AGENT SKILL

suede-emails

Use when asked "build a welcome email sequence" or to design nurture, onboarding, win-back, post-purchase or trigger-based lifecycle email flows. Suede AI returns entry and exit criteria, timing, exact copy, sender-rule checks and a measurement plan. NOT FOR: cold outbound (use suede-cold-email), SMS (use suede-sms), in-product onboarding (use suede-onboarding), or broader lifecycle operations (use suede-revops).

适用职业人力资源
使用场景邮件与沟通
License 许可
Apache-2.0
最近更新
2026-11-11
Stars
★ 1.6k
Forks
474

01 前言 Front Matter

name
suede-emails
metadata
{ "version": "2.1.0", "display-name": "Suede AI Lifecycle Email Skills" }
description
Use when asked "build a welcome email sequence" or to design nurture, onboarding, win-back, post-purchase or trigger-based lifecycle email flows. Suede AI returns entry and exit criteria, timing, exact copy, sender-rule checks and a measurement plan. NOT FOR: cold outbound (use suede-cold-email), SMS (use suede-sms), in-product onboarding (use suede-onboarding), or broader lifecycle operations (use suede-revops).

02 资源文件 8

03 SKILL.md 正文

Suede AI Lifecycle Email Skills

Design lifecycle email as a consent-aware system of triggers, message roles, pacing, and measurable next actions. Create sequences that move a known audience toward value without inventing intent, exhausting the list, or confusing lifecycle messaging with cold outreach.

Compatibility

Any agent with product, consent and lifecycle context. Current deliverability checks need web access; producing a handoff does not require an email-service integration.

Initial Assessment

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.

Before creating a sequence, understand:

  1. Sequence Type

    • Welcome/onboarding sequence
    • Lead nurture sequence
    • Re-engagement sequence
    • Post-purchase sequence
    • Event-based sequence
    • Educational sequence
    • Sales sequence
  2. Audience Context

    • Who are they?
    • What triggered them into this sequence?
    • What do they already know/believe?
    • What's their current relationship with you?
    • What other emails are they already receiving?
    • What's the current email performance to beat?
  3. Goals

    • Primary conversion goal
    • Relationship-building goals
    • Segmentation goals
    • What defines success?

Core Principle

One email, one job: a single purpose and a single primary CTA per email. Everything downstream, sequence length, roles, copy, follows from that.


Email Sequence Strategy

Sequence lengths are set per type in Sequence Types Overview below; use those numbers, not a generic range. Adjust for sales-cycle length, product complexity, and relationship stage.

Timing/Delays

  • Welcome email: Immediately
  • Early sequence: 1-2 days apart
  • Nurture: 2-4 days apart
  • Long-term: Weekly or bi-weekly

Consider:

  • B2B: Avoid weekends
  • B2C: Test weekends
  • Time zones: Send at local time

Subject Line Strategy

  • Clear > Clever
  • Specific > Vague
  • Benefit or curiosity-driven
  • 40-60 characters, front-loading the words that matter for mobile truncation
  • Test emoji (they're polarizing)
  • Judge subject tests on clicks or conversions, not opens: Apple Mail Privacy Protection preloads images and inflates open rates

Patterns that work:

  • Question: "Still struggling with X?"
  • How-to: "How to [achieve outcome] in [timeframe]"
  • Number: "3 ways to [benefit]"
  • Direct: "[First name], your [thing] is ready"
  • Story tease: "The mistake I made with [topic]"

Preview Text

  • Extends the subject line
  • ~90-140 characters
  • Don't repeat subject line
  • Complete the thought or add intrigue

Sequence Types Overview

Welcome Sequence (Post-Signup)

Length: 5-7 emails over 12-14 days Goal: Activate, build trust, convert

Key emails:

  1. Welcome + deliver promised value (immediate)
  2. Quick win (day 1-2)
  3. Story/Why (day 3-4)
  4. Social proof (day 5-6)
  5. Overcome objection (day 7-8)
  6. Core feature highlight (day 9-11)
  7. Conversion (day 12-14)

Lead Nurture Sequence (Pre-Sale)

Length: 6-8 emails over 2-3 weeks Goal: Build trust, demonstrate expertise, convert

Key emails:

  1. Deliver lead magnet + intro (immediate)
  2. Expand on topic (day 2-3)
  3. Problem deep-dive (day 4-5)
  4. Solution framework (day 6-8)
  5. Case study (day 9-11)
  6. Differentiation (day 12-14)
  7. Objection handler (day 15-18)
  8. Direct offer (day 19-21)

Re-Engagement Sequence

Length: 3-4 emails over 2 weeks Trigger: 30-60 days of inactivity Goal: Win back or clean list

