeGmail/Yahoo/Microsoft now reject non-compliant bulk mail. Run deliverability_checker.py.
Bounce rate above 3%Unverified email list or role-based addressesVerify every address before sending. Remove catch-alls and role accounts.
Spam complaint rate above 0.10%Irrelevant targeting or too-frequent sendsGmail enforces 0.10% threshold as of 2026. Improve targeting and reduce volume per domain.
Replies but wrong outcomeCTA mismatch with funnel stageAlign CTA friction to prospect readiness. C-suite wants a question; managers accept a demo link.
Domain blacklistedSending from primary domain or too-high volumeUse dedicated sending subdomains. Warm new domains 4-6 weeks. Max 100 emails/day/address.

Success Criteria

  • Open rate consistently above 35% across sequence (benchmark: 25-40% for cold B2B)
  • Reply rate above 3% (benchmark: 2-5% for well-targeted cold outreach)
  • Bounce rate below 2% on every campaign (Gmail/Microsoft 2026 threshold)
  • Spam complaint rate below 0.10% (2026 Gmail/Yahoo hard enforcement line)
  • Deliverability rate above 95% with SPF/DKIM/DMARC/RFC 8058 fully configured
  • Sequence produces replies from emails 2-5, not just email 1 (follow-ups carry 60%+ of replies)
  • Every email under 150 words with one CTA and zero corporate speak

Scope & Limitations

In Scope:

  • B2B cold email outreach strategy and copy
  • Multi-email sequence design and optimization
  • Subject line and body copy frameworks
  • Deliverability infrastructure setup (SPF, DKIM, DMARC, domain warming)
  • CAN-SPAM, GDPR, CASL compliance guidance
  • Performance diagnosis and iteration methodology

Out of Scope:

  • Email HTML template design (use email-template-builder)
  • Marketing automation platform configuration (Outreach, Salesloft, Apollo)
  • Email list building or scraping (compliance risk)
  • Warm/inbound email sequences (use email-sequence)
  • Phone call scripts or LinkedIn outreach sequences
  • Legal advice on compliance (consult legal counsel for jurisdiction-specific requirements)

Limitations:

  • Scripts use heuristic analysis, not live inbox testing (use mail-tester.com for production validation)
  • Deliverability checker cannot perform live DNS lookups (verify SPF/DKIM/DMARC records separately)
  • Benchmarks are B2B SaaS-focused; adjust thresholds for other industries

Python Automation Tools

1. Subject Line Scorer (scripts/subject_line_scorer.py)

Scores cold email subject lines on deliverability, spam risk, and open-rate potential using deterministic heuristics.

bash
python scripts/subject_line_scorer.py "quick question"
python scripts/subject_line_scorer.py --file subjects.txt --json
2. Deliverability Checker (scripts/deliverability_checker.py)

Audits email content for spam triggers, HTML complexity, link density, and compliance against 2025-2026 Gmail/Yahoo/Microsoft requirements.

bash
python scripts/deliverability_checker.py email.txt
python scripts/deliverability_checker.py email.txt --domain yourdomain.com --json
3. Sequence Optimizer (scripts/sequence_optimizer.py)

Analyzes cold email sequence performance data against industry benchmarks. Diagnoses open rate, reply rate, bounce rate, and cadence issues.

bash
python scripts/sequence_optimizer.py sequence_data.json
python scripts/sequence_optimizer.py --sample --json

© borghei, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (scripts) in marketing/cold-email of borghei/Claude-Skills.

  • SKILL.md
  • scripts/deliverability_checker.py
  • scripts/sequence_optimizer.py
  • scripts/subject_line_scorer.py

Open the folder on GitHubat commit 4a698e8

Compare with similar skills

Cold Email next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Cold Email compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cold Email this skillborghei/Claude-Skills881—~5.7kAutomated safety check: PassMIT
Cold Outbound Optimizerericosiu/ai-marketing-skills3.6k1 repos~1.7kAutomated safety check: PassMIT
Prospectingcoreyhaines31/marketingskills54k—~4.9kAutomated safety check: PassMIT
Sales OsromangojiberryAI/gojiberryai-sales-os138—~2kAutomated safety check: PassMIT
ProspectingCesarjoquin/Marketing-Skills2001 repos~3.8kAutomated safety check: PassMIT
Cold Outreach Personalizeraiskilloftheweek/claude-ai-skill-of-the-week146—~2.6kAutomated safety check: PassNone

Similar skills

  • Cold Outbound Optimizer

    ericosiu/ai-marketing-skills

    Design, analyze, and optimize cold outbound email campaigns for Instantly.

    3.6k GitHub starsUsed in 1 repo~1.7k tokens
    Sales & SupportAuto-check passed
  • Prospecting

    coreyhaines31/marketingskills

    When the user wants to find, qualify, and build a list of prospects to reach out to, across B2B SaaS, general B2B, or local small businesses.

