Install
$ agentstack add skill-rediumvex-ai-marketing-claude-market-emails ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Market Emails — Sequence Writer
Produce full, send-ready email sequences. Every email has a purpose, every sequence has a goal, every send has a metric target.
Sequence Types
| Type | Goal | Length | Cadence | |---|---|---|---| | Welcome | Activate new signups | 5–7 emails | Day 0, 1, 3, 5, 7, (10, 14) | | Nurture | Convert warm leads to buyers | 6–8 emails | Every 2–3 days | | Launch | Drive sales for a new product | 5–7 emails | 14 days: tease → reveal → proof → urgency → cart close | | Cold outreach | Start B2B conversations | 4–6 touches | Day 0, 3, 7, 14, 21, 30 | | Cart abandon | Recover lost revenue | 3 emails | 1h, 24h, 72h | | Re-engagement | Wake inactive subscribers | 3–4 emails | Every 3–4 days | | Onboarding | Drive product activation | 5–6 emails | Triggered on signup + milestones |
Benchmarks (2024+)
| Metric | B2B | B2C | E-com | |---|---|---|---| | Open rate | 25–35% | 20–30% | 18–25% | | Click rate | 2–5% | 2–4% | 2–5% | | Reply rate (cold) | 3–10% | — | — | | Unsubscribe | <0.5% | <0.5% | <0.5% | | Cart recovery | — | — | 10–25% |
Subject line failure = open rate < benchmark. CTA failure = click rate < benchmark. Offer failure = conversion below expected.
Subject Line Formulas
| Formula | Pattern | Example | |---|---|---| | Curiosity | Tease without revealing | "The reporting mistake we all made" | | Specificity | Number + outcome | "How Jamie cut reports from 8h to 20min" | | Personal | First name + context | "{{first_name}}, a quick question" | | Contrarian | Challenge common belief | "Stop A/B testing your headlines" | | Question | Prompt self-reflection | "Is your funnel actually a funnel?" | | Urgency | Real deadline | "Last day for the 2025 rate" | | Social proof | Show outcome | "5,000 teams use this now" | | Fear of missing out | What others know | "What growth teams are doing in Q2" | | Pattern interrupt | Unexpected framing | "Ignore this if you're already ranking" | | Plain text-style | No marketing gloss | "quick question about acme" |
Always ship 3 subject line variants per email so the client can A/B test.
Pre-flight
- Load
BRAND-VOICE.mdif present; match tone. - Confirm the goal, audience, and product/offer.
- Confirm cadence and sending platform (affects formatting — Mailchimp vs SendGrid vs HubSpot all render differently).
- Ask for a "from" name and reply-to — it matters more than people think.
Email Anatomy
Every email includes:
- From name (real human preferred over "Acme Team")
- Subject line (3 variants)
- Preview text (40–90 chars, complements subject)
- Body (plain-text-friendly when possible)
- Primary CTA (1 per email; secondary only in nurture/launch)
- PS (often the second most-read line in the email)
Body structures
| Position | Function | |---|---| | Opening line | Hook — curiosity, relevance, story start. Never "Hi {{name}}, I hope this email finds you well." | | Setup | Context — why this matters to them, what they'll get | | Payoff | The actual value — insight, offer, story, proof | | CTA | Clear next step, value-driven, linked once or twice max | | Signature | Real name, human | | PS | Restate value, add urgency, or surface a secondary offer |
Compliance (do not skip)
- CAN-SPAM (US): physical address, unsubscribe link, truthful headers, honor unsubs in 10 days
- GDPR (EU): explicit consent, unsubscribe, data purpose disclosed
- CASL (Canada): express consent for cold outreach; implied consent only in narrow cases
- Cold outreach specifically: include why you're reaching out, who you are, and an easy opt-out
Every sequence output must include a compliance note stating which regions it's cleared for.
Output Format
## [Sequence Type] Email Sequence — [Brand]
**Goal:** [activation / conversion / recovery / etc]
**Audience:** [describe]
**Cadence:** [days between sends]
**Expected metrics:** [open / click / convert targets]
**Compliance:** [CAN-SPAM / GDPR / CASL cleared]
---
### Email 1: [Purpose] — Send: [Day X]
**From:** [Name]
**Subject A:** "[subject]"
**Subject B:** "[subject]"
**Subject C:** "[subject]"
**Preview:** "[40–90 char preview text]"
[Full body]
[Sign-off]
[Name]
PS: [PS line]
**Why this email:** [1-sentence rationale]
---
### Email 2: ...
Cold Outreach (special case)
Cold emails need extra care. Use this structure for every touch:
- Touch 1 (Day 0): Personal observation + specific problem + light CTA ("worth a quick chat?")
- Touch 2 (Day 3): Value drop — share an insight or resource, no ask
- Touch 3 (Day 7): Social proof — similar company outcome
- Touch 4 (Day 14): Direct ask with clear offer
- Touch 5 (Day 21): Breakup — "should I close the loop?"
- Touch 6 (Day 30, optional): New hook, different angle
Never send a 500-word first email. Cold outreach above 120 words dies.
Quality Bar
- Read every email aloud. If it sounds like a template, rewrite.
- Personalization tokens are not personalization. A real observation is.
- Never promise a discount you can't deliver. Never fake scarcity.
- If the user can't point to a real outcome or proof, the sequence will fail no matter how good the copy is — say so.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: rediumvex
- Source: rediumvex/ai-marketing-claude
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.