Key emails:

  1. Check-in (genuine concern)
  2. Value reminder (what's new)
  3. Incentive (special offer)
  4. Last chance (stay or unsubscribe)

Onboarding Sequence (Product Users)

Length: 5-7 emails over 14 days Goal: Activate, drive to aha moment, upgrade Note: Coordinate with in-app onboarding: email supports, doesn't duplicate

Key emails:

  1. Welcome + first step (immediate)
  2. Getting started help (day 1)
  3. Feature highlight (day 2-3)
  4. Success story (day 4-5)
  5. Check-in (day 7)
  6. Advanced tip (day 10-12)
  7. Upgrade/expand (day 14+)

For detailed templates: See references/sequence-templates.md


Email Types by Category

Six categories: Onboarding · Retention · Billing · Usage · Win-Back · Campaigns.

Read references/email-types.md when you need to pick or design an individual email type: it carries the trigger, timing, role, and copy pattern for each one, plus an email audit checklist.


Email Copy Guidelines

Structure

  1. Hook: First line grabs attention
  2. Context: Why this matters to them
  3. Value: The useful content
  4. CTA: What to do next
  5. Sign-off: Human, warm close

Formatting

  • Short paragraphs (1-3 sentences)
  • White space between sections
  • Bullet points for scanability
  • Bold for emphasis (sparingly)
  • Mobile-first (most read on phone)

Tone

  • Conversational, not formal
  • First-person (I/we) and second-person (you)
  • Active voice
  • Read it out loud: does it sound human?

Never ship these strings. They are the lifecycle-email defaults a model reaches for unprompted, and every one of them is a slot where a specific sentence should be:

  • "We're thrilled to have you aboard!" / "We're excited to have you!"
  • "Welcome to the family!" / "You're in good company"
  • "Here's what you can do next" / "Let's get you started"
  • "Don't miss out" / "Act now" / "Limited time only"
  • "Quick question" / "Just checking in" / "Just following up"
  • "We noticed you haven't..." / "We miss you!"
  • "Ready to take your [X] to the next level?"
  • "Unlock the full power of..." / "Supercharge your..."
  • "As a valued customer" / "We value your feedback"

The replacement is always the same shape: name the specific thing this reader did, or the specific thing they get next. If a sentence would be true for any recipient of any product, it is one of these in disguise.

Length

  • 50-125 words for transactional
  • 150-300 words for educational
  • 300-500 words for story-driven

CTA Guidelines

  • Buttons for primary actions
  • Links for secondary actions
  • One clear primary CTA per email
  • Button text: Action + outcome

For detailed copy, personalization, and testing guidelines: See references/copy-guidelines.md


Output Format

Sequence Overview

Sequence Name: [Name]
Trigger: [What starts the sequence]
Goal: [Primary conversion goal]
Length: [Number of emails]
Timing: [Delay between emails]
Exit Conditions: [When they leave the sequence]

For Each Email

Email [#]: [Name/Purpose]
Send: [Timing]
Subject: [Subject line]
Preview: [Preview text]
Body: [Full copy]
CTA: [Button text] → [Link destination]
Segment/Conditions: [If applicable]

Metrics Plan

Per email: open rate, click rate, unsubscribe rate
Per sequence: completion rate, primary-conversion rate, revenue or signups attributed
Baseline: [the user's current numbers for this audience, or "none supplied"]
Review point: [when to read results and what number would trigger a rewrite]

Pre-delivery self-check

Run this on the drafted sequence before presenting it. Each box checks a rule this skill already states, against the copy you just wrote.

  • [ ] Every email has exactly one primary CTA
  • [ ] Every subject line is 40-60 characters: count them, do not estimate
  • [ ] No preview text repeats its subject line
  • [ ] Every body is inside the word band for its type (50-125 transactional / 150-300 educational / 300-500 story-driven)
  • [ ] Exit conditions are specified for the sequence
  • [ ] No string from the Tone blocklist appears anywhere in the copy
  • [ ] The consent and suppression assumption is stated explicitly rather than assumed: say which list, which opt-in, and what excludes a contact
  • [ ] Every marketing email is marked for one-click unsubscribe (RFC 8058 headers) and the plan says unsubscribes are honored within 48 hours
  • [ ] The re-engagement or win-back flow ends by suppressing contacts who never re-engage

Any box that fails means fix it before presenting. Do not deliver the sequence with the failure noted as a caveat.


Implementation Hand-off

Choose the provider only after reading the user's installed tools and live account state. Customer.io, Mailchimp, Resend, SendGrid, Kit, and similar services may support parts of the workflow, but this public Suede skill does not assume that any provider, connector, account, or permission is available.

