본문으로 건너뛰기
cccskills
무료GitHub에 공개

suede-cold-email

Suede AI B2B cold-email discipline: evidence-based personalization with a named source for every opening line, 2-to-4-word subject lines, bodies under 75 words, one low-friction ask, bounded 3-to-5-touch follow-up sequences, and a deliverability gate built on current Gmail, Yahoo, Microsoft, and CAN-SPAM rules. Use when writing or repairing outbound email to qualified prospects. NOT FOR: building or qualifying the prospect list (use suede-prospecting), lifecycle or nurture email to opted-in contacts (use suede-emails), or broader sales collateral (use suede-sales-enablement).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

연동 도구GmailLinkedIn

실행 점수 미검증

설치 방법 보기

포함된 파일(9)

  • SKILL.md9.7 KB
  • agents/openai.yaml551 B
  • CARD.md4.5 KB
  • evals/evals.json6.9 KB
  • references/benchmarks.md6.0 KB
  • references/follow-up-sequences.md2.5 KB
  • references/frameworks.md3.8 KB
  • references/personalization.md3.0 KB
  • references/subject-lines.md1.8 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Suede AI Cold Email Writing

Use this cold-email playbook to write concise, evidence-grounded outreach that sounds human and respects the recipient.

Before Writing

Check for product marketing context first: If .agents/product-marketing.md exists (or .claude/product-marketing.md, or the legacy product-marketing-context.md filename, in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.

Understand the situation (ask if not provided):

  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 whatever the user gives you. If they have a strong signal and a clear value prop, that's enough to write. Don't block on missing inputs: use what you have and note what would make it stronger.


Writing Principles

Write like a peer, not a vendor

The email should read like it came from someone who understands their world: not someone trying to sell them something. 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. The best cold emails feel like they could have been shorter, not longer.

Personalization must connect to the problem

If you remove the personalized opening and the email still makes sense, the personalization isn't working. The observation should naturally lead into why you're reaching out.

See personalization.md for the 4-level system and research signals.

Lead with their world, not yours

The reader should see their own situation reflected back. "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 easy to say yes with a one-line reply.


Voice & Tone

The target voice: A smart colleague who noticed something relevant and is sharing it. Conversational but not sloppy. Confident but not pushy.

Calibrate to the audience:

  • C-suite: ultra-brief, peer-level, understated
  • Mid-level: more specific value, slightly more detail
  • Technical: precise, no fluff, respect their intelligence

What it should NOT sound like:

  • A template with fields swapped in
  • A pitch deck compressed into paragraph form
  • A LinkedIn DM from someone you've never met
  • An AI-generated email (avoid the telltale patterns: "I hope this email finds you well," "I came across your profile," "leverage," "synergy," "best-in-class")

Structure

There's no single right structure. Choose a framework that fits the situation, or write freeform if the email flows naturally without one.

Common shapes that work:

  • 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. We've helped similar companies with that. Curious?
  • Story → Bridge → Ask: [Similar company] had [problem]. They [solved it this way]. Relevant to you?

For the full catalog of frameworks with examples, see frameworks.md.


Subject Lines

Short, boring, internal-looking. The subject line's only job is to get the email opened: not to sell.

  • 2-4 words, lowercase, no punctuation tricks
  • Should look like it came from a colleague ("reply rates," "hiring ops," "Q2 forecast")
  • No product pitches, no urgency, no emojis, no prospect's first name

See subject-lines.md for the full data.


Follow-Up Sequences

Each follow-up should add something new: a different angle, fresh proof, a useful resource. "Just checking in" gives the reader no reason to respond.

  • 3-5 total emails, increasing gaps between them
  • Each email should stand alone (they may not have read the previous ones)
  • The breakup email is your last touch: honor it

See follow-up-sequences.md for cadence, angle rotation, and breakup email templates.


Quality Check

Run this pass on the draft before presenting it. Every item resolves to something you can observe in the text, not a feeling about it.

  • "You/your" outnumbers "I/we" in the body
  • Deleting the personalization sentence breaks the sentence that follows it
  • Exactly one ask, answerable with a one-line reply
  • Body is under 75 words
  • Zero strings from What to Avoid appear in the draft: check that list term by term, not by impression
  • Read aloud it uses contractions, and no sentence reads as marketing copy

Any item that fails means rewrite before presenting. Do not hand over a draft with a caveat attached to it.


Output Format

Deliver every email in this shape, with these field labels verbatim.

Subject: [2-4 words, lowercase]

Body: (NN words, target under 75)
[the email exactly as it would be pasted into the send tool]

CTA: [the single ask, quoted from the body]

Personalization source: [the specific signal this email traces to (the post, the filing,
the job ad, the release) with enough detail that the user can confirm it is real]

Personalization source: is required on every email. It is what makes the "do not invent personalization" boundary auditable. If you cannot name a real source, you do not have personalization, and the opening line has to change.

Emit the follow-up table only when the user asked for a sequence rather than a single message:

#Send dayNew angle it carriesSubject
10......
2+3......

3-5 emails total: see follow-up-sequences.md for cadence and angle rotation. Omit the table entirely for a single-message request.