    54k GitHub stars~4.9k tokensUpdated today
    Sales & SupportAuto-check passed
  • Sales Os

    romangojiberryAI/gojiberryai-sales-os

    A complete outbound sales department in one skill. An agent skill from romangojiberryAI/gojiberryai-sales-os.

    138 GitHub stars~2k tokensUpdated 1 mo ago
    Sales & SupportAuto-check passed
  • Prospecting

    Cesarjoquin/Marketing-Skills

    When the user wants to find, qualify, and build a list of prospects to reach out to — across B2B SaaS, general B2B, or local small businesses.

    200 GitHub starsUsed in 1 repo~3.8k tokens
    Sales & SupportAuto-check passed
  • Cold Outreach Personalizer

    aiskilloftheweek/claude-ai-skill-of-the-week

    Generates hyper-personalized cold outreach messages (email, LinkedIn DM, connection request) from raw prospect research.

    146 GitHub stars~2.6k tokensUpdated 4 mo ago
    Sales & SupportAuto-check passed
  • Business Email Extractor

    gmapsscraper/google-maps-agent-skills

    Extract verified business email addresses from Google Maps listings.

    132 GitHub stars~1.1k tokensUpdated 4 mo ago
    Sales & SupportAuto-check passed

More from borghei/Claude-Skills

All 349 skills in this repo
  • Agents In The Team

    borghei/Claude-Skills

    Run delivery when AI coding and ops agents take tickets. An agent skill from borghei/Claude-Skills.

    881 GitHub stars~4.2k tokensUpdated today
    Auto-check passed
  • AI Content Disclosure

    borghei/Claude-Skills

    Check AI-generated marketing content and reviews for required disclosures under the EU AI Act, FTC rules and platform AI-label policies.

    881 GitHub stars~3.4k tokensUpdated today
    Auto-check passed
  • AI Prototyping

    borghei/Claude-Skills

    Idea to AI-generated prototype to customer validation to engineering handoff.

    881 GitHub stars~3.6k tokensUpdated today
    Auto-check passed
  • Analytics Engineer

    borghei/Claude-Skills

    Analytics engineering across data modeling, dbt, transformation, and semantic layers.

    881 GitHub stars~3.4k tokensUpdated today
    Auto-check passed
  • Ansoff Matrix

    borghei/Claude-Skills

    Ansoff Matrix — 4-quadrant framework for growth options: market penetration, market/product development, and diversification.

    881 GitHub stars~2.2k tokensUpdated today
    Auto-check passed
  • Brainstorm Okrs

    borghei/Claude-Skills

    OKR brainstorming and validation using the Radical Focus framework — outcome objectives, measurable key results, counter-metrics.

    881 GitHub stars~1.4k tokensUpdated today
    Auto-check passed

Categories

Questions about Cold Email

What does Cold Email do?

Write and optimize B2B cold email outreach sequences that get replies, covering personalization, follow-up cadence, deliverability, and compliance. Cold Email is an agent skill from borghei/Claude-Skills. Write and optimize B2B cold email outreach sequences that get replies, covering personalization, follow-up cadence, deliverability, and compliance.

When should I use Cold Email?

Cold Email fits situations like: writing cold outreach; prospecting/SDR emails; building outbound sequences.

How do I install Cold Email in Claude Code?

Run `npx skills add borghei/Claude-Skills --skill cold-email -a claude-code`. Or copy the skill folder (marketing/cold-email in borghei/Claude-Skills) into .claude/skills/cold-email in your project. Claude Code loads it when a task matches its description.

How do I install Cold Email in Codex?

Run `npx skills add borghei/Claude-Skills --skill cold-email -a codex`. Or copy the skill folder (marketing/cold-email in borghei/Claude-Skills) into .agents/skills/cold-email in your project. Codex loads it when a task matches its description.

Can I use Cold Email in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add borghei/Claude-Skills --skill cold-email -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cold-email, .gemini/skills/cold-email, .github/skills/cold-email and .opencode/skills/cold-email in your project.

What does Cold Email need to run?

Going by SKILL.md and its folder, Cold Email needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Cold Email access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Cold Email safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Cold Email use?

Cold Email is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Cold Email use?

About 5.7k tokens (SKILL.md is roughly 23k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Cold Email?

Skills that share tags, products or a category with Cold Email: Cold Outbound Optimizer (ericosiu/ai-marketing-skills, 3.6k stars), Prospecting (coreyhaines31/marketingskills, 54k stars), Sales Os (romangojiberryAI/gojiberryai-sales-os, 138 stars) and Prospecting (Cesarjoquin/Marketing-Skills, 200 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cold Email?

borghei (a GitHub user) maintains it in borghei/Claude-Skills, which has 881 GitHub stars. The repository holds 349 skills in this directory. The repository was last updated on October 7, 2026.

Source: borghei/Claude-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.