Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add finsilabs/awesome-ecommerce-skills --skill customer-retention-enginegit clone --depth 1 https://github.com/finsilabs/awesome-ecommerce-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/finsilabs/awesome-ecommerce-skills/customer-retention-engine)<a href="https://agentmods.dev/skills/finsilabs/awesome-ecommerce-skills/customer-retention-engine"><img src="https://agentmods.dev/badge/skills/finsilabs/awesome-ecommerce-skills/customer-retention-engine/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/finsilabs/awesome-ecommerce-skills/customer-retention-engine"><img src="https://agentmods.dev/badge/skills/finsilabs/awesome-ecommerce-skills/customer-retention-engine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00024 | $0.02300 |
| Opus 5 | $0.00012 | $0.01150 |
| Sonnet 5 | $0.00005 | $0.00460 |
| Haiku 4.5 | $0.00002 | $0.00230 |
Grade B, and why
customer-retention-engine scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
await fetch('https://a.klaviyo.com/api/events/', { method: 'POST', How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customer Retention Engine
Overview
Acquiring a new customer costs 5–7x more than retaining an existing one. A retention engine identifies customers who show declining engagement — reduced purchase frequency, decreasing order values, browsing without buying — and intervenes with personalized campaigns before they lapse. Klaviyo and AutomateWoo can build these workflows with no custom code using predictive analytics built into the platform.
Note: For reactivating already-lapsed customers, see @win-back-reactivation. This skill focuses on proactive churn prevention before customers lapse.
When to Use This Skill
- When repeat purchase rate is declining month-over-month
- When a significant percentage of customers only ever purchase once
- When you want to proactively contact customers before they go fully dormant
- When building a post-purchase nurture program beyond the first 30 days
- When needing to identify which customers are worth offering a discount vs. which will repurchase anyway
Core Instructions
Step 1: Choose the right tool for your platform
| Platform | Recommended Tool | Why |
|---|---|---|
| Shopify | Klaviyo | Klaviyo's predictive analytics automatically calculates expected next purchase date and churn risk for every customer; no manual scoring needed |
| WooCommerce | AutomateWoo ($99/yr) | Deep WooCommerce integration, "Customer win-back" workflow type, RFM segmentation built in |
| BigCommerce | Klaviyo or Omnisend | Both integrate natively with BigCommerce order events and offer predictive churn scoring |
| Custom / Headless | Klaviyo (via API) | Send order events to Klaviyo; use their predictive analytics to identify at-risk customers |
Step 2: Define your churn threshold
Churn timing depends on your product's natural repurchase cycle:
| Product Category | Expected Repurchase Cycle | At-Risk Threshold | Churned Threshold |
|---|---|---|---|
| Consumables (skincare, supplements) | 30–60 days | 60+ days since last order | 120+ days |
| Apparel/fashion | 60–90 days | 90+ days | 180+ days |
| Home goods | 90–180 days | 180+ days | 365+ days |
| Electronics accessories | 120–365 days | 180+ days | 365+ days |
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/behavioral-triggers-measurement-and-cont/criteria.json 2.8 KB
- evals/behavioral-triggers-measurement-and-cont/task.md 1.6 KB
- evals/churn-scoring-logic-and-customer-segment/criteria.json 2.8 KB
- evals/churn-scoring-logic-and-customer-segment/task.md 1.7 KB
- evals/retention-workflow-deduplication-and-int/criteria.json 2.9 KB
- evals/retention-workflow-deduplication-and-int/task.md 1.8 KB
- tile.json 313 B
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 199 lines · 24 tokens per session scan B 83020f8ac6a9
customer-retention-engine is a skill published in the GitHub repository finsilabs/awesome-ecommerce-skills (52 stars, last pushed 6mo ago), licensed MIT. It adds 24 tokens to every session and 2,300 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (sends data to an external url). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
01-voucher-design
Thiết kế voucher phù hợp với segment user và cấp độ campaign. Ở cấp S, ít kênh hơn đồng nghĩa mechanic voucher phải tự thân vận động.
retention-check
Score client health, detect churn risk, prescribe intervention actions. Produces per-client Health Score + portfolio dashboard + intervention playbook + save-vs-let-churn economics. Feeds /case-study when clients hit wins and /email-sequence when re-engagement sequences are required. Consumes Customer Success SOP +…
churn-prevention
Reduce voluntary and involuntary churn — cancel flow design, save offers, exit surveys, dunning sequences, and payment recovery.
holiday-shopper-reactivation
Segments users who only purchase during Q4 (Black Friday/Cyber Monday) for specific holiday warm-up campaigns.
loyalty-point-breakage-estimator
Analyzes point accrual vs redemption rates. Predicts the liability reduction from expiring points this quarter.
cart-abandonment-value-segmentation
Splits cart abandoners into 'High Value' (for personal outreach) and 'Low Value' (for automated email).