What to Avoid

  • Opening with "I hope this email finds you well" or "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
  • Fake "Re:" or "Fwd:" subject lines
  • Identical templates with only {{FirstName}} swapped
  • Asking for 30-minute calls in first touch
  • "Just checking in" follow-ups

Deliverability Gate

Copy that lands in spam earns nothing, and a burned domain takes months to recover. When the user asks for a sequence or a send plan, state these as recommendations alongside the copy:

  • Send from a secondary domain or subdomain, never the primary domain that carries invoices and password resets.
  • SPF, DKIM, and DMARC (p=none minimum, aligned) must pass. Gmail treats close to 5,000 daily messages to personal accounts as bulk, and Microsoft enforces authentication above 5,000 a day; both reject non-compliant mail.
  • Keep the spam-complaint rate under 0.1% and never near 0.3%.
  • Include a working opt-out and a postal address (CAN-SPAM); honor opt-outs fast and permanently.
  • Verify addresses first; stop if hard bounces pass 2%.
  • Plain text, at most one link, no images or attachments on first touch.

Sources and detail: benchmarks.md.

References

Use them to inform the writing, not as a checklist to satisfy.


Boundaries

  • Do not invent personalization, mutual connections, customer facts, results, urgency, or prior contact.
  • Do not scrape prohibited data, expose sensitive personal information, or advise evasion of consent, spam, or platform rules.
  • Do not send, schedule, enroll, or follow up with anyone without explicit authorization for the exact recipients and sequence.
  • Do not decide that silence means consent; honor opt-outs and suppression lists before any execution.

Routing

  • Need a qualified prospect list -> use suede-prospecting.
  • Need lifecycle or nurture email -> use suede-emails.
  • Need positioning context or collateral -> use suede-product-marketing or suede-sales-enablement.
  • Need CRM stages, lead routing, or suppression operations -> use suede-revops.
  • Before anything goes to a real recipient -> use suede-deslop.
  • From those skills, route cold outbound message and follow-up writing back to suede-cold-email.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Suede AI Android app factory: plan, build, test, and prepare a production native Android app from product idea to a Play-ready signed bundle. Use for requests to create, ship, monetize, or modernize an Android app. Covers Kotlin and Jetpack Compose architecture, live target-API and Play policy checks, 16 KB page sizes, accessibility, privacy and Data Safety, Play Billing Library 8+, Play Integrity, account deletion, kids and Families rules, testing, performance, store assets, signing, and a release evidence gate. NOT FOR: uploading, promoting, or rolling out a build on Play (use suede-play-release); turning a website into an iOS app (use site-to-ios-app); a review-only pass on an existing app (use suede-code --findings-only); Play listing, keyword, and screenshot strategy (use suede-aso).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

JasonColapietro/suede-creator-skills1252026년 10월 24일 업데이트

Design, review, and visually QA web and app interfaces against explicit design laws so shipped screens look intentional instead of generic AI output.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

JasonColapietro/suede-creator-skills1252026년 10월 24일 업데이트

Suede AI workflow for turning a live website, PWA, dashboard, or marketplace into an iOS app. Use when the user has a site or web app and asks to put it on the App Store, wrap it in an app, ship an iOS version, or convert a PWA to native. Produces SITE_TO_IOS_AUDIT.md and SITE_TO_IOS_PLAN.md: URL audit, shell-vs-native strategy, App Store Guideline 4.2 wrapper risk and the native value that mitigates it, current SDK, privacy manifest, age rating, login and payment checks, kids-app rules, QA matrix, and a release gate. NOT FOR: Android builds or conversions (use android-app-factory); Google Play uploads and rollouts (use suede-play-release); App Store listing, keyword, and screenshot strategy (use suede-aso).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

JasonColapietro/suede-creator-skills1252026년 10월 24일 업데이트

Suede AI experimentation discipline: hypotheses, sample size and power, test duration, guardrail metrics, significance and readouts, sequential designs, and an ICE-ranked experiment backlog with a reusable playbook. Use when comparing variants, deciding whether a result is reliable, or building an experiment program and cadence. NOT FOR: analytics instrumentation (use suede-analytics), post-click conversion diagnosis (use suede-site-alchemy), writing the variant copy (use suede-copy), or channel-level incrementality and geo holdouts (use suede-attribution).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

JasonColapietro/suede-creator-skills1252026년 10월 24일 업데이트

Suede AI paid-media creative system: angles, hooks, headlines, primary text, RSA and Performance Max assets, static and motion concepts, iOS-native reveal videos, grounded batch production, client review pages, and iteration from performance data, all checked against platform character limits. Use when producing or iterating ad creative for Google, Meta, LinkedIn, TikTok, or X from real product, review, and performance inputs. NOT FOR: campaign budgets, bidding, or targeting (use suede-ads), statistical test design (use suede-ab-testing), organic social posts (use suede-social), general marketing images such as OG or hero graphics (use suede-image), or landing-page copy (use suede-copy).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

JasonColapietro/suede-creator-skills1252026년 10월 24일 업데이트

suede-ads

무료

Suede AI paid-acquisition operating system for channel choice, campaign structure, audiences, bidding, budget pacing, negative keywords, retargeting, B2B and ABM playbooks, and kill-or-scale decisions, with platform facts checked in October 2026 (Meta Andromeda and attribution windows, Performance Max controls). Use when planning, auditing, or optimizing paid campaigns on Google, Meta, LinkedIn, X, TikTok, or comparable platforms. NOT FOR: producing ad copy or creative variants (use suede-ad-creative), implementing tracking (use suede-analytics), attribution models or reconciliation (use suede-attribution), or the landing page (use suede-site-alchemy).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

JasonColapietro/suede-creator-skills1252026년 10월 24일 업데이트

JasonColapietro의 스킬 모두 보기

이 스킬의 문제 신고