Install
$ agentstack add skill-0-shiv-secondstep-claude-skills-email-segmentation ✓ 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
Email Segmentation — Sub-Skill
Overview
Segmentation is the difference between batch-and-blast and precision email marketing. Segmented campaigns drive 14.31% higher open rates, 100.95% higher click rates, and 760% more revenue than non-segmented sends. This sub-skill covers RFM analysis, behavioral segmentation, engagement scoring, and lifecycle stages.
Command: /email segments
Segmentation Audit Checklist
- [ ] Subscribers are segmented beyond just "all subscribers"
- [ ] RFM model implemented (or equivalent purchase-based segmentation)
- [ ] Engagement-based segments defined (active, at-risk, dormant)
- [ ] Lifecycle stages mapped (new, active, at-risk, churned)
- [ ] Demographic segments used where relevant
- [ ] Behavioral triggers feed into segments
- [ ] Segments are updated dynamically (not static lists)
- [ ] Different content/offers sent to different segments
- [ ] Suppression segments defined (unengaged, bounced, complained)
- [ ] Segment sizes are monitored for health
1. RFM Analysis (Recency, Frequency, Monetary)
RFM is the gold standard for customer segmentation in e-commerce and subscription businesses. Score each customer on three dimensions.
Scoring Matrix
Recency — How recently did they purchase/engage?
| Score | E-commerce | SaaS/Subscription | |-------|-----------|-------------------| | 5 | Last 7 days | Active this week | | 4 | Last 30 days | Active this month | | 3 | Last 90 days | Active last quarter | | 2 | Last 180 days | Active last 6 months | | 1 | 180+ days ago | Inactive 6+ months |
Frequency — How often do they purchase/engage?
| Score | E-commerce | SaaS/Subscription | |-------|-----------|-------------------| | 5 | 10+ purchases | Daily active | | 4 | 6-9 purchases | Weekly active | | 3 | 3-5 purchases | Monthly active | | 2 | 2 purchases | Quarterly active | | 1 | 1 purchase | One-time only |
Monetary — How much do they spend?
| Score | E-commerce | SaaS/Subscription | |-------|-----------|-------------------| | 5 | Top 10% spenders | Enterprise tier | | 4 | Top 25% spenders | Pro tier | | 3 | Top 50% spenders | Growth tier | | 2 | Bottom 50% spenders | Starter tier | | 1 | Bottom 25% spenders | Free tier |
RFM Segments
| RFM Score | Segment Name | Strategy | |-----------|-------------|----------| | 555, 554, 545 | Champions | Reward, ask for reviews, refer-a-friend | | 543, 444, 435 | Loyal Customers | Upsell, cross-sell, early access | | 553, 552, 541 | Potential Loyalists | Nurture, recommend related products | | 512, 511, 422 | Recent Customers | Onboard well, encourage second purchase | | 525, 524, 433 | Promising | Incentivize next purchase, build habit | | 443, 434, 343 | Need Attention | Win back with relevant offers | | 331, 321, 312 | About to Sleep | Urgency, time-limited re-engagement | | 255, 254, 245 | Can't Lose | Win-back with best offers, personal outreach | | 155, 154, 144 | At Risk | Re-engagement or sunset | | 111, 112, 121 | Lost | Remove or final win-back attempt |
2. Behavioral Segments
Segment based on what subscribers actually do, not just who they are.