Before implementation, return:

  1. The required trigger, audience, fields, suppression rules, and exit criteria
  2. The provider-neutral sequence and event contract
  3. The exact account or integration that must be inspected
  4. The deliverability checklist from references/deliverability.md: SPF, DKIM, DMARC alignment, one-click unsubscribe, complaint-rate monitoring below 0.1%, and separated transactional and marketing streams. Gmail began rejecting non-compliant bulk mail more aggressively in November 2025, and Microsoft has enforced its high-volume rules since May 2025.
  5. A preview-and-approval checkpoint before any live change or send

Boundaries

  • Do not send, schedule, import contacts, alter automations, or change suppression lists without explicit authorization.
  • Do not invent consent, deliverability, attribution, audience, or performance data.
  • Do not promise inbox placement or revenue; separate observed results from projections.
  • Do not decide legal compliance, transactional classification, or contact eligibility on the user's behalf.

Routing

  • Use suede-lead-magnets for the asset that feeds a nurture sequence.
  • Use suede-churn-prevention for cancellation, save, and dunning strategy.
  • Use suede-onboarding for in-product activation and suede-copy for destination-page copy.
  • Use suede-ab-testing for sequence experiments and suede-revops for lifecycle-stage orchestration.
  • Use suede-sms when the same lifecycle program should also reach people by text: SMS layers on top of email, it does not replace it.
  • Use suede-deslop before any email in the sequence goes to a real recipient.
  • From those skills, route lifecycle sequence design, cadence, and message roles back to suede-emails.

Worked contract

Worked contract gives a bounded input, expected output and failure check for this workflow.

04 同仓库更多 Skills

hashgraph-online
hashgraph-online/awesome-codex-plugins

migrate-to-e2e

Moves an existing Playwright, Cypress, Selenium, Appium, Detox, Maestro, or TesterArmy suite to e2e one slice at a time, with the old suite running beside the new one until each ported test is proven. Keeps a MIGRATION.md progress file so any later session resumes where the last stopped. Optionally plants a defect to show both suites catch it. Use for /migrate-to-e2e, "migrate our tests to e2e", "port these Maestro flows", "move our TesterArmy tests", or when a project has an e2e config and an older suite still running.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

e2e

Writes, runs, and debugs end-to-end tests for web and mobile apps with e2e, the agentic test runner, which mixes agent.act goals with exact locator assertions on a Playwright browser or an iOS or Android device. Also drives a project's running app live over the e2e MCP server to look at a screen, check a UI change, take a screenshot or record a video, and try a locator; and runs bug bashes, parallel e2e explore runs with each bug proven by a repro test. Use when a project depends on e2e or has an e2e.config.ts, when asked for end-to-end, browser, mobile, or agentic UI tests, to check a change in the running app, to QA or bug bash an app or branch, or when an e2e run fails.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

create-verification-skill

Generate a project-local verify-<app> skill on top of e2e, so any coding agent can launch the app, check it is worth driving, exercise a feature the way a user does, keep evidence, and bug bash it. Writes the skill, a feature map with one explore charter per feature, and proves it once. Use for /create-verification-skill, "make a verification skill for this repo", or when a project has no scripted way to prove UI behavior.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

deja-search

deja-vu memory — search the user's past AI coding sessions with the deja CLI. Holds what they already settled and never wrote into the repo (naming rules, banned or already-tried tools, required checks before merge, preferred values, who owns what). Use before your first edit in a task, before you call a change done or ready to merge, before you recommend a tool, library, design or reviewer, before re-debugging an error that may already be solved, when they say 'didn't we fix this before', 'what did we decide about X' or 'I already have that', and before telling them something on this machine does not exist.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

deja-reflect

End-of-session reflection and memory curation with deja-vu. Review what was decided, what commands broke and what repaired them, and record durable project rules or decisions with deja remember so the next session starts with them.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

revid

Make, edit, export and post AI videos with Revid (revid.ai) through the Revid MCP server. Use whenever the user wants a short-form or long-form video made (from an idea, a script, a URL, an article, a PDF, a tweet, a product page, their own clips, or a song), wants to find what is going viral on TikTok, YouTube, Instagram or X before making something, wants to edit or re-export an existing Revid project, generate a standalone AI image or clip, make a series episode, or publish and schedule a finished video to connected social accounts. Covers setup (hosted MCP with OAuth, or an API key), the 36 tools, credits, polling and the rules for publishing. Routes to the more specific revid-* skills when one fits.

图像与多媒体Skill与智能体开发
★ 1.6k