Email Engagement Segments
| Segment | Definition | Size Target | Strategy | |---------|-----------|-------------|----------| | Highly Engaged | Opened 5+ of last 10 emails | 15-25% | Send first, most content, VIP offers | | Engaged | Opened 2-4 of last 10 emails | 30-40% | Regular sends, A/B test subjects | | Passive | Opened 1 of last 10 emails | 15-20% | Reduce frequency, re-engage | | At Risk | No opens in 30-60 days | 10-15% | Win-back sequence | | Dormant | No opens in 60-90 days | 5-10% | Final win-back, then suppress | | Dead | No opens in 90+ days | <10% | Suppress from regular sends |
Website Behavior Segments
| Segment | Trigger | Email Strategy | |---------|---------|---------------| | Product Viewers | Viewed product page 2+ times | Send product-specific content | | Cart Abandoners | Added to cart but didn't purchase | Abandoned cart sequence | | Browse Abandoners | Browsed category but didn't add to cart | Category recommendations | | Content Consumers | Read 3+ blog posts | Nurture with more content | | Pricing Page Visitors | Viewed pricing page | Sales follow-up | | Feature Page Visitors | Viewed specific feature pages | Feature-specific nurture |
3. Demographic Segments
| Segment Type | Data Source | Use Case | |-------------|-----------|----------| | Geography | Signup form, IP | Localized offers, timezone-based sends | | Industry | Signup form, enrichment | Industry-specific content | | Company Size | Signup form, enrichment | Appropriate product tier recommendations | | Job Title/Role | Signup form, enrichment | Content tailored to decision-maker level | | Age/Gender | Signup form | Product recommendations | | Language | Browser, form | Localized email content |
4. Lifecycle Stages
Map every subscriber to a lifecycle stage and tailor communication accordingly.
| Stage | Definition | Email Goal | Frequency | |-------|-----------|-----------|-----------| | Subscriber | Signed up, hasn't purchased | Convert to first purchase | 2-3/week | | First-time Buyer | Made 1 purchase | Drive second purchase (critical) | 2/week | | Repeat Buyer | Made 2-3 purchases | Build loyalty, increase AOV | 1-2/week | | Loyal Customer | Made 4+ purchases or high LTV | Retain, reward, refer | 1-2/week | | VIP | Top 5% by revenue | White-glove treatment, exclusive access | 1/week | | At Risk | Engaged before but activity declining | Re-engage, incentivize | 1/week | | Lapsed | Was a buyer, hasn't purchased in 90+ days | Win-back offer | 1/2 weeks | | Churned | Lapsed 180+ days, no engagement | Final win-back or suppress | Monthly or suppress |
The Second Purchase Problem
The most critical transition is from first-time buyer to repeat buyer. Stats:
- Probability of selling to a first-time buyer again: 27%
- Probability of selling to a second-time buyer again: 45%
- Probability of selling to a third-time buyer again: 54%
Action: Create a dedicated post-first-purchase sequence focused entirely on driving the second purchase. This is the highest-leverage sequence after welcome.
5. Engagement Scoring Methodology
Assign points for every interaction to create a unified engagement score.
Point System
| Action | Points | Decay | |--------|--------|-------| | Email open | +1 | -0.5/week | | Email click | +3 | -1/week | | Website visit | +2 | -0.5/week | | Page view (product/pricing) | +5 | -1/week | | Content download | +10 | -2/week | | Form submission | +15 | -3/week | | Purchase | +25 | -5/week | | Unsubscribe click (didn't complete) | -5 | — | | Spam complaint | -50 | — | | Hard bounce | Remove | — |
Score Tiers
| Score | Tier | Action | |-------|------|--------| | 50+ | Hot | Priority sends, sales follow-up | | 25-49 | Warm | Regular cadence, nurture | | 10-24 | Cool | Reduced frequency, value-focused | | 1-9 | Cold | Re-engagement sequence | | 0 or negative | Frozen | Suppress or sunset |
Segmentation Scoring
| Criterion | Weight | Scoring | |-----------|--------|---------| | Any segmentation beyond "all" | 20% | 0 or 100 | | 3+ active segments | 15% | 0-100 | | Engagement-based segments | 20% | 0 or 100 | | Lifecycle stages mapped | 15% | 0 or 100 | | RFM or purchase-based segments | 15% | 0 or 100 | | Segments are dynamic (auto-updating) | 15% | 0 or 100 |
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: 0-shiv
- Source: 0-shiv/secondstep-claude-skills
- 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.